[go: nahoru, domu]

CN113590802A - Session content abnormity detection method and device, electronic equipment and storage medium - Google Patents

Session content abnormity detection method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113590802A
CN113590802A CN202111132641.9A CN202111132641A CN113590802A CN 113590802 A CN113590802 A CN 113590802A CN 202111132641 A CN202111132641 A CN 202111132641A CN 113590802 A CN113590802 A CN 113590802A
Authority
CN
China
Prior art keywords
session
knowledge entity
text
keyword
knowledge
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202111132641.9A
Other languages
Chinese (zh)
Other versions
CN113590802B (en
Inventor
刘雪强
舒燕
尤旸
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Mininglamp Software System Co ltd
Original Assignee
Beijing Mininglamp Software System Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Mininglamp Software System Co ltd filed Critical Beijing Mininglamp Software System Co ltd
Priority to CN202111132641.9A priority Critical patent/CN113590802B/en
Publication of CN113590802A publication Critical patent/CN113590802A/en
Application granted granted Critical
Publication of CN113590802B publication Critical patent/CN113590802B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

The application provides a method and a device for detecting session content abnormity, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring first session data in an online session between a user side and a contact side; wherein the first session data corresponds to a session text; aiming at each session text, if a business keyword exists in the session text, performing semantic analysis on the session text based on the business keyword, and identifying a first knowledge entity included in the session text; detecting the accuracy of the first knowledge entity through a second knowledge entity which is in a preset content library and corresponds to the standard of the first knowledge entity; if the accuracy of the first knowledge entity does not meet the set accuracy condition, generating prompt information according to the second knowledge entity, and sending the prompt information to the user side so that the user side can display the prompt information in a session window; the method and the device can detect the error in the session content, prompt and improve the communication efficiency.

Description

Session content abnormity detection method and device, electronic equipment and storage medium
Technical Field
The present application relates to the field of computer data processing technologies, and in particular, to a method and an apparatus for detecting session content anomaly, an electronic device, and a storage medium.
Background
With the rapid development of science and technology, the living standard is continuously improved, the requirements of people on communication efficiency are also improved, and various real-time communication forms are generated.
In the process of real-time communication, a lot of knowledge is mentioned, but when the knowledge is edited, the knowledge which the user wants to transfer is wrong due to input errors and the like. For example, the contact sends wrong knowledge to the contact, or the contact sends wrong knowledge to the contact, which requires more time for the two communication parties to explain, and reduces the communication efficiency. Therefore, a session content abnormality detection method is required.
Disclosure of Invention
In view of the above, an object of the present application is to provide a method, an apparatus, an electronic device, and a storage medium for detecting an error in session content, so as to prompt the error and improve communication efficiency.
In a first aspect, an embodiment of the present application provides a method for detecting an abnormal session content, which is applied to a server, where the server establishes an online session between a user side and a contact side in advance; the method comprises the following steps:
acquiring first session data in an online session between a user side and a contact side; wherein the first session data corresponds to a session text;
aiming at each session text, if a business keyword exists in the session text, performing semantic analysis on the session text based on the business keyword, and identifying a first knowledge entity included in the session text;
detecting the accuracy of the first knowledge entity through a second knowledge entity which is in a preset content library and corresponds to the standard of the first knowledge entity;
and if the accuracy of the first knowledge entity does not meet the set accuracy condition, generating prompt information according to the second knowledge entity, and sending the prompt information to the user side so that the user side displays the prompt information in a session window.
In a preferred technical solution of the present application, if the first session data in the online session between the user side and the contact side includes non-text data, the non-text data is converted into corresponding text data.
In a preferred technical solution of the present application, the service keyword in the session text is identified by the following method:
for each conversation text, performing word segmentation processing on the conversation text to obtain a first keyword in the conversation text;
expanding the first keyword to obtain an expanded word of the first keyword;
respectively calculating a first matching degree of the first keyword and a preset second keyword and a second matching degree of an expanded word of the first keyword and the preset second keyword;
and determining the service keywords in the session text according to the first matching degree, the second matching degree and preset matching requirements.
In a preferred technical solution of the present application, the determining the service keyword in the session text according to the first matching degree, the second matching degree and a preset matching requirement includes:
if the first matching degree meets a first requirement, taking the first keyword or the second keyword as a service keyword in the session text;
if the second matching degree meets a second requirement, taking the second keyword as a service keyword in the session text;
if the first matching degree meets a first requirement and the second matching degree meets a second requirement, taking the first key or the second key as a business key in the conversation text;
and if the first matching degree does not meet the first requirement and the second matching degree does not meet the second requirement, no service key word exists in the session text.
In a preferred technical solution of the present application, the performing semantic analysis on the session text based on the service keyword to identify a first knowledge entity included in the session text includes:
and performing semantic analysis on key sentences which are related to the service keywords and can represent the main ideas of the conversation text based on the service keywords.
In a preferred technical solution of the present application, the second knowledge entity corresponding to the standard of the first knowledge entity is determined from a preset content library by the following method:
and selecting a preset knowledge entity containing the business key words from a preset content library as a second knowledge entity corresponding to the first knowledge entity.
In a preferred technical solution of the present application, the prompt information includes a prompt that the first knowledge entity has an error, and pushes a correct second knowledge entity corresponding to the incorrect first knowledge entity or replaces the incorrect first knowledge entity with a preset correct second knowledge entity.
In a second aspect, an embodiment of the present application provides a method for detecting an abnormal session content, which is applied to a user side, where the user side provides a graphical user interface, and the graphical user interface includes a dialog window between a user and a contact; the method comprises the following steps:
displaying first session data in online sessions between a user and contacts in the session window, and sending the first session data to a server;
and receiving prompt information of the server aiming at the first session data, and displaying the prompt information.
In a preferred technical solution of the present application, the dialog window includes a session area and a prompt area; the first session data comprises second session data sent by a contact to a user, third session data already sent by the user to the contact and fourth session data edited by the user; the prompt information prompts that the first knowledge entity has errors, the first knowledge entity which is pushed and wrong corresponds to a correct second knowledge entity or a preset correct second knowledge entity is used for replacing the wrong first knowledge entity; the receiving prompt information of the server for the first session data and displaying the prompt information includes:
receiving information that the server prompts that the first knowledge entity has errors aiming at the second session data, and displaying an identifier that the first knowledge entity has errors in a session area;
receiving third session data which are sent to a contact by the server aiming at a user, prompting that the first knowledge entity has wrong information or pushing information of a correct second knowledge entity corresponding to the wrong first knowledge entity, and displaying a mark that the first knowledge entity has the wrong information in a session area or displaying the correct second knowledge entity corresponding to the wrong first knowledge entity in a prompt area;
and receiving fourth session data which is edited by the server aiming at the user, prompting the information that the first knowledge entity has errors or pushing a correct second knowledge entity corresponding to the wrong first knowledge entity, displaying an error identifier of the first knowledge entity in a session area, and displaying the correct second knowledge entity corresponding to the wrong first knowledge entity in a prompt area or displaying the correct second knowledge entity corresponding to the wrong first knowledge entity in the prompt area and replacing the wrong first knowledge entity with a preset correct second knowledge entity.
In a third aspect, an embodiment of the present application provides a device for detecting session content abnormality, where the device includes:
the acquisition module is used for acquiring first session data in online sessions between the user side and the contact side; wherein the first session data corresponds to a session text;
the recognition module is used for carrying out semantic analysis on the session text based on the service keywords if the service keywords exist in the session text and recognizing a first knowledge entity included in the session text aiming at each session text;
the detection module is used for detecting the accuracy of the first knowledge entity through a second knowledge entity which is in a preset content library and corresponds to the standard of the first knowledge entity;
and the generating module is used for generating prompt information according to the second knowledge entity if the accuracy of the first knowledge entity does not meet the set accuracy condition, and sending the prompt information to the user side so that the user side displays the prompt information in a session window.
In a fourth aspect, an embodiment of the present application provides an apparatus for detecting abnormal session content, where the apparatus resides at a user side, and the user side provides a graphical user interface, where the graphical user interface includes a dialog window between a user and a contact, and the apparatus includes:
the sending module is used for displaying first session data in online sessions between the user and the contact person in the session window and sending the first session data to the server;
and the receiving module is used for receiving the prompt message of the server aiming at the first session data and displaying the prompt message.
In a fifth aspect, an embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the session content abnormality detection method in the first aspect when executing the computer program.
In a sixth aspect, the present application provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the session content abnormality detection method in the first aspect are performed.
In a seventh aspect, an embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor, when executing the computer program, implements the steps of the session content anomaly detection method in the second aspect.
In an eighth aspect, the present application provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the session content abnormality detection method in the second aspect are performed.
The technical scheme provided by the embodiment of the application can have the following beneficial effects:
the method comprises the steps of obtaining first session data in online sessions of a user side and a contact side; wherein the first session data corresponds to a session text; then, aiming at each session text, if a service keyword exists in the session text, performing semantic analysis on the session text based on the service keyword, and identifying a first knowledge entity included in the session text; then, detecting the accuracy of the first knowledge entity through a second knowledge entity which is in a preset content library and corresponds to the standard of the first knowledge entity; finally, if the accuracy of the first knowledge entity does not meet the set accuracy condition, generating prompt information according to the second knowledge entity, and sending the prompt information to the user side so that the user side can display the prompt information in a session window; the method and the device can detect the error in the session content, prompt and improve the communication efficiency.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flowchart illustrating a session content anomaly detection method according to an embodiment of the present application;
fig. 2 is a schematic diagram illustrating another session content anomaly detection method provided in an embodiment of the present application;
fig. 3 is a schematic diagram illustrating a session content anomaly detection apparatus according to an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating another session content anomaly detection apparatus provided in an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of another electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
In the real-time communication, if errors may exist in the messages sent to the contact person, the messages sent to the contact person or the messages edited by the contact person, the messages cannot be found in time, and problems in communication can be caused.
Based on this, embodiments of the present application provide a method and an apparatus for detecting session content anomaly, an electronic device, and a storage medium, which are described below by way of embodiments.
Fig. 1 is a schematic flowchart illustrating a method for detecting session content anomaly according to an embodiment of the present application, which is applied to a server, where the server establishes an online session between a user side and a contact side in advance, where the method includes steps S101-S104; specifically, the method comprises the following steps:
s101, acquiring first session data in online sessions of a user side and a contact side; wherein the first session data corresponds to a session text;
s102, aiming at each session text, if a business keyword exists in the session text, performing semantic analysis on the session text based on the business keyword, and identifying a first knowledge entity included in the session text;
s103, detecting the accuracy of the first knowledge entity through a second knowledge entity which is in a preset content library and corresponds to the standard of the first knowledge entity;
and S104, if the accuracy of the first knowledge entity does not meet the set accuracy condition, generating prompt information according to the second knowledge entity, and sending the prompt information to the user side so that the user side can display the prompt information in the conversation window.
The method and the device can detect the error in the session content, prompt and improve the communication efficiency.
Some embodiments of the present application are described in detail below. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Before the method is implemented, a knowledge content base is established in the server, and the knowledge content base comprises the wanted knowledge and the second key words corresponding to the knowledge. When a knowledge content base is established, a storage space is divided into different attribute areas; and writing second knowledge entities corresponding to the attributes in different attribute areas respectively.
In specific implementation, the knowledge content base may include knowledge ID, knowledge release time, knowledge tag, knowledge type, knowledge creator, knowledge reference relationship, and the like. And establishing an index of the document through an Elasticissearch storage and recording the index as documentIndex. Designing a knowledge content base: building a base table, defining attributes in the base table and accessing/inputting knowledge. The attribute here may be the name, type, etc. of knowledge. The knowledge content base storage form includes but is not limited to all storage forms of data such as an offline database, an online database, a knowledge base, a knowledge graph and the like.
The knowledge entities, i.e., knowledge points in the present application include, but are not limited to, Frequently Asked Questions (FAQ), agenda, time and place, etc. attributes, files, and the like. The knowledge entities are in the form of data content in a knowledge storage form and referred to in all user sessions, such as document knowledge, question Answer (AQ) knowledge, people relation knowledge, data knowledge and the like. The knowledge entity can be a word, a word or a sentence.
S101, acquiring first session data in online sessions of a user side and a contact side; wherein the first session data corresponds to a session text.
In the embodiment of the application, the server pre-establishes the online session between the user side and the contact side, where the user side and the contact side are relatively speaking, and the user side and the contact side can be mutually converted. For example, the server establishes an online session between the a side and the B side, and when we look through the a side, the a side is the user side, and the B side is the contact side; if we look through the B-side, the B-side is the user side, and the a-side is the contact side. Like our existing real-time communication software, when we look at this side, messages sent by contacts are displayed on the left side, and messages sent by us to contacts are displayed on the right side; when the contact looks sideways, the messages we send to the contact are shown on the left side and the messages we send to are shown on the right side.
After the online session between the user side and the contact side is established in the server, the user operates through the user side and the contact operates through the contact side, and the server acquires first session data in the online session between the user side and the contact side.
The first session data generally comprises text data and non-text data, the non-text data mainly comprises picture data and voice data, and if the acquired first session data in the online session between the user side and the contact side comprises the non-text data, the non-text data is converted into corresponding text data.
S102, aiming at each conversation text, if the business keywords exist in the conversation text, performing semantic analysis on the conversation text based on the business keywords, and identifying a first knowledge entity included in the conversation text.
The method and the device aim at detecting the conversation text corresponding to the first conversation data, and can not distinguish the sentence pattern type of the conversation text. The conversation text includes statement sentences, question sentences, imperative sentences, exclamation sentences, affirmative sentences, negative sentences, question setting sentences, question reversing sentences, phrase and quilt phrases. That is, the inventive concept of the present application does not depend on the type of the conversation text, but is to determine whether the first knowledge entity in the conversation text is correct. If it is recognized that the first knowledge entity is not present in the conversation text, no subsequent determination is made as to whether the conversation text is an question or not. And finally, judging whether the first knowledge entity in the conversation text has errors or not.
When the first knowledge entity is identified in the conversation text, the business key words in the conversation text are identified, and then the first knowledge entity is identified according to the business key words.
The method identifies the service keywords in the session text in the following way:
for each conversation text, performing word segmentation processing on the conversation text to obtain a first keyword in the conversation text;
expanding the first keyword to obtain an expanded word of the first keyword;
respectively calculating a first matching degree of the first keyword and a preset second keyword and a second matching degree of an expanded word of the first keyword and the preset second keyword;
and determining the service keywords in the session text according to the first matching degree, the second matching degree and the preset matching requirement.
If the first matching degree meets the first requirement, taking the first keyword or the second keyword as a service keyword in the session text;
if the second matching degree meets a second requirement, taking the second keyword as a service keyword in the session text;
if the first matching degree meets the first requirement and the second matching degree meets the second requirement, taking the first key or the second key as a business key in the conversation text;
and if the first matching degree does not meet the first requirement and the second matching degree does not meet the second requirement, no service key word exists in the conversation text.
In the application, for each conversation text, word segmentation Processing is performed on the conversation text through Natural Language Processing (NLP) to obtain at least one first keyword corresponding to the conversation text.
The first keyword is then expanded, where the expansion includes semantic expansion and related substitution expansion. Semantic expansion characterizes expansion of the same meaning, for example, the first keyword is "happy", and the "happy" is expanded to obtain the expansion word "happy". The related replacement extension characterization uses corresponding related word replacement, for example, the current time is 2021 year 6 month 2, the session text is "yesterday is a child festival", and the related replacement extension is performed on the first keyword "yesterday" in the session text, so that the extension word of "yesterday" in the session text is "2021 year 6 month 1". As another example, English words are extended with pinyin or Chinese character related alternatives.
The method and the device respectively calculate a first matching degree of the first keyword and a preset second keyword and a second matching degree of the expanded word of the first keyword and the preset second keyword, and further determine whether a service keyword exists in a session text. The matching degree in the present application includes at least one of: text matching degree and semantic matching degree.
During comparison, if the first keyword is completely matched with a preset second keyword (including text and semantics), that is, the first keyword and the second keyword are the same word, the first keyword or the second keyword is used as a service keyword in the session text. For example, if the first keyword is "happy" and the second keyword is "happy", the "happy" is used as the service keyword in the session text.
And if the text matching degree of the first keyword and the preset second keyword meets the requirement, taking the second keyword as a service keyword in the conversation text. For example, the first keyword is "applet", the second keyword is "applet", and the first requirement is: there are five identical letters; at this time, the first matching degree of the first keyword "applet" and the second keyword "applet" satisfies the first requirement, and the second keyword is used as the service keyword in the conversation text.
And if the semantic matching degree of the first keyword and the preset second keyword meets the requirement, taking the second keyword as a service keyword in the session text. For example, if the first keyword is "happy" and the second keyword is "happy", the "happy" is used as the service keyword in the session text.
And if the expanded word of the first keyword is the same word represented by the semantic meaning of the preset second keyword, taking the second keyword as a service keyword in the conversation text. For example, if the current time is 2021 year 6 month 2, the first keyword is "yesterday", and the second keyword is "2021 year 6 month 1", then "2021 year 6 month 1" is used as the business keyword in the session text.
If the first keyword is completely matched with the preset second keyword and the expanded word of the first keyword is the same word represented by the semantics of the preset second keyword, the first keyword and the second keyword are also the same word at the moment, the first keyword can be selected as a service keyword in the session text, and the second keyword can also be selected as a service keyword in the session text.
Otherwise, the required business keywords do not exist in the session text.
When the business keyword does not exist in the session text, the first knowledge entity related to the business keyword does not exist in the session text. When the first knowledge entity does not exist in the conversation text, the conversation text is the object to be detected by the method.
After determining the service keywords in the session text, the method and the device perform semantic analysis on the session text based on the service keywords to determine a first knowledge entity in the session text.
In order to improve the processing efficiency, when the session text is subjected to semantic analysis based on the service keywords and the first knowledge entity included in the session text is identified, key sentences which are related to the service keywords and can represent the main ideas of the session text are selected from the session text.
And performing semantic analysis on key sentences which are related to the service keywords and can represent the main ideas of the conversation text based on the service keywords.
In order to improve the processing efficiency of the server, the method does not process other words and sentences irrelevant to the first knowledge entity in the conversation text, only selects key sentences relevant to the service keywords and capable of representing the main idea of the conversation text to perform semantic analysis, and determines the first knowledge entity from the key sentences.
For example, the current time is No. 5/31, the session text is "good happy, tomorrow is a child festival", and when the session text is recognized, the service keywords are recognized as "tomorrow" and "child festival". And determining that a key sentence in the conversation text is 'tomorrow is child festival' based on the business keywords 'tomorrow' and 'child festival', and then performing semantic analysis on 'tomorrow is child festival' to determine that 'tomorrow is child festival' as a first knowledge entity.
As another example, the session text is "I want to know if apple's English is apple or not apple". The conversation text is segmented to obtain first keywords of 'I', 'thinking', 'knowing', 'apple', 'English', 'yes', 'not' and 'applet'. A preset second keyword "applet". And determining that the service keyword is 'applet' by comparing the first keyword with the second keyword. And determining a key sentence in the conversation text as an applet based on the business keyword 'applet', and then determining the 'applet' as a first knowledge entity.
As another example, the conversation text is "apple in english is applet". The conversation text is segmented to obtain first keywords of apple, English, yes and applet. The preset second keywords "apple", "English", and "apple". And determining that the service keywords are apple, English and apple by comparing the first keywords with the second keywords. Based on the service keywords "apple", "English" and "applet", determining that a key sentence in the conversation text is "apple English is applet", and then determining "apple English is applet" as a first knowledge entity.
S103, detecting the accuracy of the first knowledge entity through a second knowledge entity which is in a preset content library and corresponds to the standard of the first knowledge entity.
The method and the device have the advantages that the accuracy of the first knowledge entity is detected through the second knowledge entity in the preset content base, when the accuracy of the first knowledge entity is detected, the second knowledge entity corresponding to the first knowledge entity in the standard is firstly determined from the preset content base, and then the second knowledge entity corresponding to the first knowledge entity in the standard is used for detecting the first knowledge entity.
The method comprises the steps of selecting a preset knowledge entity containing business keywords from a preset content library as a second knowledge entity corresponding to a standard of a first knowledge entity.
The method and the device screen out the second knowledge entity corresponding to the first knowledge entity in the standard from a preset content library, and then detect the first knowledge entity. Knowledge entities which do not contain business keywords in the preset content library are not used, and the detection times of the first knowledge entity are reduced.
For example, the conversation text is "apple's english is applet", the service keywords are "apple", "applet", and the first knowledge entity is "apple applet". The preset second knowledge entities are peach, apple and banana. According to the application, the preset peach and banana in the second knowledge entity are eliminated based on the fact that the business keywords are apple and apple, and the second knowledge entity which corresponds to the first knowledge entity is apple.
The second knowledge entity in the present application includes text and semantic detection when detecting the accuracy of the first knowledge entity.
And S104, if the accuracy of the first knowledge entity does not meet the set accuracy condition, generating prompt information according to the second knowledge entity, and sending the prompt information to the user side so that the user side can display the prompt information in the conversation window.
And comparing and calculating the text and the semantics of the first knowledge entity and the standard second knowledge entity to obtain the accuracy of the first knowledge entity and the standard second knowledge entity.
If the accuracy of the first knowledge entity and the second knowledge entity of the standard is greater than or equal to the accuracy preset threshold, the fact that the first knowledge entity and the second knowledge entity of the standard are characterized by the same fact is indicated.
If the accuracy of the first knowledge entity and the second knowledge entity of the standard is smaller than a preset threshold, the deviation between the first knowledge entity and the second knowledge entity of the standard is indicated, and the first knowledge entity is considered to have errors.
When the first knowledge entity has errors, the server generates prompt information according to the correct second knowledge entity. The prompt message prompts the first knowledge entity to have an error, pushes a correct second knowledge entity corresponding to the incorrect first knowledge entity, or replaces the incorrect first knowledge entity with a preset correct second knowledge entity.
For example, if the first knowledge entity is "apple english is applet", and the second knowledge entity is "apple english is applet", the accuracy threshold is one hundred percent, where the accuracy refers to text accuracy, the accuracy of the first knowledge entity and the second knowledge entity is less than the accuracy preset threshold, and there is an error in the first knowledge entity.
As another example, the current time is 2021 year 6 month 2, the first knowledge entity is "yesterday is a child's day", the second knowledge entity is "2021 year 6 month 1 is a child's day", the accuracy threshold is one hundred percent, where the accuracy threshold is semantic accuracy, the accuracy of the first knowledge entity and the second knowledge entity is equal to the accuracy preset threshold, and there is no error in the first knowledge entity.
In the embodiment of the present application, as an optional embodiment, as shown in fig. 2, the present application further provides another method for detecting an abnormal session content, which is applied to a user side, where the user side provides a graphical user interface, and the graphical user interface includes a dialog window between a user and a contact; the method comprises the following steps:
s201, displaying first session data in online session between a user and a contact in a session window, and sending the first session data to a server;
s202, receiving prompt information of the server aiming at the first session data, and displaying the prompt information.
The dialog window comprises a conversation area and a prompt area; the first session data comprises second session data sent by the contact to the user, third session data already sent by the user to the contact and fourth session data being edited by the user; the prompt information includes prompting that the first knowledge entity has an error, pushing a second knowledge entity corresponding to the error first knowledge entity or replacing the error first knowledge entity with a preset correct second knowledge entity;
the user side receives the prompt message of the server aiming at the first session data and displays the prompt message, and the prompt message comprises:
the receiving server prompts the first knowledge entity that the error exists according to the second session data, and displays the identification that the error exists in the first knowledge entity in the session area;
the receiving server prompts the first knowledge entity to have wrong information or pushes the information of a correct second knowledge entity corresponding to the wrong first knowledge entity aiming at third session data which is sent to the contact by the user, and displays a mark that the first knowledge entity has the wrong information in a session area or displays the correct second knowledge entity corresponding to the wrong first knowledge entity in a prompt area;
and the receiving server prompts the first knowledge entity to have wrong information or pushes a second knowledge entity which corresponds to the wrong first knowledge entity and has a wrong identifier in the session area according to fourth session data which is edited by the user, and displays the second knowledge entity which corresponds to the wrong first knowledge entity in the prompt area or displays the second knowledge entity which corresponds to the wrong first knowledge entity in the prompt area and replaces the wrong first knowledge entity with a preset correct second knowledge entity.
The contact terminal responds to the operation of the contact and sends the related content keyed in by the contact to the server, the server sends the second session data sent by the contact to the user terminal, and the user terminal displays the second session data sent by the contact to the user in the session area. If the server detects that the first knowledge entity with the error exists in the second session data, the server sends a prompt message for the first knowledge entity with the error in the second session data to the user side, and the user side displays the prompt message of the server for the first knowledge entity with the error in the second session data in the session area. The prompt message aiming at the first knowledge entity with the error in the second session data is a message prompting that the first knowledge entity has the error. In specific implementation, the first knowledge entity may be indicated by highlighting, marked by underlining, or by a special symbol, and the way of indicating that the first knowledge entity has the wrong information is not specifically limited.
And the user side responds to the operation of the user and sends the third session data to the contact side through the server. The user terminal also displays third session data that the user has sent to the contact in the session area. If the server detects that the first knowledge entity with the error exists in the third session data, the server sends a prompt message for the first knowledge entity with the error in the third session data to the user side, and the user side displays the prompt message for the first knowledge entity with the error in the second session data in the session area. The prompting method here is the same as the prompting method of the first knowledge entity having the error in the second session data, and is not described in detail here. The third conversation data of the first knowledge entity with the error is displayed with correct content besides error prompt. If the server detects that the wrong first knowledge entity exists in the third session data, the server sends a correct second knowledge entity corresponding to the wrong first knowledge entity to the user side, and the user side displays the received correct second knowledge entity in the prompt area;
according to the method and the device, for the fourth session data which is being edited by the user, if the server detects that the first knowledge entity with the error exists in the fourth session data, besides the prompt information and the display information which are the same as those of the third session data, a replacement function is provided. If the server detects that the wrong first knowledge entity exists in the fourth session data, the user side displays a correct second knowledge entity corresponding to the wrong first knowledge entity and a replacement identifier for replacing the wrong first knowledge entity with the preset correct second knowledge entity in the prompt area, and the user can replace the wrong first knowledge entity being edited with the correct second knowledge entity corresponding to the wrong first knowledge entity by clicking the replacement identifier, so that the wrong first knowledge entity is effectively prevented from being sent to the contact person, and the communication efficiency is improved.
The method and the device solve the problem that in online conversation communication, the contact person sends unclear knowledge content to cause that the contact person cannot answer, and can inquire the mentioned knowledge content in real time.
The problem that in online conversation communication, when people communicate with contacts, information is inconsistent with information in a preset content library or information is wrong, and the contacts are troubled is solved. The accuracy matching and error prompt of the knowledge which is consistent with the current system when the user answers or edits the knowledge content for the contact can be inquired.
The problem that a user cannot refer or send correct knowledge to a contact person because the user uses wrong knowledge content in online conversation communication is solved.
Fig. 3 is a schematic structural diagram illustrating a session content anomaly detection apparatus provided in an embodiment of the present application, where the apparatus includes:
the acquisition module is used for acquiring first session data in online sessions between the user side and the contact side; wherein the first session data corresponds to a session text;
the recognition module is used for carrying out semantic analysis on the session text based on the service keywords if the service keywords exist in the session text and recognizing a first knowledge entity included in the session text aiming at each session text;
the detection module is used for detecting the accuracy of the first knowledge entity through a second knowledge entity which is in a preset content library and corresponds to the standard of the first knowledge entity;
and the generating module is used for generating prompt information according to the second knowledge entity if the accuracy of the first knowledge entity does not meet the set accuracy condition, and sending the prompt information to the user side so that the user side can display the prompt information in the session window.
The obtaining module, when being used for obtaining first session data in an online session between a user side and a contact side, includes: and if the first session data in the online session between the user side and the contact side comprises the non-text data, converting the non-text data into corresponding text data.
The identification module, when used for identifying the service keyword in the session text, includes: for each conversation text, performing word segmentation processing on the conversation text to obtain a first keyword in the conversation text;
expanding the first keyword to obtain an expanded word of the first keyword;
respectively calculating a first matching degree of the first keyword and a preset second keyword and a second matching degree of an expanded word of the first keyword and the preset second keyword;
and determining the service keywords in the session text according to the first matching degree, the second matching degree and the preset matching requirement.
Determining a service keyword in the session text according to the first matching degree, the second matching degree and a preset matching requirement, wherein the step of determining the service keyword comprises the following steps:
if the first matching degree meets the first requirement, taking the first keyword or the second keyword as a service keyword in the session text;
if the second matching degree meets a second requirement, taking the second keyword as a service keyword in the session text;
if the first matching degree meets the first requirement and the second matching degree meets the second requirement, taking the first key or the second key as a business key in the conversation text;
and if the first matching degree does not meet the first requirement and the second matching degree does not meet the second requirement, no service key word exists in the conversation text.
Performing semantic analysis on the session text based on the service keywords, and identifying a first knowledge entity included in the session text, including:
and performing semantic analysis on key sentences which are related to the service keywords and can represent the main ideas of the conversation text based on the service keywords.
The detection module, when being used for determining a second knowledge entity corresponding to the standard of the first knowledge entity from a preset content library, comprises: and selecting a preset knowledge entity containing the business key words from a preset content library as a second knowledge entity of the corresponding standard of the first knowledge entity.
Fig. 4 is a schematic structural diagram illustrating a session content anomaly detection apparatus provided in an embodiment of the present application, where the apparatus includes:
the sending module is used for displaying first session data in online sessions between the user and the contact person in the session window and sending the first session data to the server;
and the receiving module is used for receiving the prompt message of the server aiming at the first session data and displaying the prompt message.
The receiving module is used for displaying the prompt information, and the conversation window comprises a conversation area and a prompt area; the first session data comprises second session data sent by the contact to the user, third session data already sent by the user to the contact and fourth session data being edited by the user; the prompt information includes prompting that the first knowledge entity has an error, pushing a second knowledge entity corresponding to the error first knowledge entity or replacing the error first knowledge entity with a preset correct second knowledge entity; receiving prompt information of the server aiming at the first session data, and displaying the prompt information, wherein the prompt information comprises:
the receiving server prompts the first knowledge entity that the error exists according to the second session data, and displays the identification that the error exists in the first knowledge entity in the session area;
the receiving server prompts the first knowledge entity to have wrong information or pushes the information of a correct second knowledge entity corresponding to the wrong first knowledge entity aiming at third session data which is sent to the contact by the user, and displays a mark that the first knowledge entity has the wrong information in a session area or displays the correct second knowledge entity corresponding to the wrong first knowledge entity in a prompt area;
and the receiving server prompts the first knowledge entity to have wrong information or pushes a second knowledge entity which corresponds to the wrong first knowledge entity and has a wrong identifier in the session area according to fourth session data which is edited by the user, and displays the second knowledge entity which corresponds to the wrong first knowledge entity in the prompt area or displays the second knowledge entity which corresponds to the wrong first knowledge entity in the prompt area and replaces the wrong first knowledge entity with a preset correct second knowledge entity.
As shown in fig. 5, an embodiment of the present application provides an electronic device 800, where the electronic device 800 includes: the device comprises a processor 801, a memory 802 and a bus, wherein the memory 802 stores machine-readable instructions executable by the processor 801, when an electronic device runs, the processor 801 communicates with the memory 802 through the bus, and the processor 801 executes the machine-readable instructions for executing the session content abnormality detection method in the first embodiment of the present application.
Specifically, the memory 802 and the processor 801 may be general-purpose memory and processor, which are not limited in particular, and when the processor runs a computer program stored in the memory, the session content abnormality detection method described above can be executed.
Corresponding to the session content anomaly detection method in the first embodiment of the present application, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to perform the steps of the session content anomaly detection method described above.
Specifically, the storage medium can be a general-purpose storage medium, such as a removable disk, a hard disk, or the like, and when the computer program on the storage medium is executed, the above-mentioned session content abnormality detection method can be executed.
As shown in fig. 6, an embodiment of the present application provides an electronic device 900, where the electronic device 900 includes: the session content anomaly detection device comprises a processor 901, a memory 902 and a bus, wherein the memory 902 stores machine-readable instructions executable by the processor 901, when the electronic device runs, the processor 901 communicates with the memory 902 through the bus, and the processor 901 executes the machine-readable instructions for executing the session content anomaly detection method in the second embodiment of the application.
Specifically, the memory 902 and the processor 901 may be general-purpose memory and processor, which are not limited in particular, and when the processor runs a computer program stored in the memory, the session content abnormality detection method described above can be executed.
Corresponding to the session content anomaly detection method in the second embodiment of the present application, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to perform the steps of the session content anomaly detection method.
Specifically, the storage medium can be a general-purpose storage medium, such as a removable disk, a hard disk, or the like, and when the computer program on the storage medium is executed, the above-mentioned session content abnormality detection method can be executed.
In the embodiments provided in the present application, it should be understood that the disclosed system and method may be implemented in other ways. The above-described system embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and there may be other divisions in actual implementation, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of systems or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus once an item is defined in one figure, it need not be further defined and explained in subsequent figures, and moreover, the terms "first", "second", "third", etc. are used merely to distinguish one description from another and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the present disclosure, which should be construed in light of the above teachings. Are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (15)

1. A method for detecting abnormal conversation content is characterized in that the method is applied to a server, and the server establishes an online conversation between a user side and a contact side in advance; the method comprises the following steps:
acquiring first session data in an online session between a user side and a contact side; wherein the first session data corresponds to a session text;
aiming at each session text, if a business keyword exists in the session text, performing semantic analysis on the session text based on the business keyword, and identifying a first knowledge entity included in the session text;
detecting the accuracy of the first knowledge entity through a second knowledge entity which is in a preset content library and corresponds to the standard of the first knowledge entity;
and if the accuracy of the first knowledge entity does not meet the set accuracy condition, generating prompt information according to the second knowledge entity, and sending the prompt information to the user side so that the user side displays the prompt information in a session window.
2. The method according to claim 1, wherein if the first session data in the online session between the user side and the contact side includes non-text data, the non-text data is converted into corresponding text data.
3. The method of claim 1, wherein the service keywords are identified in the session text by:
for each conversation text, performing word segmentation processing on the conversation text to obtain a first keyword in the conversation text;
expanding the first keyword to obtain an expanded word of the first keyword;
respectively calculating a first matching degree of the first keyword and a preset second keyword and a second matching degree of an expanded word of the first keyword and the preset second keyword;
and determining the service keywords in the session text according to the first matching degree, the second matching degree and preset matching requirements.
4. The method according to claim 3, wherein the determining the service keyword in the session text according to the first matching degree, the second matching degree and a preset matching requirement comprises:
if the first matching degree meets a first requirement, taking the first keyword or the second keyword as a service keyword in the session text;
if the second matching degree meets a second requirement, taking the second keyword as a service keyword in the session text;
if the first matching degree meets a first requirement and the second matching degree meets a second requirement, taking the first key or the second key as a business key in the conversation text;
and if the first matching degree does not meet the first requirement and the second matching degree does not meet the second requirement, no service key word exists in the session text.
5. The method of claim 1, wherein the semantic analyzing the session text based on the service keyword, and identifying a first knowledge entity included in the session text comprises:
and performing semantic analysis on key sentences which are related to the service keywords and can represent the main ideas of the conversation text based on the service keywords.
6. The method of claim 1, wherein the second knowledge entity corresponding to the first knowledge entity is determined from a predetermined content library by:
and selecting a preset knowledge entity containing the business key words from a preset content library as a second knowledge entity corresponding to the first knowledge entity.
7. The method of claim 1, wherein the prompting message comprises prompting the first knowledge entity that there is an error, pushing a correct second knowledge entity corresponding to the incorrect first knowledge entity, or replacing the incorrect first knowledge entity with a preset correct second knowledge entity.
8. The method for detecting the abnormal conversation content is characterized by being applied to a user side, wherein the user side provides a graphical user interface, and the graphical user interface comprises a conversation window of a user and a contact person; the method comprises the following steps:
displaying first session data in online sessions between a user and contacts in the session window, and sending the first session data to a server;
and receiving prompt information of the server aiming at the first session data, and displaying the prompt information.
9. The method of claim 8, wherein the dialog window comprises a conversation region and a prompt region; the first session data comprises second session data sent by a contact to a user, third session data already sent by the user to the contact and fourth session data edited by the user; the prompt information prompts that the first knowledge entity has errors, the first knowledge entity which is pushed and wrong corresponds to a correct second knowledge entity or a preset correct second knowledge entity is used for replacing the wrong first knowledge entity; the receiving prompt information of the server for the first session data and displaying the prompt information includes:
receiving information that the server prompts that the first knowledge entity has errors aiming at the second session data, and displaying an identifier that the first knowledge entity has errors in a session area;
receiving third session data which are sent to a contact by the server aiming at a user, prompting that the first knowledge entity has wrong information or pushing information of a correct second knowledge entity corresponding to the wrong first knowledge entity, and displaying a mark that the first knowledge entity has the wrong information in a session area or displaying the correct second knowledge entity corresponding to the wrong first knowledge entity in a prompt area;
and receiving fourth session data which is edited by the server aiming at the user, prompting the information that the first knowledge entity has errors or pushing a correct second knowledge entity corresponding to the wrong first knowledge entity, displaying an error identifier of the first knowledge entity in a session area, and displaying the correct second knowledge entity corresponding to the wrong first knowledge entity in a prompt area or displaying the correct second knowledge entity corresponding to the wrong first knowledge entity in the prompt area and replacing the wrong first knowledge entity with a preset correct second knowledge entity.
10. An apparatus for detecting abnormality in session content, the apparatus comprising:
the acquisition module is used for acquiring first session data in online sessions between the user side and the contact side; wherein the first session data corresponds to a session text;
the recognition module is used for carrying out semantic analysis on the session text based on the service keywords if the service keywords exist in the session text and recognizing a first knowledge entity included in the session text aiming at each session text;
the detection module is used for detecting the accuracy of the first knowledge entity through a second knowledge entity which is in a preset content library and corresponds to the standard of the first knowledge entity;
and the generating module is used for generating prompt information according to the second knowledge entity if the accuracy of the first knowledge entity does not meet the set accuracy condition, and sending the prompt information to the user side so that the user side displays the prompt information in a session window.
11. An apparatus for detecting abnormal content of a conversation, the apparatus residing at a user side, the user side providing a graphical user interface, the graphical user interface including a dialog window between a user and a contact, the apparatus comprising:
the sending module is used for displaying first session data in online sessions between the user and the contact person in the session window and sending the first session data to the server;
and the receiving module is used for receiving the prompt message of the server aiming at the first session data and displaying the prompt message.
12. An electronic device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is operating, the machine-readable instructions when executed by the processor performing the steps of the session content anomaly detection method according to any one of claims 1 to 7.
13. A computer-readable storage medium, having stored thereon a computer program for performing, when executed by a processor, the steps of the session content anomaly detection method according to any one of claims 1 to 7.
14. An electronic device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is operating, the machine-readable instructions when executed by the processor performing the steps of the session content anomaly detection method according to any one of claims 8 to 9.
15. A computer-readable storage medium, having stored thereon a computer program for performing, when being executed by a processor, the steps of the session content anomaly detection method according to any one of claims 8 to 9.
CN202111132641.9A 2021-09-27 2021-09-27 Session content abnormity detection method and device, electronic equipment and storage medium Active CN113590802B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111132641.9A CN113590802B (en) 2021-09-27 2021-09-27 Session content abnormity detection method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111132641.9A CN113590802B (en) 2021-09-27 2021-09-27 Session content abnormity detection method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113590802A true CN113590802A (en) 2021-11-02
CN113590802B CN113590802B (en) 2021-12-28

Family

ID=78242315

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111132641.9A Active CN113590802B (en) 2021-09-27 2021-09-27 Session content abnormity detection method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113590802B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115955451A (en) * 2023-03-09 2023-04-11 广东维信智联科技有限公司 Online session information safety monitoring system
CN116112265A (en) * 2023-02-13 2023-05-12 山东云天安全技术有限公司 Abnormal session determining method, electronic equipment and storage medium
CN116976359A (en) * 2023-09-22 2023-10-31 太仓市律点信息技术有限公司 Abnormality detection report analysis method, server and medium for online service session

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7149970B1 (en) * 2000-06-23 2006-12-12 Microsoft Corporation Method and system for filtering and selecting from a candidate list generated by a stochastic input method
CN108595708A (en) * 2018-05-10 2018-09-28 北京航空航天大学 A kind of exception information file classification method of knowledge based collection of illustrative plates
CN109947265A (en) * 2019-03-14 2019-06-28 百度在线网络技术（北京）有限公司 Processing method and processing device, server and the computer-readable medium of session text
CN110825865A (en) * 2020-01-09 2020-02-21 浩鲸云计算科技股份有限公司 Multi-round conversation intelligent customer service system based on special word correction and cold start
CN111444318A (en) * 2020-04-08 2020-07-24 厦门快商通科技股份有限公司 Text error correction method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7149970B1 (en) * 2000-06-23 2006-12-12 Microsoft Corporation Method and system for filtering and selecting from a candidate list generated by a stochastic input method
CN108595708A (en) * 2018-05-10 2018-09-28 北京航空航天大学 A kind of exception information file classification method of knowledge based collection of illustrative plates
CN109947265A (en) * 2019-03-14 2019-06-28 百度在线网络技术（北京）有限公司 Processing method and processing device, server and the computer-readable medium of session text
CN110825865A (en) * 2020-01-09 2020-02-21 浩鲸云计算科技股份有限公司 Multi-round conversation intelligent customer service system based on special word correction and cold start
CN111444318A (en) * 2020-04-08 2020-07-24 厦门快商通科技股份有限公司 Text error correction method

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116112265A (en) * 2023-02-13 2023-05-12 山东云天安全技术有限公司 Abnormal session determining method, electronic equipment and storage medium
CN116112265B (en) * 2023-02-13 2023-07-28 山东云天安全技术有限公司 Abnormal session determining method, electronic equipment and storage medium
CN115955451A (en) * 2023-03-09 2023-04-11 广东维信智联科技有限公司 Online session information safety monitoring system
CN115955451B (en) * 2023-03-09 2023-07-14 广东维信智联科技有限公司 Online session information security monitoring system
CN116976359A (en) * 2023-09-22 2023-10-31 太仓市律点信息技术有限公司 Abnormality detection report analysis method, server and medium for online service session
CN116976359B (en) * 2023-09-22 2023-11-24 太仓市律点信息技术有限公司 Abnormality detection report analysis method, server and medium for online service session

Also Published As

Publication number Publication date
CN113590802B (en) 2021-12-28

Similar Documents

Publication Publication Date Title
CN113590802B (en) Session content abnormity detection method and device, electronic equipment and storage medium
US10515156B2 (en) Human-to-human conversation analysis
US8694304B2 (en) Semantic clustering and user interfaces
US20120089394A1 (en) Visual Display of Semantic Information
US20130253910A1 (en) Systems and Methods for Analyzing Digital Communications
CN108062955B (en) Intelligent report generation method, system and equipment
US20110238408A1 (en) Semantic Clustering
US20140200891A1 (en) Semantic Graphs and Conversational Agents
CN111666746A (en) Method and device for generating conference summary, electronic equipment and storage medium
CN110598645A (en) Method for rapidly repairing fault and risk of information system
CN113379398B (en) Project requirement generation method and device, electronic equipment and storage medium
EP2673687A2 (en) Visual display of semantic information
CN111737424A (en) Question matching method, device, equipment and storage medium
US10803247B2 (en) Intelligent content detection
CN107908792B (en) Information pushing method and device
CN114220113A (en) Paper quality detection method, device and equipment
CN114297380A (en) Data processing method, device, equipment and storage medium
CN113158629A (en) Information processing apparatus, recording medium, and information processing method
CN113836288B (en) Method and device for determining service detection result and electronic equipment
CN117851575B (en) Large language model question-answer optimization method and device, electronic equipment and storage medium
JP2014038565A (en) Document management device and program
CN111126052B (en) Function point generation method, device, electronic equipment and computer readable storage medium
CN109359181B (en) Negative emotion reason identification method, device and computer-readable storage medium
CN114169307A (en) Information validity verification method, device, equipment and storage medium of input information
CN112069268A (en) Text error recognition method and system based on semantic relevance

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant