CN109726372B - Method and device for generating work order based on call records and computer readable medium - Google Patents
Method and device for generating work order based on call records and computer readable medium Download PDFInfo
- Publication number
- CN109726372B CN109726372B CN201711043042.3A CN201711043042A CN109726372B CN 109726372 B CN109726372 B CN 109726372B CN 201711043042 A CN201711043042 A CN 201711043042A CN 109726372 B CN109726372 B CN 109726372B
- Authority
- CN
- China
- Prior art keywords
- client
- text information
- customer service
- call
- customer
- 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.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Machine Translation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a device for generating a work order based on call records and a computer readable medium. The method comprises the following steps: according to the call text information of the client and the customer service, acquiring basic information of the client; generating a problem form and a customer service answering form of a customer according to the call text information and a pre-trained form generation model; and generating a work sheet based on the call records according to the basic information of the client, the problem form of the client and the answer form of the customer service. According to the technical scheme, the work order based on the call records can be automatically generated, and compared with the manual filling work order in the prior art, the work order generation method and the work order generation device can save time and labor and effectively improve the work order generation efficiency.
Description
[ field of technology ]
The present invention relates to the field of computer application technologies, and in particular, to a method and apparatus for generating a work order based on call records, and a computer readable medium.
[ background Art ]
In order to provide better services for users, many service institutions provide customer service platforms, provide customer hotlines to listen to problems and advice of customers, and provide solutions for customers in time.
In the existing customer service platforms, most of the customer service platforms are realized by adopting manual customer service. The manual customer service answers the incoming call of the customer, acquires the basic information of the customer in the call recording process of the customer, listens to the problem of the customer and records the problem of the customer. There is also a need to provide solutions to customers and record the solutions provided to customers. And based on the problems, the work order of the customer service is filled in manually.
However, in the prior art, the manual filling of customer service personnel is required in the whole process of the customer service work orders, so that the generation process of the work orders in the prior art is time-consuming and labor-consuming, and the generation efficiency is low.
[ invention ]
The invention provides a method and a device for generating a work order based on call records and a computer readable medium, which are used for improving the work order generation efficiency.
The invention provides a method for generating a work order based on call records, which comprises the following steps:
according to the call text information of the customer and customer service, acquiring basic information of the customer;
generating a problem form of the client and a solution form of the customer service according to the call text information and a pre-trained form generation model;
and generating a work order based on call records according to the basic information of the client, the problem form of the client and the answer form of the customer service.
Further optionally, in the method as described above, before the basic information of the client is obtained according to the call text information of the client and the customer service, the method further includes:
monitoring voice call records of clients and customer service;
and carrying out voice recognition on the voice call record to obtain the call text information of the client and the customer service.
Further optionally, in the method as described above, the obtaining basic information of the client according to call text information of the client and customer service specifically includes:
acquiring the identity information of the client in a preset format from the call text information;
and acquiring the basic information of the client from a user information base according to the identity information of the client.
Further optionally, in the method as described above, generating the problem form of the customer and the answer form of the customer service according to the call text information and a pre-trained form generation model specifically includes:
respectively extracting first call text information of the client and second call text information of the customer service from the call text information;
mapping the problem form of the client according to the first call text information and the form generation model;
And mapping the answer form of the customer service according to the second conversation text information and the form generation model.
Further optionally, in the method as described above, mapping the problem form of the client according to the first call text information and the form generation model specifically includes:
word segmentation processing is carried out on the first call text information, and a plurality of first word segments are obtained;
generating a first word segmentation feature expression corresponding to the first call text information according to the plurality of first word segmentation and a preset dictionary;
inputting the first word segmentation feature expression into the form generation model, so that the form generation model outputs a problem form of the client;
further, according to the second session text information and the form generation model, mapping the answer form of the customer service specifically includes:
word segmentation processing is carried out on the second conversation text information, so that a plurality of second words are obtained;
generating a second word segmentation feature expression corresponding to the second conversation text information according to the plurality of second word segments and the dictionary;
and inputting the second word segmentation feature expression into the form generation model, so that the form generation model outputs a solution form of the customer service.
Further optionally, in the method as described above, before generating the problem form of the customer and the answer form of the customer service according to the call text information and a pre-trained form generation model, the method further includes:
collecting a plurality of pieces of training data, wherein each piece of training data comprises: training call text information of a training client and a training customer service, a known problem form of the training client and a known answer form of the training customer service;
and training the form generation model according to each piece of training data.
The invention provides a device for generating a work order based on call records, which comprises the following components:
the client information acquisition module is used for acquiring basic information of a client according to call text information of the client and customer service;
the form generation module is used for generating a problem form of the client and a solution form of the customer service according to the call text information and a pre-trained form generation model;
and the work order generation module is used for generating a work order based on call records according to the basic information of the client, the problem form of the client and the answer form of the customer service.
Further optionally, in the apparatus as described above, further includes:
The monitoring module is used for monitoring the voice call records of the clients and the customer service;
and the voice recognition module is used for carrying out voice recognition on the voice call record to obtain the call text information of the customer and the customer service.
Further optionally, in the apparatus as described above, the client information obtaining module is specifically configured to:
acquiring the identity information of the client in a preset format from the call text information;
and acquiring the basic information of the client from a user information base according to the identity information of the client.
Further alternatively, in the apparatus as described above, the form generating module includes:
the information extraction unit is used for respectively extracting the first call text information of the client and the second call text information of the customer service from the call text information;
the problem form mapping unit is used for mapping the problem form of the client according to the first call text information and the form generation model;
and the answer form mapping unit is used for mapping the answer form of the customer service according to the second conversation text information and the form generation model.
Further optionally, in the apparatus as described above, the problem form mapping unit is specifically configured to:
Word segmentation processing is carried out on the first call text information, and a plurality of first word segments are obtained;
generating a first word segmentation feature expression corresponding to the first call text information according to the plurality of first word segmentation and a preset dictionary;
inputting the first word segmentation feature expression into the form generation model, so that the form generation model outputs a problem form of the client;
further, the solution form mapping unit is specifically configured to:
word segmentation processing is carried out on the second conversation text information, so that a plurality of second words are obtained;
generating a second word segmentation feature expression corresponding to the second conversation text information according to the plurality of second word segments and the dictionary;
and inputting the second word segmentation feature expression into the form generation model, so that the form generation model outputs a solution form of the customer service.
Further, the solution form mapping unit is specifically configured to:
word segmentation processing is carried out on the second conversation text information, so that a plurality of second words are obtained;
generating a second word segmentation feature expression corresponding to the second conversation text information according to the plurality of second word segments and the dictionary;
And inputting the second word segmentation feature expression into the form generation model, so that the form generation model outputs a solution form of the customer service.
Further optionally, in the apparatus as described above, further includes:
the acquisition module is used for acquiring a plurality of pieces of training data, and each piece of training data comprises: training call text information of a training client and a training customer service, a known problem form of the training client and a known answer form of the training customer service;
and the training module is used for training the form generation model according to each piece of training data.
The present invention also provides a computer device comprising:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the call log based worksheet generation method described above.
The present invention also provides a computer-readable medium having stored thereon a computer program which, when executed by a processor, implements a method of generating a call log-based work order as described above.
According to the method, the device and the computer readable medium for generating the work order based on the call records, basic information of a client is obtained according to call text information of the client and customer service; generating a problem form and a customer service answering form of a customer according to the call text information and a pre-trained form generation model; and generating a work sheet based on the call records according to the basic information of the client, the problem form of the client and the answer form of the customer service. According to the technical scheme, the work order based on the call records can be automatically generated, and compared with the manual filling work order in the prior art, the work order generation method and the work order generation device can save time and labor and effectively improve the work order generation efficiency.
[ description of the drawings ]
Fig. 1 is a flowchart of a first embodiment of a method for generating a work order based on call records according to the present invention.
Fig. 2 is a flowchart of a second embodiment of a method for generating a work order based on call records according to the present invention.
Fig. 3 is a block diagram of a first embodiment of a call log-based work order generation apparatus according to the present invention.
Fig. 4 is a block diagram of a second embodiment of a call log-based work order generation apparatus according to the present invention.
Fig. 5 is a block diagram of an embodiment of a computer device of the present invention.
Fig. 6 is an exemplary diagram of a computer device provided by the present invention.
[ detailed description ] of the invention
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
Fig. 1 is a flowchart of a first embodiment of a method for generating a work order based on call records according to the present invention. As shown in fig. 1, the method for generating a work order based on call records in this embodiment may specifically include the following steps:
100. according to the call text information of the client and the customer service, acquiring basic information of the client;
the execution main body of the call record-based work order generation method in this embodiment is a call record-based work order generation device, and the call record-based work order generation device may be disposed on a customer service platform side of a service provider, so as to be capable of helping customer service to automatically generate a work order based on call records, and omitting customer service personnel to manually generate the work order.
In practical application, when a customer consults with customer service, the customer consults with information about services that the customer enjoys, for example, a customer buying financial resources consults with problems related to financial resources. The customer applying the loan may consult the loan-related questions. In order to facilitate the improvement of customer service quality and the accurate positioning of the customer, the customer service can inquire the identification information of the customer, such as the identification information of the customer, which can be uniquely identified by an identification card number, a mobile phone number or a mailbox, etc. And then the customer service can acquire the product purchased by the user from the user information base of the service provider according to the identity information of the user, so that the problem of the user can be conveniently positioned, the problem of the user can be more clearly understood, and more accurate answers can be provided for the user. Based on the above, it can be known that the call text information of the customer and the customer service generally includes the identification information of the customer, and in practical application, the identification information of the customer can be directly used as the basic information of the customer and recorded in the work order.
In addition, because the identity information of the client can be an identity card number, a mobile phone number or a mailbox which all have a certain format, for example, the identity card number and the mobile phone number respectively have preset lengths, the mailbox has a preset special format, and the identity information of the client can be easily obtained from the call text information according to the specificity of the identity information. For example, in this embodiment, the obtaining basic information of the client according to the call text information of the client and the customer service may specifically include: the identification information of the client is obtained from the call text information, and the identification information of the client is used as the basic information of the client.
Or the basic information of the customer in the work order may include richer information. At this time, according to the call text information of the customer and the customer service, the basic information of the customer is obtained, which may specifically include: acquiring the identity information of a client in a preset format from call text information; and acquiring the basic information of the client from the user information base according to the identity information of the client. The user information base here is in particular a user information base of a service provider, in which all information of all clients of the service provider can be recorded, but of course also identification information of the clients. Such as customer name, identification number, mailbox, purchased service product, etc.
101. Generating a problem form and a customer service answering form of a customer according to the call text information and a pre-trained form generation model;
in this embodiment, the pre-trained form generation model may be obtained by training a deep learning strategy by using a neural network model as a prototype. Thus, the trained form generation model is utilized to identify the call text information, and the problem insurance policy and customer service answering form of the customer are obtained.
102. And generating a work sheet based on the call records according to the basic information of the client, the problem form of the client and the answer form of the customer service.
For example, the acquired basic information of the customer, the problem form of the customer and the solution form of the customer service are input into a work form template together, and the corresponding positions are filled in, so that the work form based on the call records can be automatically generated.
According to the method for generating the work order based on the call records, basic information of a client is obtained according to call text information of the client and customer service; generating a problem form and a customer service answering form of a customer according to the call text information and a pre-trained form generation model; and generating a work sheet based on the call records according to the basic information of the client, the problem form of the client and the answer form of the customer service. According to the technical scheme, the work order based on the call records can be automatically generated, compared with the manual filling work order in the prior art, the time and labor can be saved, and the generation efficiency of the work order can be effectively improved.
In addition, in the prior art, customer service personnel not only need to listen to the problem of the customer in the conversation with the customer, and provide a solution for the customer, but also need to manually fill in the work order, and the problem that the recorded information is lost, so that the customer is incompletely recorded can be solved.
In addition, in the prior art, customer service personnel not only need to listen to the problem of the customer in the conversation with the customer, so as to provide a solution for the customer, but also need to manually fill in a work order, thus leading the customer service personnel to be unable to concentrate on understanding and processing the problem of the customer and leading to the reduction of the service level of the customer service. The technical scheme of the embodiment can automatically generate the work order, can enable the customer personnel to listen to the customer's problems in a concentrated manner, and can provide a solution for the customer without processing the writing of the work order, thereby effectively improving the service capacity of customer service and enhancing the experience of the customer.
Fig. 2 is a flowchart of a second embodiment of a method for generating a work order based on call records according to the present invention. The method for generating a work order based on call records in this embodiment further describes the technical scheme of the present invention in more detail on the basis of the technical scheme of the embodiment shown in fig. 1. As shown in fig. 2, the method for generating a work order based on call records in this embodiment may specifically include the following steps:
200. monitoring voice call records of clients and customer service;
the device for generating the work order based on the call records is arranged on the customer service platform side of the service provider, and can monitor the voice call records of each customer and customer service.
201. Performing voice recognition on the voice call records to obtain call text information of clients and customer service;
in this embodiment, the worksheet generating device based on the call records may perform voice recognition on the voice call records, and convert the voice call records into call text information.
202. Acquiring the identity information of a client in a preset format from call text information;
203. acquiring basic information of a client from a user information base according to the identity information of the client;
similarly, the identification information of the client in this embodiment may be an identification card number, a mobile phone number or a mailbox of the client, and the implementation of steps 202 and 203 may refer to the related description of the embodiment shown in fig. 1, which is not repeated herein.
204. Respectively extracting first call text information of a customer and second call text information of customer service from the call text information;
specifically, the voices of different people have different voice characteristics, and in this embodiment, different marks can be made during voice recognition of the people with different voice characteristics when voice recognition is performed on the voice call records, that is, call text information of clients and customer services are distinguished by using different marks. Thus, the first call text information of the customer and the second call text information of the customer service can be extracted from all call text information.
205. Generating a model according to the first call text information and a pre-trained form, and mapping a problem form of a client;
for example, the step 205 may specifically include the following steps:
(a1) Word segmentation processing is carried out on the first call text information, and a plurality of first word segments are obtained;
(b1) Generating a first word segmentation feature expression corresponding to the first call text information according to the plurality of first word segments and a preset dictionary;
(c1) And inputting the first word segmentation feature expression into a form generation model, so that the form generation model outputs a problem form of a client.
In this embodiment, the first call text information of the client may be subjected to word segmentation, and specifically, the first call text information may be subjected to word segmentation by adopting an existing word segmentation policy. In this embodiment, a dictionary may be preset, where the dictionary may include all words covering questions and solutions of all products of the service provider, so that it may be ensured that a word in a question of a client can hit a word in the dictionary. The number of words included in the dictionary must be large enough.
And then, arranging innumerable words in the dictionary in sequence, and establishing a feature vector with the size equal to the number of words in the dictionary, wherein each position in the feature vector corresponds to one word in the dictionary. And then sequentially analyzing whether each first word obtained by word segmentation of the first call text information hits a word in a dictionary, if so, setting an element at a position corresponding to the first word in the feature vector as 1, otherwise, setting the element at the position as 0, and obtaining the feature expression of the first word. Or further normalizing the first word segmentation feature expression, and inputting the normalized first word segmentation feature expression into a form generation model, so that the form generation model outputs a problem form of a client. Because each first word in the first call text information can represent a question of a client, a question form of the client can be mapped according to a trained form generation model based on the first call text information.
In addition, optionally, when normalizing the feature expression of the first word segment, the feature vector may be normalized according to the occurrence frequency of each first word segment, so that the value of the element corresponding to the position of the first word segment with high occurrence frequency is greater than the value of the element corresponding to the position of the first word segment with low occurrence frequency.
206. Generating a model according to the second conversation text information and the pre-trained form, and mapping the answer form of the customer service;
for example, the step 206 may specifically include the following steps:
(a2) Word segmentation processing is carried out on the second conversation text information, and a plurality of second words are obtained;
(b2) Generating a second word segmentation feature expression corresponding to the second dialogue text information according to the plurality of second word segmentation and the dictionary;
(c2) And inputting the second word characteristic expression into a form generation model, so that the form generation model outputs a customer service solution form.
The specific implementation process of steps (a 2) - (c 2) may be implemented by referring to the implementation principles of steps (a 1) - (c 1), and detailed descriptions of the related embodiments are omitted here.
207. And generating a work sheet based on the call records according to the basic information of the client, the problem form of the client and the answer form of the customer service.
And finally, inputting the acquired basic information of the client, the problem form of the client and the answer form of the customer service into a work form template together, and filling the corresponding position, so that the work form based on the call record can be automatically generated.
According to the method for generating the work order based on the call records, the work order based on the call records can be automatically generated by adopting the technical scheme, and compared with the manual filling work order in the prior art, the time and labor can be saved, and the generation efficiency of the work order can be effectively improved.
It should be noted that, before step 101 in the embodiment shown in fig. 1 and step 205 in the embodiment shown in fig. 2, the method may specifically further include the following steps:
(a3) Collecting a plurality of pieces of training data, wherein each piece of training data comprises: training call text information of training clients and training customer service, a known problem form of the training clients and a known answer form of the training customer service;
(b3) And generating a model according to each training data by training the form.
For example, the number of training data collected in this embodiment may reach more than 1560 ten thousand, and the more the number of training data collected, the more accurate the problem form and the answer form of customer service are mapped by the training form generation model.
Before training, a prototype of a form generation model is selected, and initial values are given to parameters in the form generation model. Aiming at the training call text information of the training clients and the training customer service in each piece of training data, the training call text information of the training clients and the training call text information of the training customer service can be obtained. According to the training call text information of the training clients of each piece of training data and a preset dictionary, word segmentation feature expressions of each training client are obtained, and according to the training call text information of the training customer service of each piece of training data and the preset dictionary, word segmentation feature expressions of each training customer service are obtained, and the detailed reference can be made to the first word segmentation feature expression and the second word segmentation feature expression obtaining mode in the embodiment respectively.
And then inputting word segmentation characteristic expressions of training clients of each training data into a form generation model, and outputting predicted problem forms of the training clients by the corresponding form generation model. Detecting a predicted problem form for the training client, comparing the predicted problem form with the known problem form for the training client, and if the predicted problem form for the training client does not match the known problem form for the training client, adjusting parameters of a form generation model such that the predicted problem form for the training client tends to the known problem form for the training client. And then continuing training, inputting word segmentation feature expression of training customer service of the training data into a form generation model, and outputting a predicted answer form of the training customer service by the corresponding form generation model. Detecting a predicted solution form of the training customer service, comparing the predicted solution form of the training customer service with a known solution form of the training customer service, and if the predicted solution form of the training customer service is inconsistent with the known solution form of the training customer service, continuing to adjust parameters of a form generation model so that the predicted solution form of the training customer service tends to the known solution form of the training customer service. And training each piece of training data in the mode, and adjusting parameters of the form generation model until the predicted problem form output by the form generation model is consistent with the known problem form, and the output predicted solution form is consistent with the known solution form, so that the parameters of the form generation model are determined, and the form generation model is determined.
In addition, optionally, the problem form of the customer trained in the above embodiment and the solution form of the customer service are implemented by using the same form generation model. In practical applications, two form generation models, such as a form generation model for a problem form and a form generation model for a solution form, may also be trained in the manner of the above embodiments. For example, when training, only training call text information of a training client is used to train a form generation model of a problem form. And training the form generation model of the answer form by using only training call text information of the training customer service. And then respectively using the call text information of the customer and the form generation model of the problem form, mapping the problem form of the customer, using the call text information of the customer service and the form generation model of the solution form, and mapping the solution form of the customer service, wherein details of the solution form of the customer service can be referred to the description of the embodiment and are not repeated.
Fig. 3 is a block diagram of a first embodiment of a call log-based work order generation apparatus according to the present invention. As shown in fig. 3, the generating device of the work order based on the call record in this embodiment may specifically include:
the client information acquisition module 10 acquires basic information of a client according to call text information of the client and customer service;
The form generation module 11 generates a problem form and a customer service answering form of a customer according to the call text information and a pre-trained form generation model;
the work order generation module 12 generates a work order based on call records based on the basic information of the customer acquired by the customer information acquisition module 10, the problem form of the customer and the answer form of the customer service generated by the form generation module 11.
The implementation principle and the technical effect of the call record-based work order generation device in this embodiment are the same as those of the related method embodiments, and detailed description of the related method embodiments may be referred to herein and will not be repeated.
Fig. 4 is a block diagram of a second embodiment of a call log-based work order generation apparatus according to the present invention. As shown in fig. 4, the apparatus for generating a work order based on call records according to the present embodiment further describes the technical scheme of the present invention in more detail based on the technical scheme of the embodiment shown in fig. 3.
As shown in fig. 4, the apparatus for generating a work order based on call records according to the present embodiment further includes:
the monitoring module 13 is used for monitoring the voice call records of the clients and the customer service;
The voice recognition module 14 is used for performing voice recognition on the voice call records to obtain call text information of clients and customer services.
Correspondingly, the client information acquisition module 10 acquires basic information of the client according to the call text information of the client and customer service, which is identified by the voice identification module 14;
the form generation module 11 generates a problem form and a customer service answering form of the customer according to the call text information obtained by the recognition of the voice recognition module 14 and a pre-trained form generation model;
further alternatively, in the call record-based work order generation apparatus of the present embodiment, the client information acquisition module 10 is specifically configured to:
acquiring the identity information of a client in a preset format from call text information;
and acquiring the basic information of the client from the user information base according to the identity information of the client.
As a further alternative, as shown in fig. 4, in the apparatus for generating a work order based on call records of the present embodiment, the form generating module 11 includes:
the information extraction unit 111 is configured to extract first call text information of a client and second call text information of a customer service from the call text information obtained by the recognition of the voice recognition module 14, respectively;
the question form mapping unit 112 is configured to map a question form of a client according to the first call text information and the form generation model extracted by the information extracting unit 111;
The answer form mapping unit 113 is configured to map an answer form of the customer service according to the second session text information and the form generation model extracted by the information extraction unit 111.
Further alternatively, in the call record-based worksheet generating device of the present embodiment, the problem form mapping unit 112 is specifically configured to:
word segmentation processing is performed on the first call text information extracted by the information extraction unit 111, so as to obtain a plurality of first word segments;
generating a first word segmentation feature expression corresponding to the first call text information according to the plurality of first word segments and a preset dictionary;
inputting the first word segmentation feature expression into a form generation model, so that the form generation model outputs a problem form of a client;
further, the solution form mapping unit 113 is specifically configured to:
word segmentation processing is performed on the second text message extracted by the information extraction unit 111 to obtain a plurality of second words;
generating a second word segmentation feature expression corresponding to the second dialogue text information according to the plurality of second word segmentation and the dictionary;
and inputting the second word characteristic expression into a form generation model, so that the form generation model outputs a customer service solution form.
Further alternatively, as shown in fig. 4, the apparatus for generating a work order based on call records in this embodiment further includes:
The acquisition module 15 is configured to acquire a plurality of pieces of training data, where each piece of training data includes: training call text information of training clients and training customer service, a known problem form of the training clients and a known answer form of the training customer service;
the training module 16 is configured to train the form generation model according to each piece of training data collected by the collection module 15.
Correspondingly, the question form mapping unit 112 is configured to map a question form of the client according to the first call text information extracted by the information extracting unit 111 and the form generation model trained by the training module 16;
the answer form mapping unit 113 is configured to map the answer form of the customer service according to the second text information of the conversation extracted by the information extracting unit 111 and the form generation model trained by the training module 16.
The implementation principle and the technical effect of the call record-based work order generation device in this embodiment are the same as those of the related method embodiments, and detailed description of the related method embodiments may be referred to herein and will not be repeated.
Fig. 5 is a block diagram of an embodiment of a computer device of the present invention. As shown in fig. 5, the computer device of the present embodiment includes: the system comprises one or more processors 30 and a memory 40, wherein the memory 40 is used for storing one or more programs, and when the one or more programs stored in the memory 40 are executed by the one or more processors 30, the one or more processors 30 implement the method for generating a work order based on call records according to the embodiment shown in fig. 1-2. The embodiment shown in fig. 5 is exemplified as including a plurality of processors 30.
For example, fig. 6 is an exemplary diagram of a computer device provided by the present invention. FIG. 6 illustrates a block diagram of an exemplary computer device 12a suitable for use in implementing embodiments of the present invention. The computer device 12a shown in fig. 6 is only an example and should not be construed as limiting the functionality and scope of use of embodiments of the invention.
As shown in fig. 6, the computer device 12a is in the form of a general purpose computing device. Components of computer device 12a may include, but are not limited to: one or more processors 16a, a system memory 28a, and a bus 18a that connects the different system components, including the system memory 28a and the processor 16 a.
The system memory 28a may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30a and/or cache memory 32a. The computer device 12a may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34a may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard disk drive"). Although not shown in fig. 6, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be coupled to bus 18a through one or more data medium interfaces. The system memory 28a may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the embodiments of the invention described above with respect to fig. 1-4.
A program/utility 40a having a set (at least one) of program modules 42a may be stored in, for example, system memory 28a, such program modules 42a including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42a generally perform the functions and/or methods of the embodiments of fig. 1-4 described above for the present invention.
The computer device 12a may also communicate with one or more external devices 14a (e.g., keyboard, pointing device, display 24a, etc.), one or more devices that enable a user to interact with the computer device 12a, and/or any devices (e.g., network card, modem, etc.) that enable the computer device 12a to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22 a. Also, the computer device 12a may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through a network adapter 20 a. As shown, network adapter 20a communicates with other modules of computer device 12a over bus 18 a. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with computer device 12a, including, but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processor 16a executes a program stored in the system memory 28a to perform various functional applications and data processing, for example, to implement the call record-based work order generation method shown in the above-described embodiment.
The present invention also provides a computer-readable medium having stored thereon a computer program which, when executed by a processor, implements a method of generating a call record-based work order as shown in the above-described embodiments.
The computer readable medium of this embodiment may include RAM30a, and/or cache memory 32a, and/or storage system 34a in system memory 28a in the embodiment shown in fig. 6, described above.
With the development of technology, the propagation path of the computer program is no longer limited to a tangible medium, but may be directly downloaded from a network or obtained in other manners. Thus, the computer readable medium in this embodiment may include not only tangible media but also intangible media.
The computer-readable medium of the present embodiment may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
In the several embodiments provided in the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is merely a logical function division, and there may be other manners of division when actually implemented.
The units described as separate units may or may not be physically separate, and units shown 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 may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in hardware plus software functional units.
The integrated units implemented in the form of software functional units described above may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform part of the steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather to enable any modification, equivalent replacement, improvement or the like to be made within the spirit and principles of the invention.
Claims (14)
1. A method for generating a work order based on call records is characterized by comprising the following steps:
according to the call text information of the customer and customer service, acquiring basic information of the customer;
generating a problem form of the client and a solution form of the customer service according to the call text information and a pre-trained form generation model;
generating a work order based on call records according to the basic information of the client, the problem form of the client and the answer form of the customer service;
generating a work order based on call records according to the basic information of the client, the problem form of the client and the answer form of the customer service, wherein the work order comprises the following steps:
filling the basic information of the client, the problem form of the client and the solution form of the customer service into corresponding positions in a work form template respectively to generate a work form based on call records;
generating a problem form of the client and a solution form of the customer service according to the call text information and a pre-trained form generation model, wherein the method comprises the following steps:
Mapping a problem form of a client according to first call text information of the client extracted from the call text information and the form generation model;
generating a model according to second call text information of customer service extracted from the call text information and the form, and mapping a solution form of the customer service;
according to the first call text information of the customer extracted from the call text information and the form generation model, mapping the problem form of the customer, specifically comprising:
word segmentation processing is carried out on the first call text information, and a plurality of first word segments are obtained;
generating a first word segmentation feature expression corresponding to the first call text information according to the plurality of first word segmentation and a preset dictionary;
and inputting the first word segmentation feature expression into the form generation model, so that the form generation model outputs the problem form of the client.
2. The method of claim 1, wherein prior to obtaining the basic information of the customer based on the text information of the call between the customer and the customer service, the method further comprises:
monitoring voice call records of clients and customer service;
and carrying out voice recognition on the voice call record to obtain the call text information of the client and the customer service.
3. The method of claim 1, wherein the obtaining basic information of the customer according to the call text information of the customer and the customer service specifically comprises:
acquiring the identity information of the client in a preset format from the call text information;
and acquiring the basic information of the client from a user information base according to the identity information of the client.
4. A method according to any one of claims 1-3, characterized in that before mapping the problem form of the customer based on the first call text information of the customer extracted from the call text information and the form generation model, further comprises:
and respectively extracting the first call text information of the client and the second call text information of the customer service from the call text information.
5. The method according to claim 1, wherein mapping the solution form of the customer service based on the second call text information of the customer service extracted from the call text information and the form generation model specifically comprises:
word segmentation processing is carried out on the second conversation text information, so that a plurality of second words are obtained;
generating a second word segmentation feature expression corresponding to the second conversation text information according to the plurality of second word segments and the dictionary;
And inputting the second word segmentation feature expression into the form generation model, so that the form generation model outputs a solution form of the customer service.
6. The method of claim 1, wherein prior to generating the customer's question form and the customer service's answer form based on the call text information and a pre-trained form generation model, the method further comprises:
collecting a plurality of pieces of training data, wherein each piece of training data comprises: training call text information of a training client and a training customer service, a known problem form of the training client and a known answer form of the training customer service;
and training the form generation model according to each piece of training data.
7. A device for generating a work order based on call records, the device comprising:
the client information acquisition module is used for acquiring basic information of a client according to call text information of the client and customer service;
the form generation module is used for generating a problem form of the client and a solution form of the customer service according to the call text information and a pre-trained form generation model;
the work order generation module is used for generating a work order based on call records according to the basic information of the client, the problem form of the client and the answer form of the customer service;
The work order generation module is used for respectively filling the basic information of the client, the problem form of the client and the solution form of the customer service into the corresponding positions in the work order template to generate a work order based on call records;
the form generation module comprises:
a question form mapping unit, configured to map a question form of a client according to first call text information of the client extracted from the call text information and the form generation model;
a solution form mapping unit for mapping the solution form of the customer service according to the second call text information of the customer service extracted from the call text information and the form generation model;
the problem form mapping unit is used for:
word segmentation processing is carried out on the first call text information, and a plurality of first word segments are obtained;
generating a first word segmentation feature expression corresponding to the first call text information according to the plurality of first word segmentation and a preset dictionary;
and inputting the first word segmentation feature expression into the form generation model, so that the form generation model outputs the problem form of the client.
8. The apparatus of claim 7, wherein the apparatus further comprises:
The monitoring module is used for monitoring the voice call records of the clients and the customer service;
and the voice recognition module is used for carrying out voice recognition on the voice call record to obtain the call text information of the customer and the customer service.
9. The apparatus of claim 7, wherein the client information acquisition module is specifically configured to:
acquiring the identity information of the client in a preset format from the call text information;
and acquiring the basic information of the client from a user information base according to the identity information of the client.
10. The apparatus of any of claims 7-9, wherein the form generation module further comprises:
and the information extraction unit is used for respectively extracting the first call text information of the client and the second call text information of the customer service from the call text information.
11. The apparatus according to claim 10, wherein the solution form mapping unit is specifically configured to:
word segmentation processing is carried out on the second conversation text information, so that a plurality of second words are obtained;
generating a second word segmentation feature expression corresponding to the second conversation text information according to the plurality of second word segments and the dictionary;
And inputting the second word segmentation feature expression into the form generation model, so that the form generation model outputs a solution form of the customer service.
12. The apparatus of claim 7, wherein the apparatus further comprises:
the acquisition module is used for acquiring a plurality of pieces of training data, and each piece of training data comprises: training call text information of a training client and a training customer service, a known problem form of the training client and a known answer form of the training customer service;
and the training module is used for training the form generation model according to each piece of training data.
13. A computer device, the device comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-6.
14. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711043042.3A CN109726372B (en) | 2017-10-31 | 2017-10-31 | Method and device for generating work order based on call records and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711043042.3A CN109726372B (en) | 2017-10-31 | 2017-10-31 | Method and device for generating work order based on call records and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109726372A CN109726372A (en) | 2019-05-07 |
| CN109726372B true CN109726372B (en) | 2023-06-30 |
Family
ID=66293076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711043042.3A Active CN109726372B (en) | 2017-10-31 | 2017-10-31 | Method and device for generating work order based on call records and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109726372B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110225210A (en) * | 2019-06-18 | 2019-09-10 | 北京智合大方科技有限公司 | Based on call abstract Auto-writing work order method and system |
| CN110689357B (en) * | 2019-09-23 | 2022-08-26 | 四川新网银行股份有限公司 | Work order generation method for online customer service based on machine learning |
| CN111859913B (en) * | 2020-06-12 | 2024-04-12 | 北京百度网讯科技有限公司 | Processing method and device of wind control characteristic factors, electronic equipment and storage medium |
| CN111835921A (en) * | 2020-07-16 | 2020-10-27 | 普强时代(珠海横琴)信息技术有限公司 | Real-time automatic telephone traffic summary system and method |
| CN112434501B (en) * | 2020-10-23 | 2024-07-02 | 杭州未名信科科技有限公司 | Method, device, electronic equipment and medium for intelligent generation of worksheet |
| CN112686674A (en) * | 2020-12-25 | 2021-04-20 | 科讯嘉联信息技术有限公司 | Customer service conversation work order summarizing method |
| CN115098090B (en) * | 2022-06-15 | 2024-07-05 | 马上消费金融股份有限公司 | Form generation method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6640210B1 (en) * | 1999-11-12 | 2003-10-28 | Frederick Anthony Schaefer | Customer service operation using wav files |
| US7907705B1 (en) * | 2006-10-10 | 2011-03-15 | Intuit Inc. | Speech to text for assisted form completion |
| CN102456344A (en) * | 2010-10-22 | 2012-05-16 | 中国电信股份有限公司 | System and method for analyzing customer behavior characteristic based on speech recognition technique |
| US9191476B1 (en) * | 2009-01-08 | 2015-11-17 | Amdocs Software Systems Limited | System, method, and computer program for speech recognition assisted call center and self service interface |
| CN106572230A (en) * | 2016-10-31 | 2017-04-19 | 努比亚技术有限公司 | Device and method for recording calls |
| CN106874134A (en) * | 2017-01-22 | 2017-06-20 | 国网新疆电力公司信息通信公司 | The processing method of work order type, apparatus and system |
| CN107230142A (en) * | 2017-07-12 | 2017-10-03 | 陈维龙 | Method and device, method of commerce and system based on speech production order |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7660779B2 (en) * | 2004-05-12 | 2010-02-09 | Microsoft Corporation | Intelligent autofill |
| US20060129532A1 (en) * | 2004-12-13 | 2006-06-15 | Taiwan Semiconductor Manufacturing Co., Ltd. | Form generation system and method |
| WO2006116796A1 (en) * | 2005-04-29 | 2006-11-09 | Steven James Mitchell | Automatic audio content creation and delivery system |
| CN101242452B (en) * | 2007-02-05 | 2013-01-23 | 国际商业机器公司 | Method and system for automatic generation and provision of sound document |
| US9123254B2 (en) * | 2012-06-07 | 2015-09-01 | Xerox Corporation | Method and system for managing surveys |
| US9137345B2 (en) * | 2012-09-13 | 2015-09-15 | Unify Gmbh & Co. Kg | Apparatus and method for audio data processing |
| CN104202491B (en) * | 2014-09-25 | 2017-03-22 | 北京橙鑫数据科技有限公司 | Method for handling customer service telephone call and device thereof |
| CN104580477A (en) * | 2015-01-14 | 2015-04-29 | 百度在线网络技术（北京）有限公司 | Voice data processing method and device |
| US9723149B2 (en) * | 2015-08-21 | 2017-08-01 | Samsung Electronics Co., Ltd. | Assistant redirection for customer service agent processing |
| US9691070B2 (en) * | 2015-09-01 | 2017-06-27 | Echostar Technologies L.L.C. | Automated voice-based customer service |
| CN105224662A (en) * | 2015-09-30 | 2016-01-06 | 北京奇虎科技有限公司 | Worksheet method and apparatus |
| JP6604836B2 (en) * | 2015-12-14 | 2019-11-13 | 株式会社日立製作所 | Dialog text summarization apparatus and method |
| CN105657129A (en) * | 2016-01-25 | 2016-06-08 | 百度在线网络技术（北京）有限公司 | Call information obtaining method and device |
| CN107103005B (en) * | 2016-02-23 | 2020-10-30 | 创新先进技术有限公司 | Question and answer corpus collection method and device |
| CN106095834A (en) * | 2016-06-01 | 2016-11-09 | 竹间智能科技（上海）有限公司 | Intelligent dialogue method and system based on topic |
| CN106649561B (en) * | 2016-11-10 | 2020-05-26 | 复旦大学 | Intelligent question-answering system for tax consultation service |
| CN107153965A (en) * | 2017-04-05 | 2017-09-12 | 芜湖恒天易开软件科技股份有限公司 | A kind of intelligent customer service solution of multiple terminals |
-
2017
- 2017-10-31 CN CN201711043042.3A patent/CN109726372B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6640210B1 (en) * | 1999-11-12 | 2003-10-28 | Frederick Anthony Schaefer | Customer service operation using wav files |
| US7907705B1 (en) * | 2006-10-10 | 2011-03-15 | Intuit Inc. | Speech to text for assisted form completion |
| US9191476B1 (en) * | 2009-01-08 | 2015-11-17 | Amdocs Software Systems Limited | System, method, and computer program for speech recognition assisted call center and self service interface |
| CN102456344A (en) * | 2010-10-22 | 2012-05-16 | 中国电信股份有限公司 | System and method for analyzing customer behavior characteristic based on speech recognition technique |
| CN106572230A (en) * | 2016-10-31 | 2017-04-19 | 努比亚技术有限公司 | Device and method for recording calls |
| CN106874134A (en) * | 2017-01-22 | 2017-06-20 | 国网新疆电力公司信息通信公司 | The processing method of work order type, apparatus and system |
| CN107230142A (en) * | 2017-07-12 | 2017-10-03 | 陈维龙 | Method and device, method of commerce and system based on speech production order |
Non-Patent Citations (1)
| Title |
|---|
| 网通客服中心系统设计与实现;张松元;;信息技术(第08期);104-107 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109726372A (en) | 2019-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109726372B (en) | Method and device for generating work order based on call records and computer readable medium | |
| CN107103903B (en) | Acoustic model training method and device based on artificial intelligence and storage medium | |
| US11100934B2 (en) | Method and apparatus for voiceprint creation and registration | |
| CN107680019B (en) | Examination scheme implementation method, device, equipment and storage medium | |
| US10796700B2 (en) | Artificial intelligence-based cross-language speech transcription method and apparatus, device and readable medium using Fbank40 acoustic feature format | |
| US10817707B2 (en) | Attack sample generating method and apparatus, device and storage medium | |
| CN108090127B (en) | Method and device for establishing question and answer text evaluation model and evaluating question and answer text | |
| CN109389971A (en) | Insurance recording quality detecting method, device, equipment and medium based on speech recognition | |
| WO2021175019A1 (en) | Guide method for audio and video recording, apparatus, computer device, and storage medium | |
| CN109993150B (en) | Method and device for identifying age | |
| CN110597952A (en) | Information processing method, server, and computer storage medium | |
| CN109785846B (en) | Role recognition method and device for mono voice data | |
| CN109670055A (en) | A kind of multi-medium data checking method, device, equipment and storage medium | |
| CN109462603A (en) | Voiceprint authentication method, equipment, storage medium and device based on blind Detecting | |
| CN111598122B (en) | Data verification method and device, electronic equipment and storage medium | |
| CN112417158A (en) | Training method, classification method, device and equipment of text data classification model | |
| CN111291882A (en) | Model conversion method, device, equipment and computer storage medium | |
| CN110598008A (en) | Data quality inspection method and device for recorded data and storage medium | |
| CN113903363A (en) | Violation detection method, device, equipment and medium based on artificial intelligence | |
| CN117251547A (en) | User question response method and device, equipment and medium thereof | |
| CN109710939B (en) | Method and device for determining theme | |
| US20170213544A1 (en) | Training a cognitive agent using document output generated from a recorded process | |
| CN106959945A (en) | The method and apparatus that slug is generated for news based on artificial intelligence | |
| CN111178531B (en) | Method, device and storage medium for acquiring relationship reasoning and relationship reasoning model | |
| CN113642443A (en) | Model testing method and device, electronic equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191205 Address after: 201210 room j1328, floor 3, building 8, No. 55, Huiyuan Road, Jiading District, Shanghai Applicant after: SHANGHAI YOUYANG NEW MEDIA INFORMATION TECHNOLOGY Co.,Ltd. Address before: 100085 Baidu building, No. 10, ten Street, Haidian District, Beijing Applicant before: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190507 Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd. Assignor: SHANGHAI YOUYANG NEW MEDIA INFORMATION TECHNOLOGY Co.,Ltd. Contract record no.: X2019110000009 Denomination of invention: Work order generation method and device based on call records and computer readable medium License type: Exclusive License Record date: 20191218 |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |