JP2002342557A - System for statistical processing population distribution on the basis of positional information of portable terminal - Google Patents

Abstract

PROBLEM TO BE SOLVED: To grasp the state of concentration and movement of population and further to predict movement by constantly gathering population distribution information not in a specified area but over a wide region and applying statistical processing. SOLUTION: This system is equipped with; one or more base-station exchanges which receive position registration information sent from portable terminals (portable telephone and PHS) in respective areas through base stations in the respective areas, count and store the reception numbers of the position registration information of the respective areas in a specific observation time, and transfers the count values in respective observation times of the respective areas in every observation cycle wherein the specific observation time is repeated as many times as specified; and a statistical information management database which stores the count values in the respective observation times of the respective areas transferred from the base-station exchanges, holds the count values by the areas as population distribution data in the respective observation times, and statistically analyzes the count values to predict a population distribution in the near future and then compute a new-future prediction value.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a statistical processing of population distribution for statistically grasping the movement of mobile terminals (mobile phones, PHSs) which have become widespread and performing population concentration, movement, and movement prediction. About the system.

[0002]

2. Description of the Related Art Conventionally, in order to grasp the concentration and movement of population in urban areas and the like, a method of counting the movement (traffic volume) of a person by placing an investigator at each of a plurality of survey points has conventionally been used. It was a target. In this method, numerical values counted at regular intervals are counted and statistically processed later, and real-time information acquisition is not assumed. In addition, a large amount of labor is required to collect information over a wide area, so that the use has been limited to local use.

On the other hand, a mobile communication carrier monitors and controls the load of an exchange from the viewpoint of congestion countermeasures for its own communication network, but uses the location registration information of the portable terminal itself for network control and other services. Nothing is currently done.

[0004]

In the conventional street survey method, the survey time and the survey area are limited due to manual operation. As a result, it is possible to understand the movement of people for a limited time in a specific area,
It has been difficult to collect extensive and long term (eg, months) data.

According to the present invention, there is provided a mobile phone that constantly collects population distribution information over a wide area, not limited to a specific area, performs further statistical processing, grasps the population concentration state and movement state, and further enables movement prediction. An object is to provide a population distribution statistical processing system based on terminal location information.

[0006]

SUMMARY OF THE INVENTION A population distribution statistical processing system based on location information of a portable terminal according to the present invention is based on location registration information of a portable terminal (mobile phone, PHS), and is used as a base station exchange. And the statistical information management database is provided with the following functions.

First, the functions to be added to the existing base station exchange are as follows. (1) The number of position registration information within the observation time T is counted and accumulated for each area (base station). (2) At the observation period (T × N), the collected data (count number) at each observation time for each area is transferred to the statistical information management database. (3) Clear the transferred data and restart data collection in the next observation cycle.

Next, the functions of the newly provided statistical information management database are as follows. (4) Provide an information collection interface for the supervising base station exchange, and receive data transferred from a plurality of subordinate base station exchanges. The installation unit of the statistical information management database is assumed to be, for example, at the prefectural level. (5) Data transferred from each base station exchange (raw data)
To accumulate. (6) Statistical processing is performed on the accumulated raw data (population distribution data at each observation time), and the results (statistical data) are accumulated. As this statistical processing, for example, (a)
Calculation of a short-term future forecast value based on the past fluctuation situation for a certain area, (b) prediction of the movement situation between adjacent areas by obtaining a correlation of statistical data for the adjacent area,
And so on.

(7) Short-term future prediction based on statistical processing,
The prediction algorithm is corrected based on the actual result. This is to improve the accuracy of the prediction algorithm by feeding back the difference between the value predicted in (6-a) and the actual value to the prediction algorithm. (8) Display population distribution data and short-term future predicted values of each area in association with each other on a map.

(9) Perform user registration / authentication processing. In this method, a user who can refer to information managed by the statistical information management database is registered in advance, and authentication is performed to determine whether or not the requesting user is a referable user. (10) An interface for providing information to the user is provided. This provides the requested information to the authenticated user. (11) Network between statistical information management databases. As shown in (4), for example, by connecting a statistical information management database installed in each prefecture with a network, information can be managed in a wider range.

As described above, conventionally, only data in a limited area in a specific time zone could be collected due to manual work. However, as long as the mobile terminal (cellular phone, PHS) can be used, all areas can be collected. , Population distribution data such as population concentration and movement can be collected in real time and constantly. Moreover, it is possible to collect highly accurate population distribution data over a wide range.

[0012]

FIG. 1 shows an embodiment of the system of the present invention. In the figure, location registration information transmitted from the portable terminals 1a to 1f in each of the areas A, B, and C is transferred to a base station exchange 3 that manages a plurality of areas via the base station 2 in each area. The location registration information transferred to the base station exchange 3 is counted and accumulated at the observation time T for each area. The base station switch 3 has an observation period (T × N)
The collected data (count number) at each observation time T is transferred to the statistical information management database 4 for each area.

The statistical information management database 4 has an information collection interface for the supervising base station exchange 3, and receives and accumulates data transferred from a plurality of subordinate base station exchanges 3. Further, the statistical information management databases 4 are connected to each other, and a network is established. Here, data for each area in each of the control areas P and Q is accumulated in the statistical information management databases 4P and 4Q.

The statistical information management database 4 performs statistical processing on data transferred from each base station exchange, and accumulates the results (statistical data). For example, for a certain area, a short-term future predicted value based on a past fluctuation situation is calculated, and a difference between the predicted value and an actual value is fed back to a prediction algorithm to improve the accuracy of the prediction algorithm. Further, it performs user registration and authentication from the access terminal 5 and provides information in response to the request.

FIG. 2 shows functions added to the existing base station exchange 3. In the figure, the base station exchange counts and accumulates the number of location registration information received within the observation time T for each area (base station). For example, when the location registration information of the portable terminals 1a, 1b, 1c arrives from the base station in the area A within the observation time T, the count value 3 is accumulated. When the location registration information of the portable terminals 1d and 1e arrives from the base station in the area B within the observation time T, the count value 2 is accumulated. Next, the observation period (T × N)
Then, the collected data (count number) at each observation time T is transferred to the statistical information management database for each area. Next, the transferred data is cleared, and data collection in the next observation cycle is restarted.

FIG. 3 shows a configuration example of the statistical information management database 4. In the figure, a data storage unit 41 is provided with an information collection interface for a supervising base station exchange, and receives and accumulates data transferred from a plurality of subordinate base station exchanges. This raw data is accumulated for, for example, about one week for each area (base station).

The statistical processing section 42 performs a statistical process on the accumulated raw data, and accumulates the result (statistical data). As the statistical processing, for example, the short-term prediction algorithm 43 calculates and outputs a short-term future predicted value based on the past fluctuation situation for a certain area, and the prediction error feedback correction unit 44 calculates a difference between the predicted value and the actual value. To the prediction algorithm to improve the accuracy of the prediction algorithm. The output short-term future predicted value is displayed in association with each area on a map. The statistical data is accumulated for each area (base station), for example, for the past three months, and the statistical data that exceeds three months is temporarily saved from the database and is managed off-line.

The user registration / authentication processing unit 45 registers in advance a user who can refer to the information managed by the statistical information management database, and authenticates whether the requesting user is a referable user. The information providing interface unit 46 provides the requested data to the authenticated user. The information display means for the user is assumed to be a terminal (a personal computer or the like) on which a graphic application required for display is installed and a mobile terminal (a mobile phone or a PHS). Information is provided in a format. For example, a terminal such as a personal computer displays information of each area on a map, and a portable terminal transmits information to a user by voice (talking). The inter-database connection unit 47 controls connection with another statistical information management database and exchanges database management information with each other.

FIG. 4 shows an example of a processing procedure in the system of the present invention. In the figure, collected data (count number) for each area A, B and each observation time stored in each base station exchange A, B is transferred to the statistical information management database 4P. Then, data for each area and a short-term future predicted value by statistical processing are accumulated.

On the other hand, a user who wishes to refer to information managed by the statistical information management database 4P performs user registration from an access terminal in advance. Pre-registered users can access the statistical information management database 4 from a personal computer or mobile terminal.
It is possible to access P and obtain information requested after predetermined authentication. For example, area A, area A
When a request is made for the degree of incorporation in the future, information corresponding to each request can be referred to. When it is desired to check the status of another area E not managed by the statistical information management database 4P, the statistical information management database 4P
The user can access the statistical information management database 4Q via P to obtain necessary information.

Here, an example of the prediction algorithm will be described. (1) Let M be the total number of areas. (2) The number of position registration information Yj (j = 1 to M) at a certain observation time T in a certain area is assumed to be a linear multiple regression model in statistics. Assuming a bar, transportation station, school, etc., it is expressed as follows. Yj = α0 + α1 · X1 + α2 · X2 + ... + αn · Xn

(3) A time-varying element is added to the number of position registration information Yj at a certain observation time T in a certain area. Here, a time element is taken into each parameter of the linear multiple regression model, and the next model is newly constructed. Yj (T) = α0 + α1 (T) · X1 + α2 (T) · X2 + ... + αn
(T) · Xn Here, T indicates a specific time of day, for example, 1:00, 1:30, and 2:00. The algorithm for determining αi (T) is calculated by averaging accumulated data at a specific time in the past fixed period.

(4) αi at a certain time T in a certain area
The determination of (T) is obtained by solving an n-dimensional normal equation based on the least squares method with respect to the error between the actual value and the value calculated from the model. (5) For short-term future prediction, Yj is determined based on the latest parameter values obtained above.

[0024]

As described above, according to the present invention, the information on the population distribution based on the location registration information of the portable terminal is obtained.
It is possible to collect statistics over a wide range.

The obtained information can be applied to the following services. (1) Based on population distribution data or short-term future prediction data,
By grasping the area where people are concentrated or expected to be concentrated, it can be used to dispatch taxis, open stalls, etc., and increase profits. (2) In the event of a large-scale disaster in an urban area, priorities of rescue areas can be determined based on prior statistical information, and damage can be minimized. (3) The network operator can implement effective congestion measures based on detailed traffic data such as the degree of population concentration in a specific area.

[Brief description of the drawings]

FIG. 1 is a diagram showing an embodiment of the system of the present invention.

FIG. 2 is a view for explaining functions added to an existing base station exchange 3;

FIG. 3 is a diagram showing a configuration example of a statistical information management database 4.

FIG. 4 is a diagram showing an example of a processing procedure in the system of the present invention.

[Explanation of symbols]

 REFERENCE SIGNS LIST 1 mobile terminal 2 base station 3 base station exchange 4 statistical information management database 5 access terminal 41 data storage unit 42 statistical processing unit 43 short-term prediction algorithm 44 feedback correction unit 45 user registration / authentication processing unit 46 information provision interface unit 47 database connection Department

 ──────────────────────────────────────────────────続 き Continuing on the front page (72) Koji Sakai 2-3-1 Otemachi, Chiyoda-ku, Tokyo Nippon Telegraph and Telephone Corporation (72) Inventor Tohru Yonahara 2-chome Otemachi, Chiyoda-ku, Tokyo No.3-1 Nippon Telegraph and Telephone Corporation F term (reference) 5K067 AA41 BB04 EE02 EE16 FF02 FF03 HH21 JJ51

Claims (3)

[Claims] 1. A mobile terminal in each area (mobile phone, PH
S) receives the location registration information transmitted from each area via the base station in each area, counts and accumulates the number of location registration information received in each area in a predetermined observation time, and counts the predetermined observation time in a predetermined number of times. One or more base station exchanges for transferring count values at each observation time of each area for each repeated observation cycle, and accumulating count values at each observation time for each area transferred from the one or more base station exchanges; A statistical information management database that holds count values for each area as population distribution data at each observation time, and statistically analyzes and performs short-term future prediction of population distribution to calculate short-term future prediction values A population distribution statistical processing system based on location information of portable terminals. 2. The population distribution statistical processing system according to claim 1, wherein the statistical information management database receives a reference to the population distribution data and the short-term future predicted value in each of the areas. A portable terminal comprising: means for registering and authenticating a user; and means for providing the population distribution data and the short-term future predicted value in each of the areas in response to access from a registered and authenticated user. Population distribution statistical processing system based on location information. 3. The population distribution statistical processing system according to claim 1, wherein a plurality of said statistical information management databases are arranged for each region to be managed, and said statistical information management database is arranged between said statistical information management databases in each region. A population distribution statistical processing system based on location information of a portable terminal, wherein the population distribution data and the short-term future predicted value in each of the areas can be referred to each other.