WO2012105516A1 - 端末数推計装置及び端末数推計方法 - Google Patents
端末数推計装置及び端末数推計方法 Download PDFInfo
- Publication number
- WO2012105516A1 WO2012105516A1 PCT/JP2012/052030 JP2012052030W WO2012105516A1 WO 2012105516 A1 WO2012105516 A1 WO 2012105516A1 JP 2012052030 W JP2012052030 W JP 2012052030W WO 2012105516 A1 WO2012105516 A1 WO 2012105516A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- terminal
- position data
- estimation
- area
- observation
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
Definitions
- the present invention relates to a terminal number estimation device and a terminal number estimation method for estimating the number of terminals in a certain area using position information about a portable terminal obtained from network equipment of a portable terminal (for example, a cellular phone).
- operational data such as location data of the mobile terminal is generated in order to provide a telecommunication service to the user of the mobile terminal.
- statistical processing such as tabulation on such operational data, the number of mobile terminals can be calculated, and an estimated value such as “population” can be obtained from the calculation result.
- position registration signal This is a signal that is transmitted almost periodically from the mobile terminal to the serving base station.
- a base station receives a location registration signal of a mobile terminal, the mobile terminal It can be estimated that it exists in the base station sector which is the radio wave coverage of the base station.
- GPS information is information on the GPS positioning result transmitted from the mobile terminal to the serving base station periodically or in response to a terminal operation or a request from the mobile terminal network. Similarly, when GPS information is received, it can be estimated that the mobile terminal exists around the position indicated by the GPS positioning result (see, for example, Patent Document 1).
- the number of mobile terminals (number of terminals) existing in a certain geographic area can be estimated from the observation results of position data as described above, the above-mentioned population etc. It is expected that an estimated value of
- an object of the present invention is to provide a terminal number estimation device and a terminal number estimation method capable of estimating the number of mobile terminals that have stayed in an observation area for a desired time.
- a terminal number estimation device includes position data acquisition means for acquiring position data including identification information for identifying a mobile terminal, position information regarding the position of the mobile terminal, and position acquisition time information from which the position information was acquired; Observation target acquisition means for acquiring, as observation target position data, position data whose position acquisition time information is within an observation target period during which stay should be observed and whose positional information is within an observation area to be observed, and observation target acquisition means On the basis of the position acquisition time information included in the observation target position data acquired in step 1, the feature quantity calculation means for calculating the feature quantity for the observation target position data, and the feature quantity calculation means for each identification information of the mobile terminal Expected stay time calculation means for calculating the total value of the calculated feature values as expected stay time representing stay time, and the number of objects to be estimated based on the expected stay time That is the estimated target terminal selection means for selecting a mobile terminal, and the terminal number estimation means for performing the estimation of the number of estimated target terminal selected mobile terminal selected by the means, characterized in that it comprises a.
- the terminal number estimation method is a terminal number estimation method executed by a terminal number estimation device, in which identification information for identifying a portable terminal, position information regarding the position of the portable terminal, and position information are acquired.
- An observation target acquisition step acquired as observation target position data, and a feature amount for the observation target position data calculated based on position acquisition time information included in the observation target position data acquired in the observation target acquisition step A total amount of feature amounts calculated in the feature amount calculation step for each identification information of the amount calculation step and the mobile terminal, and an expected stay time representing the stay time
- position data whose position acquisition time information is within the observation target period and whose position information is within the observation area is acquired as observation target position data, and the observation target position data Based on the position acquisition time information included in the data, a feature amount for the observation target position data is calculated. Then, for each piece of identification information of the mobile terminal, the total value of the feature values is calculated as the expected stay time indicating the stay time, and the mobile terminal that is the target of number estimation is selected based on the expected stay time. Then, the number of mobile terminals selected as estimation targets is estimated.
- the expected stay time indicating the stay time in the observation area is calculated, and based on this expected stay time, the mobile terminal that is the target of estimation of the number is selected, so that the user stays in the observation area for a desired time.
- the number of mobile terminals can be estimated.
- the estimation target terminal selection means extracts a mobile terminal whose expected stay time is less than a predetermined passing residence determination threshold as a passing mobile terminal passing through the observation area, and the number of passing mobile terminals extracted is an estimation target of the number It is preferable to select as a portable terminal. In this case, it is possible to extract the passing portable terminals that pass through the observation area using the passing residence determination threshold, and it is possible to estimate the number of passing portable terminals.
- the estimation target terminal selection means extracts a mobile terminal having an expected stay time equal to or greater than a predetermined passage stay determination threshold as a stay mobile terminal staying in the observation area, and the number of the staying mobile terminals thus extracted is a target for estimation. It is preferable to select as a portable terminal. In this case, it is possible to extract a staying portable terminal that stays in the observation area using the passage stay determination threshold, and it is possible to estimate the number of staying portable terminals.
- the estimation target terminal selection unit extracts the mobile terminal included between the two passage retention determination thresholds determined in advance as the stay mobile terminal that stays in the observation area, and the extracted stay mobile terminal Is preferably selected as the portable terminal whose number is to be estimated. In this case, it is possible to extract the staying portable terminals that stay in the observation area for the time between the two passage retention determination thresholds using the two passage retention determination thresholds, and estimate the number of staying portable terminals. It becomes possible.
- the terminal number estimation means estimates the number of terminals within a predetermined estimation target period when estimating the number of mobile terminals. In this case, when the number of mobile terminals is estimated, the number of mobile terminals in the estimation target period can be estimated.
- the number of mobile terminals estimated by the terminal number estimation means the number of terminals in which one administrative division area in a predetermined wide area is address information, and one administrative division area included in the wide area It is preferable to further include population estimation means for estimating the population of the one administrative division area based on the ratio with the population based on the statistical data.
- the population can be estimated based on the ratio between the number of located areas and the population and the number of mobile terminals. Further, the population may be estimated by obtaining the ratio between the number of areas in the country and the population during the estimation target period or a certain number. Moreover, you may use the ratio calculated
- the position acquisition time information is acquired by the analysis target acquisition means and the analysis target acquisition means for acquiring position data that is within the analysis target period to be analyzed and the position information is within the observation area as the analysis target position data.
- Analysis target terminal extraction means for extracting the analysis target terminal to be analyzed based on the analysis target position data
- the estimation target terminal selection means is a user who resides in the observation area based on the expected staying time.
- mobile terminals excluding the user's mobile terminal estimated to be resident in the observation area from the analysis target terminal extracted by the analysis target terminal extraction means. It is preferable to select the mobile terminal to be estimated.
- the time it is possible to estimate the mobile terminal of the user who lives in the observation area.
- the analysis target terminals existing in the observation area within the analysis target period the mobile terminals of the users who live in the observation area are excluded, and the number of remaining mobile terminals is calculated. That is, among the users of mobile terminals existing in the observation area within the analysis target period, the number of mobile terminals of users who return home from the observation area to other areas, in other words, the user's mobile terminals that flowed into the observation area from other areas The number of terminals can be estimated. Thereby, when a disaster occurs, for example, it is possible to predict the person who returns home from the observation area to another area using the position data of the mobile terminal.
- the position data further includes address information of the user of the mobile terminal, and the terminal number estimation means, when estimating the number of mobile terminals, based on the address information of the position data corresponding to the mobile terminal.
- the number of mobile terminals estimated for each area to be estimated, the number of terminals in the area where address information is one estimation area in a predetermined wide area, and the wide area It is preferable to further include a number estimation means for estimating the number of persons for each estimation target area based on the ratio of the estimation target area to the population based on the statistical data. In this case, among the analysis target terminals existing in the observation area within the analysis target period, the number of remaining mobile terminals from which the user's mobile terminal living in the observation area is excluded is the address of the location data.
- the number of portable terminals estimated for each estimation target area is converted into the number of people. That is, it is possible to estimate, for each estimation target area, the number of people who return from the observation area to another area among the people existing in the observation area within the analysis target period.
- the number of people who are unable to return to the home is estimated to estimate the number of people who have difficulty returning from the observation area to the area to be estimated. It is preferable to further comprise estimation means. In this case, it is possible to estimate the number of people who have difficulty returning home from the observation area to the estimation target area among the people existing in the observation area within the analysis target period. As a result, it is possible to use the position data of the mobile terminal to predict a person who has difficulty in returning home from which it is difficult to return from the observation area to the estimation target area, for example, when a disaster occurs.
- the estimation target terminal selection means includes the user's portable terminal estimated as resident in the observation area from among the analysis target terminals, or the address information of the position data corresponding to the analysis target terminal is in the observation area. It is preferable to select a mobile terminal excluding the analysis target terminal as a mobile terminal that is a target of estimation of the number of terminals by the terminal number estimation means. In this case, among the analysis target terminals existing in the observation area within the analysis target period, the mobile terminal of the user estimated to be resident in the observation area, or the analysis target terminal whose address information is in the observation area Is excluded.
- a mobile terminal that does not correspond to either the mobile terminal of the user who is estimated to live in the observation area or the analysis target terminal whose address information is in the observation area is selected from the analysis target terminals.
- an analysis target acquisition unit that acquires, as analysis target position data, position data whose position acquisition time information is within the analysis target period to be analyzed and whose position information is within the analysis target area to be analyzed;
- Analysis target terminal extraction means for extracting the analysis target terminal to be analyzed based on the analysis target position data acquired by the means, and the estimation target terminal selection means is based on the expected stay time and is within the observation area.
- the mobile terminal of the user who lives in the observation area is extracted from the analysis target terminal extracted by the analysis target terminal extraction means, and the extracted mobile terminal is the terminal It is preferable to select the portable terminal as a target of estimation of the number of units by the number estimating means.
- the time it is possible to estimate the mobile terminal of the user who lives in the observation area.
- the analysis target terminals existing in the analysis target area within the analysis target period the mobile terminals of users residing in the observation area are extracted, and the number of extracted mobile terminals is calculated.
- the number of mobile terminals of the users who return from the analysis target area to the observation area that is the residence in other words, the observation area that is the residence It is possible to estimate the number of user portable terminals that have flowed out of the analysis area.
- the position data of the mobile terminal can be used to predict a person who returns home from the analysis target area to the observation area that is the residence.
- the number of mobile terminals estimated by the terminal number estimation means the number of terminals having one observation target area in a predetermined wide area as address information, and one observation target area included in the wide area Further comprising a person estimation means for estimating the number of people residing in the observation area among the persons existing in the analysis area within the analysis target period based on the ratio with the population based on the statistical data in Is preferred.
- a person estimation means for estimating the number of people residing in the observation area among the persons existing in the analysis area within the analysis target period based on the ratio with the population based on the statistical data in Is preferred.
- the number of mobile terminals of users residing in the observation area is estimated, and the estimated number of mobile terminals is Converted to the number of people.
- the analysis target area to the observation area based on the number of people residing in the observation area within the analysis target period estimated by the number of people estimation means and the analysis target area. It is preferable to further include a difficult-to-return person estimation unit for estimating the number of difficult-to-return persons who are difficult to return. In this case, it is possible to estimate the number of persons who have difficulty in returning home from the analysis target area to the observation area among the persons existing in the analysis target area within the analysis target period. Thereby, it is possible to use the position data of the mobile terminal to predict a person who has difficulty in returning home from which it is difficult to return from the analysis target area to the observation area as the residence, when a disaster occurs, for example.
- the position data further includes address information of the user of the mobile terminal
- the estimation target terminal selection means is the user's mobile terminal estimated as resident in the observation area from the analysis target terminals, or the analysis target It is preferable to extract an analysis target terminal whose address information of position data corresponding to the terminal is within the observation area, and to select the extracted mobile terminal as a mobile terminal to be estimated by the terminal number estimation means. In this case, among the analysis target terminals existing in the analysis target area within the analysis target period, the user's mobile terminal estimated to be resident in the observation area or the analysis target whose address information is in the observation area Terminal is extracted.
- At least one of the analysis target terminals in which the address information of the position data corresponding to the mobile terminal of the user estimated to live in the observation area and the analysis target terminal is within the observation area among the analysis target terminals The mobile terminal corresponding to is extracted. Thereby, among the users of the mobile terminals existing in the analysis target area within the analysis target period, it is possible to more accurately estimate the number of mobile terminals of the users who return from the analysis target area to the observation area that is the residence. .
- the position data acquired by the position data acquisition means includes first registered position data including first position information registered by the mobile terminal, and second registered position data including second position information registered by the mobile terminal.
- the observation target acquisition means acquires second registered position data whose position acquisition time information is within the observation target period during which stay is to be observed and whose position information is within the observation area to be observed as observation target position data.
- the first stay time distribution calculation for calculating the first stay time distribution indicating the relationship between the stay time of the mobile terminal staying in the observation area and the number of each stay time based on the first registered position data.
- the correction coefficient calculating means for calculating the correction coefficient for correcting the number of mobile terminals and the correction coefficient calculated by the correction coefficient calculating means are used.
- the observation target position data is acquired from the second registered position data by the observation target acquisition means, and the number of portable terminals that have registered the second registered position data based on the observation target position data is the number of terminals.
- the correction coefficient is calculated based on the correlation between the first stay time distribution calculated based on the first registered position data and the second stay time distribution calculated based on the second registered position data.
- the correction coefficient is calculated based on the second registered position data. Can be corrected based on the first registered position data. Therefore, the number of mobile terminals can be estimated more accurately by correcting the number of mobile terminals registered with the second registered position data using this correction coefficient.
- the number of mobile terminals corrected by the number correcting means the number of terminals in the area where one administrative division area in a predetermined wide area is address information, and one administrative division area included in the wide area It is preferable to further include population estimation means for estimating the population of the one administrative division area based on the ratio with the population based on statistical data. In this case, the population can be estimated based on the ratio between the number of located areas and the population and the corrected number of mobile terminals.
- the apparatus further comprises front and rear position data acquisition means for acquiring position acquisition time information of the data and position acquisition time information of the third position data that is position data immediately after the first position data.
- the difference between the position acquisition time of the second position data and the position acquisition time of the third position data is preferably calculated as a feature amount for the first position data.
- the feature amount can be calculated based on the position acquisition time information of the position data.
- the present invention it is possible to estimate the number of mobile terminals that have stayed in the observation area for a desired time.
- FIG. 1 is a diagram showing a system configuration of a communication system according to a first embodiment. It is a figure which shows the structure of a terminal number estimation apparatus. It is a figure which shows the transmission timing of position data for every portable terminal. It is a figure which shows the specific example of the number estimation process in an estimation object period. It is a figure for demonstrating the view of terminal number estimation. It is a figure for demonstrating the calculation method which concerns on terminal number estimation. It is a flowchart which shows the number estimation process of a portable terminal. It is a flowchart which shows the calculation process of a feature-value. It is a figure which shows the structure of the modification of a terminal number estimation apparatus. It is a flowchart which shows the modification of the number estimation process of a portable terminal.
- FIG. 1 is a system configuration diagram of a communication system 1 according to the first embodiment.
- the communication system 1 includes a mobile terminal 100, a BTS (base station) 200, an RNC (radio control device) 300, an exchange 400, various processing nodes 700, and a management center 500.
- the management center 500 includes a social sensor unit 501, a petamining unit 502, a mobile demography unit 503, and a visualization solution unit 504.
- the exchange 400 collects position information, which will be described later, about the mobile terminal 100 via the BTS 200 and the RNC 300.
- the RNC 300 can measure the position of the mobile terminal 100 using the delay value in the RRC connection request signal when communication connection is performed with the mobile terminal 100.
- the exchange 400 can receive the position information of the mobile terminal 100 measured in this way when the mobile terminal 100 executes communication connection.
- the exchange 400 stores the received position information, and outputs the collected position information to the management center 500 in response to a predetermined timing or a request from the management center 500.
- the various processing nodes 700 acquire the position information of the mobile terminal 100 through the RNC 300 and the exchange 400, and perform recalculation of the position in some cases, and are collected at a predetermined timing or in response to a request from the management center 500 The position information is output to the management center 500.
- the position information of the mobile terminal 100 in the present embodiment a sector number indicating the in-service sector obtained from the position registration signal, a position positioning data obtained by a GPS positioning system or a position information acquisition system by PRACH PD, and the like are adopted. be able to.
- the position data of the portable terminal 100 includes the position information as described above, identification information for identifying the portable terminal (for example, information associated with the portable terminal such as a line number), and position acquisition time information at which the position information is acquired. including.
- identification information for identifying the portable terminal
- a line number it is preferable not to use the line number as it is, but to use a value associated with the line number (for example, a hash value of the line number) for non-identification. .
- the management center 500 includes the social sensor unit 501, the petamining unit 502, the mobile demography unit 503, and the visualization solution unit 504. In each unit, the location information of the mobile terminal 100 is used. Perform statistical processing.
- the terminal number estimation apparatus 10 (FIG. 2) mentioned later can be comprised by the management center 500, for example.
- the social sensor unit 501 is a server device that collects data including location information of the mobile terminal 100 from each exchange 400 and various processing nodes 700 or offline.
- the social sensor unit 501 receives data periodically output from the exchange 400 and the various processing nodes 700, or acquires data from the exchange 400 and the various processing nodes 700 according to a predetermined timing in the social sensor unit 501. It is configured to be able to do.
- the petamining unit 502 is a server device that converts data received from the social sensor unit 501 into a predetermined data format. For example, the petamining unit 502 performs a sorting process using a user ID as a key, or performs a sorting process for each area.
- the mobile demography unit 503 is a server device that performs aggregation processing on the data processed in the petamining unit 502, that is, count processing for each item. For example, the mobile demography unit 503 can count the number of users located in a certain area, and can total the distribution of the located areas.
- the visualization solution unit 504 is a server device that processes the data aggregated in the mobile demography unit 503 so as to be visible. For example, the visualization solution unit 504 can map the aggregated data on a map. Data processed by the visualization solution unit 504 is provided to companies, government offices or individuals, and is used for store development, road traffic surveys, disaster countermeasures, environmental countermeasures, and the like. It should be noted that the information statistically processed in this way is processed so that individuals are not specified so as not to infringe privacy.
- the social sensor unit 501, petamining unit 502, mobile demography unit 503, and visualization solution unit 504 are all configured by the server device as described above, and although not shown, the basic configuration of a normal information processing device Needless to say, it includes a CPU, a RAM, a ROM, an input device such as a keyboard and a mouse, a communication device that communicates with the outside, a storage device that stores information, and an output device such as a display and a printer.
- FIG. 2 shows a functional block configuration of the terminal number estimation apparatus 10.
- the terminal number estimation device 10 includes a position data acquisition unit (position data acquisition means) 11, a storage unit 12, an observation target period acquisition unit 13, an observation area acquisition unit 14, an observation target acquisition unit (observation target Acquisition means) 15, front and rear position data acquisition section (front and rear position data acquisition means) 16, feature amount calculation section (feature amount calculation means) 17, expected stay time calculation section (expected stay time calculation means) 18, passing stay terminal selection section (Estimation target terminal selection means) 19, terminal number estimation unit (terminal number estimation means) 20, and terminal number output unit 21 are configured.
- the position data acquisition unit 11 acquires the above-described position data from the outside and stores it in the storage unit 12. In addition, it is not essential to provide the position data acquisition unit 11 in the terminal number estimation device 10, and the position data acquired by the position data acquisition unit outside the terminal number estimation device 10 is transmitted to the terminal via, for example, a storage medium. You may input into the number estimation apparatus 10.
- FIG. The accumulation unit 12 stores position data over a plurality of times for a large number of users (mobile terminals).
- the observation target period acquisition unit 13 acquires observation target period information including a set of a start time and an end time for grasping the stay state.
- the observation area acquisition unit 14 acquires observation area information associated with one or more pieces of position information.
- the observation area information here is given as, for example, a sector number, a latitude / longitude, a geographical range (for example, a municipality), etc., and the observation area acquisition unit 14 displays the expression format and position information of the acquired observation area information. It is desirable to provide a database that manages information that associates the expression format (for example, correspondence information between sector numbers and latitude and longitude).
- the observation target acquisition unit 15 acquires, from the storage unit 12, position data whose position acquisition time information is within the observation target period and whose position information is within the observation area to be observed as observation target position data. Note that the observation target position data may be further narrowed down according to separately given conditions (for example, the age group of the user of the mobile terminal). This observation target position data is a feature amount calculation target in the feature amount calculation unit 17.
- the front-rear position data acquisition unit 16 is the position data of the first position data among the position data including the same identification information as the first position data for the observation target position data (hereinafter referred to as “first position data”). Position acquisition time information of the immediately preceding position data (hereinafter referred to as “second position data”) and position acquisition time information of the position data immediately after the first position data (hereinafter referred to as “third position data”). get. Note that it is not essential for the front / rear position data acquisition unit 16 to acquire the entire second or third position data, and at least the position acquisition time information included in the position data may be acquired.
- the feature amount calculation unit 17 calculates a feature amount for each of the first position data. For example, the feature quantity calculation unit 17 calculates the difference between the position acquisition time of the second position data and the position acquisition time of the third position data as the feature quantity for the first position data. In addition, when the position acquisition time of the second position data is an abnormal value, the feature amount calculation unit 17 takes the position acquisition time of the first position data and the position acquisition time of the second position data as an example here. When the difference is larger than a predetermined reference value (for example, 1 hour), the time of the second position data is set to a time that is retroactive from the position acquisition time of the first position data by a predetermined time (for example, 1 hour). A feature amount for the first position data is calculated as the acquisition time.
- a predetermined reference value for example, 1 hour
- the feature amount calculation unit 17 uses the position acquisition time of the first position data and the position acquisition time of the third position data as an example here. Is greater than a predetermined reference value (for example, 1 hour), the time advanced from the position acquisition time of the first position data to the future by a predetermined time (for example, 1 hour) is set in the third position data. The feature amount for the first position data is calculated using the position acquisition time.
- the process when the position acquisition times of the second and third position data are abnormal values is not an essential process, but the portable terminal 100 is located outside the service area by performing the above process.
- the position data acquisition time interval becomes abnormally long due to the power of the mobile terminal 100 being turned off or the like, the influence of the abnormally long acquisition time interval may be excessive. Can be prevented.
- the expected stay time calculation unit 18 calculates the total value of the feature amounts calculated by the feature amount calculation unit 17 as the expected stay time (unit: hours) representing the stay time for each identification information of the mobile terminal.
- the expected stay time (unit: hours) representing the stay time for each identification information of the mobile terminal.
- FIG. 3 is a diagram illustrating the transmission timing of the position data for each portable terminal.
- FIG. 3 shows the timing at which each of the three mobile terminals (identification information c1, c2, c3) transmits the position data (the position data is transmitted at the timing when the mobile terminal is drawn with a solid line or a broken line). ).
- the position data transmitted when the mobile terminal is drawn with a solid line indicates that the mobile terminal is transmitted from within the observation area to be observed
- the position data transmitted at the timing when the mobile terminal is drawn with a broken line is The case where it is transmitted from outside the observation area to be shown is shown.
- the number described below the mobile terminal drawn with a solid line or a broken line indicates the feature amount of the position data transmitted at the timing when the mobile terminal is drawn.
- the expected stay time k (c2) is calculated.
- the expected stay time k (c3) of the mobile terminal of the identification information c3 is 0.7.
- the passing residence terminal selection unit 19 sorts whether the mobile terminal has passed through the observation area to be observed or stayed in the observation area to be observed during the observation target period. Do. Specifically, the passing residence terminal selection unit 19 passes a mobile terminal whose expected stay time calculated by the expected stay time calculation unit 18 is less than a predetermined passing residence determination threshold, through the observation area. And select a portable terminal having a passage retention determination threshold value or more as a retention portable terminal staying in the observation area for a passage retention determination threshold value or more.
- the passage residence determination threshold value represents time (unit: “time”).
- the passing portable terminal and the staying portable terminal are targets for estimation of the number of portable terminals in the terminal number estimation unit 20.
- the passage retention determination threshold is set to “1”, the portable terminal having the identification information c1 and c2 shown in FIG. 3 is selected as the retention portable terminal, and the portable terminal having the identification information c3 is selected as the passage portable terminal. And
- the terminal number estimation unit 20 estimates the number of passing portable terminals and remaining portable terminals selected as estimation targets by the passing residence terminal selecting unit 19. Note that the terminal number estimation unit 20 may estimate the number of both the passing portable terminal and the remaining portable terminal selected by the passing residence terminal selecting unit 19, or may calculate only one of them.
- FIG. 4 is a diagram illustrating a specific example of the number estimation process within the estimation target period.
- the mobile terminals having the identification information c1 and c2 are selected as the staying mobile terminals.
- FIG. 4 shows a case where the estimation target period (time p0 to p1) is included in the observation target period (time t0 to t1). As shown in FIG.
- the terminal number estimation unit 20 is a feature amount of the identification information c1 and c2 on the observation target position data of the portable terminal, and the position acquisition time information is a feature in the estimation target period p0 to p1.
- An amount 1 and a feature amount 0.6 (a feature amount of observation target position data in which a mobile terminal is indicated by a circle in FIG. 4) are extracted, and a total value 1.6 of the extracted feature amounts is calculated.
- the terminal number estimation unit 20 calculates a value obtained by dividing the total value of the calculated feature values by twice the time length of the estimation target period (time p1 ⁇ time p0) as the number of staying portable terminals.
- a feature quantity for calculating the number of units may be separately calculated based on the respective observation target position data, and the number of passing portable terminals and staying portable terminals may be calculated based on the calculated feature quantity for calculating the number of units. .
- the estimation target period time p0 to p1 is included in the observation target period (time t0 to t1), that is, the case where time t0 ⁇ time p0 ⁇ time p1 ⁇ time t1 is described.
- the staying time in the venue (observation area) of the event whose holding time is from time t0 to time t1 (observation target period) There are the number of portable terminals for the time p0 to the time p1 (estimation target period) of visitors who have a predetermined time or more (expected stay time is a predetermined value or more).
- a user of a mobile phone expected stay time (time t1 ⁇ time1) that has been in the venue (observation area) of an event whose holding time is from time t0 to time t1 (observation target period).
- time t1 ⁇ time1 expected stay time (time t1 ⁇ time1) that has been in the venue (observation area) of an event whose holding time is from time t0 to time t1 (observation target period).
- the terminal number estimation unit 20 estimates the number of passing portable terminals.
- the number of passing portable terminals in a predetermined estimation target period to be observed is the same as when estimating the number of staying portable terminals described above.
- the terminal number estimation unit 20 is a feature amount of the observation target position data of the mobile terminal of the identification information c3 selected as the passing mobile terminal, and the position acquisition time information is the estimation target period p0. Extract feature value 0.7 in p1 (feature value of observation target position data indicated by cross marks in FIG. 4), and sum the extracted feature values (here 0.7) calculate. Then, the terminal number estimation unit 20 calculates a value obtained by dividing the total value of the calculated feature amounts by twice the time length of the estimation target period (time p1 ⁇ time p0) as the number of passing portable terminals.
- the method of estimating the number of mobile terminals in the terminal number estimation unit 20 described above is an example, and is not limited to a specific method, and various methods can be adopted.
- a method described in Japanese Patent Application No. 2010-212456 filed earlier by the applicant of the present application can be used as another method for estimating the number of terminals.
- the information analysis apparatus receives position information indicating the position of the user, positioning time information from which the position information is obtained, and point data including the user ID from the outside, and determines the positioning time from the point data for each user.
- Extracts point data immediately before the target time and point data whose positioning time is immediately after the target time, and for each user, the position indicated by the point data immediately before the target time and the position indicated by the point data immediately after the target time Is a series of methods for estimating the user's position at the target time by calculating the population distribution of a predetermined calculation target area unit at the target time based on the estimated position of each user. Yes, this method can be applied to terminal number estimation.
- the terminal number output unit 21 outputs the number of passing portable terminals and the number of staying portable terminals estimated by the terminal number estimating unit 20.
- the output here includes various output modes such as display output, audio output, and print output.
- the observation target acquisition unit 15, the feature amount calculation unit 17, the expected stay time calculation unit 18, the passing residence terminal selection unit 19, and the terminal number estimation unit 20 are essential requirements, and other configurations It is not essential to provide the requirement in the terminal number estimation device 10.
- each terminal ai transmits a signal (for example, a position registration signal including position registration information), and those signals Is observable.
- the estimation of the number of terminals is the value of m from the observed signal qij (j is an integer from 1 to xi). It is none other than estimating.
- the estimated value E (m) of the number m of terminals can be calculated by the following equation (6).
- the terminal ai transmits the signals qi1, qi2, and qi3 within the estimation target period and the period in which the terminal ai stays in the sector S, and the signal qi0 immediately before the signal qi1.
- Is the signal qi4 transmitted immediately after the signal qi3, and the transmission times of the signals qi0, qi1, qi2, qi3, qi4 are ui0, ui1, ui2, ui3, ui4, respectively, This corresponds to estimating the stay time ti of the sector S within the estimation target period as a period from (midpoint of ui0 and ui1) to (midpoint of ui3 and ui4).
- the terminal ai transmits the signal qi4 while staying in the sector S, although it is not within the estimation target period. However, it is not estimated that the end time of the stay time ti is the same as the end time of the estimation target period T. In this way, the unbiased estimation of the stay time ti is maintained.
- step S1 position data acquisition step in FIG. 7
- storage part 12 will preserve
- step S2 after the process of step S1, you may perform the process after step S2 after time. That is, step S1 may be executed as a preliminary preparation for the processing after step S2.
- the observation target period acquisition unit 13 acquires observation target period information including a set of start time and end time, and the observation area acquisition unit 14 correlates with one or more pieces of position information.
- Is acquired step S2.
- a set of a start time t0 and an end time t1 is acquired as the observation target period information
- the sector number S is acquired as the observation area information.
- the observation target acquisition unit 15 includes position acquisition time information that is after the start time t0 and before the end time t1 from the storage unit 12, and is associated with the sector number S that is observation area information.
- position information is sector number S
- Condition 1 The position acquisition time is after the start time t0 and before the end time t1. That is, it is included in the observation target period.
- Condition 2 The position information is sector S.
- step S4 the front / rear position data acquisition unit 16 includes the same identification information as the first position data for the position data (first position data) for which the feature amount is to be obtained among the observation target position data.
- the position acquisition time information of the position data immediately before the first position data (second position data) and the position data immediately after the first position data (first 3 position data) is acquired.
- step S5 feature amount calculation step
- the feature amount calculation unit 17 calculates a feature amount for the first position data.
- the position acquisition times of the first, second, and third position data are z1, z2, and z3, respectively.
- a predetermined reference value reference value relating to the difference between the position acquisition times of the first and second position data
- a value A for example, 1 hour
- a predetermined reference value a position acquisition time of the first and third position data
- a reference value regarding the difference is set as a reference value B (for example, 1 hour).
- the feature amount calculation unit 17 determines the difference between the position acquisition times of the first and second position data (that is, the difference between the times z1 and z2) Da and the difference between the position acquisition times of the first and third position data (that is, the difference).
- the difference between the times z1 and z3) Db is calculated (step S11 in FIG. 8).
- the feature amount calculation unit 17 determines whether or not the difference Da between the position acquisition times of the first and second position data is larger than a predetermined reference value A (for example, 1 hour) (step S12), If the difference Da is larger than the reference value A, a time that goes back in the past by a predetermined time (for example, 1 hour) from the position acquisition time z1 of the first position data is referred to as a position acquisition time z2 of the second position data. (Step S13). Next, the feature quantity calculation unit 17 determines whether or not the difference Db between the position acquisition times of the first and third position data is larger than a predetermined reference value B (for example, 1 hour) (step S14).
- a predetermined reference value A for example, 1 hour
- the difference Db is larger than the reference value B
- the time acquired from the position acquisition time z1 of the first position data to the future by a predetermined time is set to the position acquisition time z3 of the third position data.
- the feature amount calculation unit 17 calculates the difference between the position acquisition time z2 of the second position data and the position acquisition time z3 of the third position data as the feature amount for the first position data (step S16). ).
- step S6 the processing in steps S4 and S5 described above is executed for each of the observation target position data, and when the execution is completed for all the observation target position data (positive determination in step S6), the process proceeds to step S7.
- step S7 the expected stay time calculation unit 18 calculates an expected stay time representing the stay time based on the calculated feature amount (expected stay time calculation step).
- the passage retention terminal selection part 19 selects the portable terminal whose feature-value is less than a passage retention determination threshold value as a passage portable terminal which passes an observation area, and a passage retention determination is carried out to the observation area the portable terminal more than a passage retention determination threshold value. It selects as a retention portable terminal which retains more than a threshold value (step S8: estimation object terminal selection step).
- the terminal number estimation unit 20 estimates the number of passing portable terminals and the remaining portable terminals selected by the passing retention terminal selection unit 19 (step S9: terminal number estimation step). Further, the terminal number output unit 21 outputs the number of terminals obtained by the estimation (step S10).
- the expected stay time calculation unit 18 calculates the expected stay time in the observation area, and based on the expected stay time, the passing residence terminal selection unit 19 determines the number of objects to be estimated. Select the mobile device to be. And the terminal number estimation part 20 estimates the number of the portable terminals calculated as estimation object. As described above, the number of mobile terminals staying in the observation area for a desired time can be estimated by the terminal number estimation device 10.
- the passing residence terminal selection unit 19 extracts the passing portable terminals that pass through the observation area using the passing residence determination threshold value, so that the number of passing portable terminals can be estimated by the terminal number estimation unit 20. .
- the passage staying terminal selection unit 19 extracts the staying portable terminals staying in the observation area using the passage staying determination threshold value, so that the number of staying portable terminals can be estimated by the terminal number estimation unit 20. .
- FIG. 9 shows a configuration example of the terminal number estimation apparatus 10 according to this modification
- FIG. 10 shows the number of mobile terminal number estimation processing contents.
- the terminal number estimation device 10 includes the same components as those in the first embodiment (FIG. 2) described above, and the functions of the respective components are substantially the same. Here, it demonstrates centering around difference with 1st Embodiment (FIG. 2) mentioned above.
- the front-rear position data acquisition unit 16 sets all the position data acquired by the position data acquisition unit 11 as first position data, and uses the second position data (previous position data) and the first position data related to the first position data.
- the position acquisition time information of each of the three position data (position data immediately after) is acquired.
- the position data acquired by the position data acquisition unit 11 may be acquired by the position data acquisition unit 11 and then stored in the storage unit 12 or stored in the storage unit 12. It may be sent from the position data acquisition unit 11 to the front / rear position data acquisition unit 16 without any change. That is, the front / rear position data acquisition unit 16 may read the position acquisition time information of the second and third position data from the storage unit 12 or may receive the position acquisition time information from the position data acquisition unit 11. Logically, either method can be used.
- the feature amount calculation unit 17 calculates the feature amount for the first position data by using all the position data acquired by the position data acquisition unit 11 as the first position data. Since this calculation result is an enormous amount, as shown in FIG. 9, the feature amount calculation unit 17 includes a feature amount storage unit 17a for storing the feature amount of the calculation result, and the feature amount storage unit 17a calculates the calculation result. It is desirable to store the feature amount.
- the feature amount calculation unit 17 calculates the difference between the position acquisition times of the second and third position data as the feature amount for the first position data, and the second or third position data shown in FIG. The point that the process is performed when the position acquisition time is an abnormal value is the same as in the first embodiment.
- the observation target acquisition unit 15 corresponds to position data in which the position acquisition time information is within the observation target period and the position information is within the observation area to be observed among the feature amounts stored in the feature amount storage unit 17a. Extract features.
- the expected stay time calculation unit 18 calculates the total feature value as the expected stay time (unit: hours) for each identification information of the mobile terminal based on the feature amount extracted by the observation target acquisition unit 15.
- the passing stay terminal selection unit 19 sorts into a passing mobile terminal and a staying mobile terminal as in the first embodiment.
- the terminal number estimation unit 20 estimates the number of passing portable terminals and remaining portable terminals selected as estimation targets by the passing retention terminal selection unit 19 as in the first embodiment.
- the terminal number output unit 21 outputs the number of passing mobile terminals estimated by the terminal number estimation unit 20 and the number of staying mobile terminals.
- the terminal number estimation process in the modification will be described.
- the sector number of the sector where the mobile terminal is located is given as the position information included in the position data of the mobile terminal.
- step S31 the front and rear position data acquisition unit 16 includes, for one piece of position data (first position data) whose feature value is to be obtained, out of position data including the same identification information as the first position data.
- the position acquisition time information of is acquired. Note that it is not essential for the front-rear position data acquisition unit 16 to acquire the entire second and third position data, and it is only necessary to acquire the position acquisition time information included in the second and third position data.
- step S32 the feature quantity calculation unit 17 calculates the feature quantity for the first position data by the procedure shown in FIG. 8 similar to that of the first embodiment described above. Since the process of step S32 is the same as the process of step S5 of FIG. 7 of the first embodiment described above, description thereof is omitted. Thereafter, the feature quantity obtained in step S32 is stored in the feature quantity storage unit 17a (step S33).
- steps S31 to S33 for one piece of position data is completed.
- steps S31 to S33 are executed for each of all the position data.
- the feature values for all the position data are calculated and stored in the feature value storage unit 17a. In this way, it is possible to calculate and store the feature amounts for all the position data in advance before performing the terminal number estimation.
- the observation target period acquisition unit 13 acquires observation target period information including a set of observation start time and observation end time, and the observation area acquisition unit 14 corresponds to one or more pieces of position information. Acquire observation area information.
- the observation target period information including a set of observation start time and observation end time
- the observation area acquisition unit 14 corresponds to one or more pieces of position information.
- Acquire observation area information it is assumed that a set of the observation start time t0 and the observation end time t1 is acquired as the observation target period information, and the sector number S is acquired as the observation area information.
- the observation target acquisition unit 15 determines that the position acquisition time information is within the observation target period and the position information is observed among the feature amounts for all the position data calculated in advance and stored in the feature amount storage unit 17a.
- a feature amount corresponding to the position data within the observation area to be extracted is extracted (step S36).
- the expected stay time calculation unit 18 calculates the expected stay time representing the stay time (step S37), and the passing stay terminal selection unit 19 Then, the selection is made between the passing portable terminal and the staying portable terminal (step S38). And the terminal number estimation part 20 estimates the number of passing portable terminals and stay portable terminals (step S39), and the terminal number output part 21 outputs the number of terminals obtained by estimation (step S40). In this way, the number of passing portable terminals and staying portable terminals can be estimated.
- the terminal number estimation device 10 acquires the observation target period information and the observation area information, and starts the estimation process for the number of terminals. Time until the number of terminals of the estimation result is obtained can be shortened.
- step S35 it is not essential to execute the process of step S35 after step S34, and the processes of steps S31 to S34 and the process of step S35 may be executed in parallel.
- the terminal number estimation apparatus 10 of the first embodiment described above may further include a population estimation unit (population estimation means) 22 that estimates the population in the observation area during the estimation target period, as shown in FIG.
- the population estimation unit 22 is based on a ratio between the number of terminals having one user attribute in a predetermined wide area and a population based on statistical data in one user attribute included in the wide area. Estimate the population of one user attribute.
- One user attribute here includes an address attribute in addition to gender and age.
- the population estimation unit 22 calculates the statistical data in the one administrative division area included in the wide-area area and the number of terminals in the wide-area area that have one administrative division area in a predetermined wide-area area as address information.
- the ratio to the population based on for example, the number of mobile terminals in the wide area including the observation area during the estimation target period (for example, the whole country in Japan) whose address information is the number of mobile terminals in the area and the observation area ( For example, the population is estimated on the basis of the ratio of the population based on statistical data whose address is Tokyo) and the number of terminals obtained by the terminal number estimation unit 20.
- the population estimation unit 22 can estimate the population of the observation area during the estimation target period by dividing the number of terminals by the ratio.
- the obtained population can be output from the terminal number output unit 21.
- the “terminal contract rate” which is the ratio of “the number of contracted terminals of a specific communication carrier from which location data is obtained” in the “population in a predetermined area” It may be used.
- the ratio for each region the ratio for each gender, the ratio for each age group, and the like to estimate the population.
- the population may be estimated by obtaining the ratio between the number of areas in the country and the population during the estimation target period or a certain number. Moreover, you may use the ratio calculated
- the terminal number estimation device 10 further includes an expansion coefficient storage unit that stores an expansion coefficient for converting the number of terminals into a population
- the population estimation unit 22 includes a feature amount for observation target position data. Based on the observation period length and the expansion factor, at least one of the population in the observation area during the observation period and the population for each population estimation unit that is a unit for estimating the population may be estimated. Examples of the “population estimation unit” include attributes, places, time zones, and the like.
- the expansion coefficient may be one stored in the expansion coefficient storage means or may be derived as follows.
- the expansion coefficient the reciprocal of “the product of the location ratio and the terminal penetration rate (that is, the ratio of the number of locations to the population)” can be used.
- the “area ratio” means the ratio of the area number to the contracted number
- the “popularity ratio” means the ratio of the contracted number to the population.
- Such an enlargement factor is desirably derived for each population estimation unit described above, but is not essential.
- the expansion coefficient may be derived using, for example, the number of terminals (the number of existing areas) estimated based on the feature amount and the observation period length as follows. That is, a feature amount is obtained from position data, and the number of terminals for each enlargement coefficient calculation unit is obtained based on the feature amount and the observation period length to obtain user number pyramid data, and statistical data (for example, Basic Resident Register) As above, population pyramid data in the same expansion coefficient calculation unit obtained in advance is acquired. And the acquisition rate (namely, the number of area / population) of the position data for every expansion coefficient calculation unit is calculated in the user number pyramid data and the population pyramid data.
- the “location data acquisition rate (that is, the number of locations / population)” obtained here corresponds to the “product of the location rate and the terminal penetration rate” described above.
- the reciprocal of the “position data acquisition rate” obtained in this way can be derived as an expansion coefficient.
- every prefecture (which may be an administrative division area and may be a municipality) of the address, every five-year or ten-year-old age group, every gender, time zone For example, every hour, or a combination of two or more of these may be used.
- the enlargement coefficient calculation unit is “male in the 20s in Tokyo”
- the males in the 20s in Japan who live in Tokyo that is, the address information in the user attribute is Tokyo
- the corresponding position data is extracted and the number of terminals is totaled to obtain user number pyramid data, and population pyramid data relating to a 20-year-old man living in Tokyo is obtained from statistical data.
- the whole country of Japan is a wide area
- the administrative division area included in the wide area is Tokyo.
- the address information in the user attribute is Tokyo instead of extracting only the location data of users residing in Tokyo. Extract location data.
- the location data acquisition rate that is, the number of people in the area / population
- the expansion coefficient calculation unit here, a man in the 20s in Tokyo
- the reciprocal of the “position data acquisition rate” can be derived as an expansion factor.
- the enlargement coefficient calculation unit and the population estimation unit are described as being equal. However, this is merely an example, and the present invention is not limited to this.
- the population of the observation area during the estimation target period is estimated and output in consideration of the number of terminals for which position data cannot be obtained (for example, terminals in a power-off state or terminals located outside the service area). can do.
- the address information of the user of the mobile terminal corresponding to the identification information included in the position data is further associated with the position data and stored in the storage unit 12.
- the number of passing portable terminals and staying portable terminals can be estimated based on the position data for each address information, and the number of passing persons and staying persons can be estimated based on the estimated number.
- the address information is information relating to the user's residence that is registered in advance by the user of the mobile terminal. In this case, out of the number of people passing through the observation area, the number of people who have certain address information can be estimated, or the number of people who have certain address information out of the number of people staying in the observation area. Can be estimated.
- the number of people passing through the observation area can be estimated for each address of the user of the mobile terminal (eg, for each prefecture or city), or the number of people staying in the observation area can be estimated by the user of the mobile terminal. It can be estimated for each address. Also in this case, when calculating the population from the number of terminals, it is desirable to obtain the ratio for each region, the ratio for each gender, the ratio for each age group, etc., and use it for the estimation of the population. Thereby, the distribution for every sex and the distribution for every age group can be obtained.
- a mobile terminal having an expected stay time within a predetermined range can be selected as an estimation target, and the population can be calculated from the number of the mobile terminals.
- the expected stay time indicates the time to stay in the observation area.
- the number of people staying in the observation area within the predetermined range is estimated. be able to.
- the number of portable terminals selected as passing portable terminals by the passing residence terminal selecting unit 19 It is also possible to calculate by directly counting based on the terminal identification information.
- the number of portable terminals selected as the staying portable terminal by the passing staying terminal selecting unit 19 is used as the identification information of the staying portable terminal. It can also be calculated by directly counting based on this.
- the passage residence terminal selection part 19 sorts a portable terminal based on whether expected stay time is more than a passage residence determination threshold value, or it is less than it, and the portable object of the estimation object of a number is used.
- the estimation target portable terminal can be selected by other methods. For example, it is possible to select a mobile terminal included between two predetermined passage determination thresholds as an expected stay time as a mobile terminal to be estimated. In this case, it is possible to estimate the number of staying portable terminals staying in the observation area for a predetermined time.
- the retention time is 0 to 1 hour, 1 to 2 hours, 2 to 3 hours, ... Etc.
- This estimation result can also be output, for example, as a graph showing the relationship between each residence time length and the number of mobile terminals in that residence time length.
- a person who has difficulty in returning home from a certain analysis target area is estimated.
- the person who has difficulty in returning home is a person who has a long distance from the current position to the place of residence (home) and cannot use the public transportation system in the event of a disaster, making it difficult to return home.
- the system configuration of the communication system of the second embodiment is the same as the system configuration in the first embodiment of FIG. 1, the description of the system configuration is omitted.
- FIG. 12 shows a functional block configuration of the terminal number estimation apparatus 10A.
- the terminal number estimation device 10A includes a position data acquisition unit (position data acquisition means) 11A, a storage unit 12A, an observation target period acquisition unit 13, an observation area acquisition unit 14, an observation target acquisition unit (observation target acquisition).
- front / rear position data acquisition unit (front / rear position data acquisition means) 16A feature amount calculation unit (feature amount calculation means) 17A, expected stay time calculation unit (expected stay time calculation means) 18A, estimated residence terminal list creation Section (estimation target terminal selection means) 25, estimated residence terminal list storage section 26, analysis target period acquisition section 31, analysis target area acquisition section 32, analysis target acquisition section (analysis target acquisition means) 33, analysis target terminal extraction section (Analysis target terminal extraction means) 34, estimation target terminal selection section (estimation target terminal selection means) 35, number of terminals estimation section (terminal number estimation means) 36, number of persons estimation section (number of persons estimation means) 7, stranded commuters number estimation unit (stranded commuters number estimating means) 38, and configured to include an output unit 39.
- the position data acquisition unit 11A acquires the position data from the outside in the same manner as the position data acquisition unit 11 of the first embodiment, and for the acquired position data, the user of the mobile terminal corresponding to the identification information included in the position data Are stored in the storage unit 12A in association with each other.
- the address information is information relating to the user's residence that is registered in advance by the user of the mobile terminal. This address information is stored in a storage unit (not shown) in a state associated with the identification information of the mobile terminal, and can be acquired by the position data acquisition unit 11A.
- the storage unit 12A stores position data over a plurality of times for a large number of users (mobile terminals).
- the observation target period acquisition unit 13 acquires observation target period information including a set of a start time and an end time for grasping the living state. Note that the observation target period information acquired by the observation target period acquisition unit 13 is, for example, information on a midnight on a predetermined day, information on a midnight on a plurality of days for a month before the present, or the like.
- the observation area acquisition unit 14 acquires observation area information associated with one or more pieces of position information.
- the observation area information here is given as, for example, a sector number, a latitude / longitude, a geographical range (for example, a municipality), etc., and the observation area acquisition unit 14 displays the expression format and position information of the acquired observation area information. It is desirable to provide a database that manages information that associates the expression format (for example, correspondence information between sector numbers and latitude and longitude).
- the observation target acquisition unit 15 obtains, from the storage unit 12A, position data whose position acquisition time information is within the observation target period and whose position information is within the observation area where the living state should be grasped, as the residence estimation target position data. get.
- the location estimation target position data may be further narrowed down according to separately given conditions (for example, the age group of the user of the mobile terminal).
- the location estimation target position data is a feature amount calculation target in the feature amount calculation unit 17A.
- the position data acquired by the observation target acquisition unit 15 is a basis for calculating the number of mobile terminals, but in the second embodiment, the observation target acquisition unit 15 acquires the position data.
- the position data to be used is used to create an estimated residence terminal list to be described later.
- the front / rear position data acquisition unit 16 ⁇ / b> A is the same as the first position data for the location estimation target position data (hereinafter referred to as “first position data”), similarly to the front / rear position data acquisition unit 16 in the first embodiment.
- first position data the first position data for the location estimation target position data
- second position data the position acquisition time information of the position data immediately before the first position data
- third position data The position acquisition time information (hereinafter referred to as “third position data”) is acquired. Note that it is not essential for the front / rear position data acquisition unit 16A to acquire the entire second or third position data, and at least the position acquisition time information included in the position data may be acquired.
- the feature amount calculation unit 17A calculates a feature amount for each of the first position data.
- the feature amount calculation processing in the feature amount calculation unit 17A is the same as the feature amount calculation unit 17 in the first embodiment, and a description thereof will be omitted.
- the expected stay time calculation unit 18A calculates the stay time as the total value of the feature amounts calculated by the feature amount calculation unit 17A for each identification information of the mobile terminal. Calculated as the expected stay time (unit: hours).
- the expected stay time unit: hours
- FIG. 13 is a diagram illustrating position data transmission timing for each mobile terminal.
- FIG. 13 shows the timing at which each of the three mobile terminals (identification information c1, c2, c3) transmits the position data (the position data is transmitted at the timing when the mobile terminal is drawn with a solid line or a broken line). ).
- the position data transmitted when the mobile terminal is drawn with a solid line indicates a case where the mobile terminal is transmitted from within the observation area where the living state should be grasped
- the position data transmitted at the timing when the mobile terminal is drawn with a broken line Indicates the case of transmission from outside the observation area.
- the number described below the mobile terminal drawn with a solid line or a broken line indicates the feature amount of the position data transmitted at the timing when the mobile terminal is drawn.
- the observation target period is from time t0 to time t1. This observation period can be, for example, midnight (a period from 1 am to 4 am, etc.). In FIG. 13, only one observation period is shown. However, as described above, for example, when a plurality of days at midnight are set as the observation period, a plurality of periods are set as the observation period. Will be.
- the expected stay time calculation unit 18A calculates the expected stay time for a certain mobile terminal, the position data transmitted within the observation target period from the time t0 to the time t1 from within the observation area in which the residence state should be grasped.
- the total value of the feature quantities is obtained. For example, when calculating the expected stay time of the mobile terminal of the identification information c2 shown in FIG. 13, the position data transmitted within the observation target period from time t0 to time t1 from within the observation area where the living state should be grasped. Is calculated as the expected stay time k (c2). Similarly, the expected stay time k (c1) of the mobile terminal of the identification information c1 is 1, and the expected stay time k (c3) of the mobile terminal of the identification information c3 is 1.
- the estimated residence terminal list creation unit 25 estimates a portable terminal owned by a user who resides in the observation area and creates a list. Specifically, the estimated residence terminal list creation unit 25 sets a mobile terminal whose expected stay time calculated by the expected stay time calculation unit 18A is less than a predetermined determination threshold as a mobile terminal that passes through the observation area. A portable terminal having a predetermined threshold value or more is selected as a portable terminal owned by a user who lives in the observation area.
- the observation target period acquisition unit 13 acquires information on the midnight zone of a plurality of days as the observation target period information and the expected stay time calculated by the expected stay time calculation unit 18A spans a plurality of days, Comparing the total value of expected stay time calculated over the day with a predetermined determination threshold, as described above, the portable terminal passing through the observation area and the portable terminal owned by the user living in the observation area Make a selection.
- the observation target period used when calculating the expected stay time as a certain time zone at midnight, the user of the mobile terminal whose total expected stay time in the time zone is equal to or greater than the determination threshold is It can be estimated as a user living in the area.
- the estimated residence terminal list creation unit 25 creates an estimated residence terminal list indicating mobile terminals owned by users who reside in the observation area for each observation area.
- the estimated residence terminal list creation unit 25 creates a list that includes only the identification information of the mobile terminal owned by the user who resides in the observation area. Or, it resides in the observation area for the identification information of all portable terminals (mobile terminals that pass through the observation area and portable terminals owned by users who live in the observation area) in the observation area. It is possible to create a list to which information indicating whether or not the mobile terminal is owned by the user is added.
- the estimated residence terminal list creation unit 25 stores the created estimated residence terminal list in the estimated residence terminal list storage unit 26.
- the estimated residence terminal list storage unit 26 stores the estimated residence terminal list for each observation area.
- the analysis target period acquisition unit 31 acquires analysis target period information including a set of a start time and an end time for estimating a person who has difficulty in returning home.
- the analysis target period information acquired by the analysis target period acquisition unit 31 may be, for example, information of a certain time zone or a plurality of days. This analysis target period is in principle a different period from the observation target period used by the observation target period acquisition unit 13.
- the analysis target area acquisition unit 32 acquires analysis target area information that is a target for estimating a person who has difficulty in returning home.
- the analysis target area information is given as, for example, latitude / longitude, polygon information including latitude / longitude, or an identifier (address code) indicating a geographical range (for example, a municipality or a mesh-divided range).
- the analysis target area acquisition unit 32 includes a database that manages information that associates the expression format of the area information to be acquired with the expression format of the position information (for example, correspondence information between identifiers and latitude and longitude). desirable.
- the observation area used by the observation area acquisition unit 14 described above is set as an analysis target area for estimating a person who has difficulty in returning home. Therefore, the analysis target area acquisition unit 32 acquires observation area information as analysis target area information.
- the analysis target acquisition unit 33 obtains, from the storage unit 12A, position data in which the position acquisition time information is within the analysis target period and the position information is within the analysis target area, which is a target area for estimating a person who is difficult to return home. Acquired as analysis target position data.
- the analysis target terminal extraction unit 34 extracts an analysis target terminal that is an object to be analyzed for those who have difficulty in returning home based on the analysis target position data acquired by the analysis target acquisition unit 33.
- the analysis target terminal extraction unit 34 extracts the mobile terminal corresponding to the analysis target position data as the analysis target terminal.
- the mobile terminal can be specified from the analysis target position data by using the identification information of the mobile terminal included in the analysis target position data. Thereby, the portable terminal whose position information is within the analysis target area and whose position acquisition time information is within the analysis target period can be extracted as the analysis target terminal.
- the analysis target terminal extraction unit 34 extracts the mobile terminal included in the analysis target position data as the analysis target terminal
- the analysis target terminal can also be extracted using other methods. For example, as described in the front / rear position data acquisition unit 16A, the feature amount calculation unit 17A, and the expected stay time calculation unit 18A, the feature amount for the analysis target position data is calculated, and the expected stay time is calculated based on the calculated feature amount. It is also possible to calculate and extract a mobile terminal whose expected stay time within the analysis target period is equal to or greater than a predetermined determination threshold as the analysis target terminal.
- the estimation target terminal selection unit 35 excludes the mobile terminals of the users who live in the analysis target area from the analysis target terminals extracted by the analysis target terminal extraction unit 34, and estimates the remaining mobile terminals for those who have difficulty in returning home. Select as the target mobile device.
- the mobile terminal of the user who lives in this analysis target area is a mobile terminal whose address data of the position data corresponding to the analysis target terminal is in the analysis target area (same as the observation area in this embodiment), or the estimated residence It is assumed that the mobile terminal is determined as the mobile terminal of the user who lives in the observation area (same as the analysis target area in the present embodiment) based on the estimated residential terminal list stored in the local terminal list storage unit 26.
- the address information of the position data corresponding to the analysis target terminal is stored in the mobile terminal that is the analysis target area and the estimated residence terminal list storage unit 26. It becomes a portable terminal corresponding to at least one of portable terminals determined as portable terminals of users who reside in the observation area based on the estimated residence terminal list. Thereby, the portable terminal which the user who lives in an analysis object area among the portable terminals in an analysis object area excludes.
- the analysis target terminal in the analysis target area extracted by the analysis target terminal extraction unit 34 is “A”
- the mobile terminal whose address data is in the analysis target area is “C”
- the estimated residence terminal A mobile terminal that is said to be resident in the observation area according to the list is represented by “O”.
- the estimation target terminal selection unit 35 includes, in the analysis target terminal A, a mobile terminal C whose address information is in the analysis target area, or a mobile terminal O that is said to be resident in the observation area according to the estimated residence terminal list. Is selected as a mobile terminal to be estimated by those who have difficulty returning home.
- the estimation target terminal selection unit 35 selects a mobile terminal that is neither the mobile terminal C nor the mobile terminal O among the analysis target terminals A as a mobile terminal that is an estimation target of a person who has difficulty in returning home.
- the portable terminal that is neither the portable terminal C nor the portable terminal O is a portable terminal owned by a user who lives outside the observation area (same as the analysis target area in this embodiment).
- the terminal number estimation unit 36 estimates the number of mobile terminals selected by the estimation target terminal selection unit 35 as estimation targets for those who have difficulty in returning home, for each address information (for each estimation target area).
- address information is matched with the position data (position data preserve
- the number of portable terminals for each address information can be estimated.
- estimation is performed for each address information (for example, for each city) associated with the position data, or for each position data. Unlike each address information, estimation can be performed for each predetermined area in order to estimate the number of mobile terminals.
- the terminal number estimation unit 36 estimates the number of mobile terminals based on the feature amount corresponding to each estimation target period while shifting the estimation target period, for example, every hour. Thereby, the number of portable terminals for each time zone can be estimated.
- the number-of-persons estimation unit 37 includes the number of terminals in the terminal whose address information is one administrative division area (estimation target area) in a predetermined wide area and one administrative division area (estimation target area) included in the wide area. Address information on the number of people who are difficult to return based on the ratio of population based on statistical data and the number of mobile terminals that are estimated by the terminal number estimation unit 36 Estimate every time. The ratio between the number of visited areas and the population is the same as that used in the modified example of the terminal number estimating device described above, and a detailed description thereof will be omitted. Thereby, the number of people who exist in the analysis target area within the analysis target area and whose return destination is different from the analysis target area is estimated for each address information.
- the number of persons who have difficulty returning home is difficult to return to the residence indicated by the address information from the analysis target area.
- a person whose distance between the analysis target area and the residence indicated by the address information is a predetermined threshold or more can be estimated as a person who has difficulty returning home.
- a person whose distance between the analysis target area and the residence indicated by the address information is less than a predetermined threshold can be estimated as a neighboring resident who lives in the vicinity of the analysis target area and can return home.
- the number of people who are difficult to return is estimated for each address information
- the number of persons who have difficulty returning home can be estimated for each address information. Accordingly, for example, when a disaster occurs, the staying person in the analysis target area is changed to a local inhabitant in the analysis target area, a neighboring inhabitant in the vicinity of the analysis target area, and the analysis target area as shown in FIG. It can be estimated by dividing it into those who have difficulty returning home. The number of neighbors may also be estimated for each address information.
- the output unit 39 outputs, in a predetermined data format, information on the number of people who have difficulty returning home estimated by the number of people having difficulty returning home 38.
- the output here includes various output modes such as display output, audio output, and print output. For example, when the number of people who have difficulty in returning home is estimated for a plurality of areas to be analyzed, as shown in FIG. Map-format data in which areas with few people who have difficulty returning home are indicated in light colors may be generated and output.
- the position data acquisition unit 11A acquires the position data and stores it in the storage unit 12A (step S51 in FIG. 17).
- the storage unit 12A stores position data over a plurality of times for a large number of users (mobile terminals).
- step S51 you may perform the process after step S52 after time. That is, step S51 may be executed as advance preparation for the processing after step S52.
- the observation target period acquisition unit 13 acquires observation target period information including a set of start time and end time, and the observation area acquisition unit 14 correlates with one or more pieces of position information. Is acquired (step S52).
- the observation target acquisition unit 15 acquires, from the storage unit 12A, position data whose position acquisition time information is within the observation target period and whose position information is the observation area as the residence estimation target position data (Step S1). S53).
- step S4 for acquiring front and rear position data
- step S5 for calculating feature values
- step S6 is the same as the processing of step S7 for calculating the expected stay time, and detailed description thereof is omitted.
- the estimated residence terminal list creation unit 25 selects a portable terminal whose expected stay time is equal to or greater than the determination threshold as a portable terminal owned by a user who lives in the observation area, and the estimated residence terminal based on the selected portable terminal A list is created (step S58). Then, the estimated residence terminal list creating unit 25 stores the created estimated residence terminal list in the estimated residence terminal list storage unit 26 (step S59). In this way, by calculating the feature amount based on the position data and obtaining the expected stay time from the calculated feature amount, the mobile terminal owned by the user who lives in the observation area can be estimated. And an estimated residence terminal list can be created based on a portable terminal owned by a user who resides in the observation area.
- the analysis target period acquisition unit 31 acquires analysis target period information including a set of a start time and an end time for estimating a person who has difficulty in returning home, and the analysis target area acquisition unit 32 Then, the analysis target area information (the same as the observation area information in the present embodiment) that is the target for estimating the person who has difficulty in returning home is acquired (step S61).
- the analysis target acquisition unit 33 acquires, as analysis target position data, position data whose position acquisition time information is within the analysis target period and whose position information is within the analysis target area from the storage unit 12A (step S1). S62). Subsequently, the analysis target terminal extraction unit 34 extracts an analysis target terminal to be analyzed for the person who has difficulty in returning home based on the analysis target position data acquired by the analysis target acquisition unit 33 (step S63).
- the estimation target terminal selection unit 35 excludes the mobile terminals of the users who live in the analysis target area from the analysis target terminals, and selects the remaining mobile terminals as mobile terminals to be estimated by those who have difficulty returning home.
- the number-of-terminals estimation part 36 estimates the number of the portable terminals selected as an estimation object of a person who has difficulty in returning home for every address information (step S65).
- the number-of-persons estimation unit 37 estimates the number of people who are difficult to return home for each address information from the number of portable terminals that are estimated by the number-of-terminals estimation unit 36 (step). S66).
- the number of persons who have difficulty in returning home estimates the number of persons who have difficulty in returning home and the number of persons based on the number of persons for each piece of address information estimated by the number of persons estimating unit 37 and the analysis target area (step S67). Then, the output unit 39 outputs information about the person who has difficulty in returning home (step S68).
- the residence estimation target position data in which the observation target period during which the stay is to be observed is set to, for example, a predetermined time zone at midnight is acquired and calculated based on the residence estimation target position data.
- the mobile terminal of the user who lives in the observation area can be estimated.
- the mobile terminals of users who reside in the observation area are excluded, and the remaining mobile terminals Is calculated.
- the number of mobile terminals of users who return from the analysis target area to another area in other words, flowed into the analysis target area from other areas.
- the number of user portable terminals can be estimated. Thereby, when a disaster occurs, for example, the position data of the mobile terminal can be used to predict a person who returns home from the analysis target area to be analyzed.
- the number of the remaining mobile terminals excluding the user's mobile terminal living in the analysis target area is the address information of the position data. Estimated every time. Then, the number of portable terminals estimated for each address information is converted into the number of people. That is, it is possible to estimate the number of people who return to another area from the analysis target area among the people existing in the analysis target area within the analysis target period for each address information that is a return destination.
- the mobile terminal of the user who lives in the analysis target area or the analysis target terminal whose address information is in the analysis target area is excluded. Thereby, it is possible to more accurately estimate the number of people who return from the analysis target area to another area among the people existing in the analysis target area within the analysis target period.
- the number of persons estimating unit 37 estimates the number of persons from the number of mobile terminals selected as the estimation target of those who have difficulty in returning home, and then the number of persons having difficulty in returning home estimates the number of persons having difficulty returning home.
- the order of estimating the number of people may be reversed. That is, after the number of difficult-to-reach persons estimation unit 38 estimates the number of portable terminals of persons who have difficulty returning home from the portable terminals selected as the estimation targets of those who have difficulty returning home, the number-of-persons estimation unit 37 The number of people may be estimated from the number.
- the ratio for each gender, the ratio for each age group, etc. it is desirable to obtain the ratio for each gender, the ratio for each age group, etc., and use it for estimating the population. Thereby, it is possible to obtain a distribution for each gender such as those who have difficulty in returning home or a distribution for each age group.
- the processing in this embodiment is performed. Detailed descriptions of components that perform the same processing as the configuration of the second embodiment are omitted.
- the configuration in which the estimated residence terminal list creating unit 25 creates the estimated residence terminal list based on the position data is the same as in the second embodiment. Below, the structure which estimates a person who has difficulty in returning home using the estimated residence terminal list created by the estimated residence terminal list creation unit 25 will be described.
- the analysis target period acquisition unit 31 acquires analysis target period information including a set of a start time and an end time for estimating a person who has difficulty in returning home.
- the analysis target area acquisition unit 32 acquires analysis target area information that is a target for estimating a person who has difficulty in returning home. In the present embodiment, unlike the second embodiment, the analysis target area acquisition unit 32 acquires information about the analysis target area that is an area different from the observation area as the analysis target area information.
- the analysis target acquisition unit 33 obtains, from the storage unit 12A, position data in which the position acquisition time information is within the analysis target period and the position information is within the analysis target area, which is a target area for estimating a person who is difficult to return home. Acquired as analysis target position data.
- the analysis target terminal extraction unit 34 extracts an analysis target terminal that is an object to be analyzed for those who have difficulty in returning home based on the analysis target position data acquired by the analysis target acquisition unit 33.
- the estimation target terminal selection unit 35 selects, from among the analysis target terminals extracted by the analysis target terminal extraction unit 34, the mobile terminal of the user who lives in the observation area as the mobile terminal that is the estimation target of the person who has difficulty in returning home. .
- the mobile terminal of the user who lives in this observation area is the mobile terminal whose address information of the position data corresponding to the analysis target terminal is the observation area, or the estimated residence terminal stored in the estimated residence terminal list storage unit 26 It is assumed that the mobile terminal is determined as the mobile terminal of the user who lives in the observation area based on the list.
- the mobile terminal of the user who lives in the observation area is the mobile terminal whose address information of the position data corresponding to the analysis target terminal is the observation area, and the estimated residence stored in the estimated residence terminal list storage unit 26. It becomes a portable terminal corresponding to at least one of portable terminals determined as portable terminals of users living in the observation area based on the local terminal list. Thereby, the portable terminal which the user who lives in an observation area owns among the portable terminals in an analysis object area is selected.
- the analysis target terminal in the analysis target area extracted by the analysis target terminal extraction unit 34 is “A”
- the mobile terminal whose location information is in the observation area is “C”
- the estimated residence terminal list The mobile terminal that is said to be resident in the observation area is represented by “O”.
- the estimation target terminal selection unit 35 selects the mobile terminal C whose address information is in the observation area or the mobile terminal O that is determined to be resident in the observation area from the estimated residence terminal list in the analysis target terminal A. , Select as a portable terminal to be estimated for those who have difficulty returning home. That is, the estimation target terminal selection unit 35 selects a mobile terminal corresponding to at least one of the mobile terminal C and the mobile terminal O among the analysis target terminals A as a mobile terminal to be estimated by a person who has difficulty returning home. .
- the terminal number estimation unit 36 estimates the number of mobile terminals selected by the estimation target terminal selection unit 35 as an estimation target of those who have difficulty in returning home. Note that, when the number of mobile terminals is estimated by the terminal number estimation unit 36, the feature amount is calculated for each position data as in the terminal number estimation unit 20 of the first embodiment described above, and the calculated feature amount is calculated. It is also possible to estimate the number of units. In this case, the terminal number estimation unit 36 estimates the number of mobile terminals based on the feature amount corresponding to each estimation target period while shifting the estimation target period, for example, every hour. Thereby, the number of portable terminals for each time zone can be estimated.
- the number of persons estimating unit 37 is a ratio between the number of terminals in the terminal area having one administrative division area in a predetermined wide area as address information and the population based on statistical data in one administrative division area included in the wide area.
- the number of mobile terminals is estimated based on the number of mobile terminals that are estimated by the terminal number estimation unit 36 and that are difficult to return. Thereby, the number of people who exist in the analysis target area within the analysis target period and whose return destination is the observation area is estimated. Thereby, it is possible to estimate how many people in the observation area are within the analysis target period and stay in the analysis target area.
- the number of persons who have difficulty in returning home 38 determines whether or not the person returning home whose observation destination is the observation area is a person who has difficulty returning home. Judging.
- the number of difficult return home estimation unit 38 is the analysis target area estimated by the number estimation unit 37. The number of people who return to the observation area is estimated as the number of people who have difficulty returning home.
- the terminal number estimation device 10A estimates how many residents in a certain analysis area are staying in which analysis area during the analysis target period. That is, the analysis target area acquisition unit 32 sequentially acquires different areas as analysis target areas to be estimated for those who have difficulty in returning home, and performs the above-described processing for each analysis target area, so that the number of people estimation unit 37 It is possible to estimate the number of people who return to the observation area from each analysis target area.
- the output unit 39 outputs information on the number of people who have difficulty in returning home estimated by the number of people who have difficulty returning home in a predetermined data format.
- Estimatimated residence terminal list creation process The estimated residence terminal list creation process according to the third embodiment is the same as the estimated residence terminal list creation process according to the second embodiment described with reference to FIG.
- the analysis target period acquisition unit 31 acquires analysis target period information including a set of a start time and an end time for estimating a person who has difficulty in returning home, and an analysis target area acquisition unit 32 obtains analysis target area information to be estimated for those who are difficult to return home (step S71).
- the analysis target acquisition unit 33 acquires, as analysis target position data, position data whose position acquisition time information is within the analysis target period and whose position information is within the analysis target area from the storage unit 12A (step S1). S72).
- the analysis target terminal extraction unit 34 extracts an analysis target terminal that is an object to be analyzed for those who have difficulty in returning home based on the analysis target position data acquired by the analysis target acquisition unit 33 (step S73).
- the estimation target terminal selection unit 35 selects, from the analysis target terminal, the portable terminal of the user who lives in the observation area as the estimation target of the person who has difficulty in returning home (step S74). And the terminal number estimation part 36 estimates the number of the portable terminals selected as an estimation object of a person having difficulty returning home (step S75). Subsequently, the number estimating unit 37 estimates the number of people returning to the observation area from the number of mobile terminals that are estimated by the terminal number estimating unit 36 as those who are difficult to return (step S76).
- the person who has difficulty in returning home is the person who has difficulty returning home. Determine whether or not.
- the number of persons having difficulty in returning home 38 estimates the number of persons having difficulty in returning home (step S77).
- the output part 39 outputs the information about a person who has difficulty in returning home (step S78).
- the residence estimation target position data in which the observation target period during which the stay is to be observed is set to, for example, a predetermined time zone at midnight is obtained and calculated based on the residence estimation target position data.
- the mobile terminal of the user who lives in the observation area can be estimated.
- the mobile terminals of users residing in the observation area are extracted, and the number of extracted mobile terminals is calculated.
- the number of mobile terminals of the users who return from the analysis target area to the observation area that is the residence in other words, the observation area that is the residence It is possible to estimate the number of user portable terminals that have flowed out of the analysis area.
- the position data of the mobile terminal can be used to predict the person who returns from the analysis target area to the observation area.
- the number of mobile terminals of users residing in the observation area among the analysis target terminals existing in the analysis target area within the analysis target period is estimated, and the estimated number of mobile terminals is converted into the number of persons. Is done. That is, it is possible to estimate the number of people who return to the observation area that is the residence from the analysis target area among the people existing in the analysis target area within the analysis target period.
- the mobile terminal of the user who lives in the observation area or the analysis target terminal whose address information is in the observation area is extracted.
- the number of persons estimating unit 37 estimates the number of persons from the number of mobile terminals selected as the estimation target of the person who has difficulty in returning home, and then the number of persons having difficulty in returning home estimates the person having difficulty in returning home.
- the order of estimating the number of people may be reversed. That is, after the number of difficult-to-reach persons estimation unit 38 estimates the number of persons who have difficulty in returning from the portable terminals selected as the estimation targets of those who have difficulty returning home, the number-of-persons estimation unit 37 estimates the number of persons from the number of portable terminals. Also good.
- the estimation target terminal selection unit 35 is that the address information resides in the observation area by the mobile terminal C in the observation area or the estimated residence terminal list.
- the selected mobile terminal O is selected as a mobile terminal to be estimated for those who have difficulty in returning home, but only mobile terminals O that are determined to be resident in the observation area according to the estimated residence terminal list are estimated for those who have difficulty in returning home. You may select as a portable terminal used as object. Even in this case, it is possible to estimate those who return home from the analysis target area to the observation area that is the residence, based on the estimated residence terminal list.
- the estimation target terminal selection unit 35 has a mobile terminal C whose address information is in the observation area and is resident in the observation area according to the estimated residence terminal list.
- the mobile terminal O may be selected as a mobile terminal to be estimated by a person who has difficulty in returning home. In this case, it is possible to estimate the user's mobile terminal whose residence is the observation area with higher accuracy.
- the ratio for each gender, the ratio for each age group, etc. it is desirable to obtain the ratio for each gender, the ratio for each age group, etc., and use it for estimating the population. Thereby, it is possible to obtain a distribution for each gender such as those who have difficulty in returning home or a distribution for each age group.
- a correction coefficient is calculated based on position data including a position registration signal and position data including a GPS signal, and the mobile phone is estimated from the position data based on the GPS signal using the calculated correction coefficient. This is to correct the number of terminals. Since the system configuration of the communication system according to the fourth embodiment is the same as the system configuration according to the first embodiment shown in FIG. 1, the description of the system configuration is omitted.
- FIG. 22 shows a functional block configuration of the terminal number estimation apparatus 10B according to the fourth embodiment.
- the terminal number estimation device 10B includes a position data acquisition unit (position data acquisition means) 11, an accumulation unit 12, an observation target period acquisition unit 13, an observation area acquisition unit 14, an observation target acquisition unit (observation target Acquisition means) 15B, front and rear position data acquisition section (front and rear position data acquisition means) 16B, feature quantity calculation section (feature quantity calculation means) 17B, expected stay time calculation section (expected stay time calculation means) 18B, estimation target terminal selection section (Estimation target terminal selection means) 19B, terminal number estimation section (terminal number estimation means, first stay time distribution calculation means, second stay time distribution calculation means) 20B, number correction section (number correction means) 50, number of terminals output And a correction coefficient calculation unit (correction coefficient calculation means) 60.
- the same components as those of the terminal number estimation device 10 according to the first embodiment are denoted by the same reference numerals, and detailed description thereof is omitted.
- the position data acquisition unit 11 acquires position data from the outside and stores it in the storage unit 12.
- the position data includes a position registration signal position data (first registered position data) including position information (first position information) obtained from the position registration signal, and a GPS positioning system when the mobile terminal uses GPS.
- GPS signal position data observed target position data, second registered position data
- the location registration signal is transmitted from the mobile terminal at a predetermined cycle. Further, for example, when the mobile terminal crosses an area across the power range of the antenna of the BTS 200, the mobile terminal transmits, the mobile terminal is turned on / off, etc. Is transmitted from the portable terminal based on the above condition.
- the transmission cycle of the location registration signal transmitted at a predetermined cycle is about every hour.
- the position information obtained by the GPS positioning system is based on the second condition such as when the user of the mobile terminal uses GPS, and when the mobile terminal automatically uses GPS to grasp the current position. Get based on.
- the timing at which the GPS signal position data is generated is shorter than the generation timing of the position registration signal position data generated based on the position registration signal transmitted at a predetermined cycle from the mobile terminal. This is because the GPS use interval at which the portable terminal automatically uses GPS to grasp the current position or the user uses GPS is shorter than the timing at which the position registration signal is transmitted.
- FIG. 23A shows an example of position registration signal position data
- FIG. 23B shows an example of GPS signal position data
- the location registration signal location data includes identification information of the mobile terminal, location information (sector number) obtained by the location registration signal, and location acquisition time when the location information was acquired.
- the position registration signal position data of the mobile terminal whose identification information is “B” has the sector number “S4” and the position acquisition time “t1”.
- the GPS signal position data includes identification information of the portable terminal, position information (latitude and longitude) obtained by using GPS, and a position acquisition time at which the position information is acquired.
- the GPS signal position data of the mobile terminal whose identification information is “A” has a latitude and longitude of “X4, Y5” and a position acquisition time of “t4”.
- the storage unit 12 stores position registration signal position data and GPS signal position data over a plurality of times for a large number of users (mobile terminals).
- the observation target acquisition unit 15B includes a position registration signal position in which the position acquisition time is within the observation target period and the position information is within the observation area to be observed from the position registration signal position data stored in the storage unit 12. Get the data.
- This position registration signal position data is a basis for calculating a correction coefficient described later.
- the observation target acquisition unit 15B has a GPS signal position in which the position acquisition time is within the observation target period and the position information is within the observation area to be observed from the GPS signal position data stored in the storage unit 12. Get the data.
- This GPS signal position data is a basis for calculating the distribution of the number of mobile terminals and also a basis for calculating a correction coefficient described later.
- the front / rear position data acquisition unit 16B after the position registration signal position data is acquired by the observation target acquisition unit 15B, is similar to the front / rear position data acquisition unit 16 in the first embodiment.
- the feature amount calculation unit 17B calculates a feature amount for each position registration signal position data.
- the expected stay time calculation part 18B calculates the expected stay time based on position registration signal position data similarly to the expected stay time calculation part 18 in 1st Embodiment.
- the front / rear position data acquisition unit 16B is the same as the front / rear position data acquisition unit 16 in the first embodiment, and the front / rear position data about the GPS signal position data is obtained.
- the feature amount calculation unit 17B calculates a feature amount for each GPS signal position data.
- the expected stay time calculation part 18B calculates the expected stay time based on GPS signal position data similarly to the expected stay time calculation part 18 in 1st Embodiment.
- the estimation target terminal selection unit 19B performs grouping for each stay time using the expected stay time based on the location registration signal calculated by the expected stay time calculation unit 18B. Specifically, the estimation target terminal selection unit 19B firstly calculates a group of mobile terminals with an expected stay time of 1 hour calculated by the expected stay time calculation unit 18B, a group of mobile terminals with an expected stay time of 2 hours, The mobile terminals are grouped for each expected stay time, such as a group of mobile terminals having a stay time of 3 hours. That is, as shown in FIG. 24, the mobile terminal group A whose position acquisition time information is within the observation target period and within the observation area where the position information is to be observed is determined for each expected stay time based on the expected stay time. Divided into groups B1, B2, B3,.
- the location registration signal is basically transmitted from the mobile terminal in units of about one hour. Therefore, it is considered appropriate to perform grouping according to the transmission cycle of this location registration signal. It is done. However, it is not essential that the time width of grouping matches the transmission cycle of the position registration signal, and grouping can be performed with an appropriate time width.
- the terminal number estimation unit 20B estimates the number of mobile terminals C1, C2, C3,... For each group B1, B2, B3,.
- the number of units is estimated using the feature amount within the estimation target period, similarly to the number of units estimation process in the terminal number estimation unit 20 of the first embodiment. Note that the estimation target period used when the terminal number estimation unit 20B estimates the number of mobile terminals is the observation target period acquired by the observation target period acquisition unit 13.
- a location registration signal stay time distribution (first order) indicating the relationship between the stay time of mobile terminals staying in the observation area and the number of stays for each stay time. 1 stay time distribution) is calculated.
- this location registration signal stay time distribution can be represented by a bar graph in which the horizontal axis is the stay time and the vertical axis is the number of mobile terminals.
- the stay time on the horizontal axis corresponds to the expected stay time.
- the number of mobile terminals with a stay time of 1 hour corresponds to the number C1 of FIG. 24 and the number of mobile terminals with a stay time of 2 hours (the number indicated by the bar graph X2).
- the bar graph X1 indicating the number of mobile terminals having a stay time of 1 hour is a mobile terminal satisfying an expected stay time of 0 hours to less than 1 hour in the observation target period. The number is shown. Alternatively, it may represent the number of mobile terminals with an expected stay time of 1 hour. Alternatively, the number of portable terminals that satisfy the expected stay time of 30 minutes or more and less than 1 hour 30 minutes may be represented.
- the bar graph X2 indicating the number of mobile terminals having a stay time of 2 hours is a mobile terminal that satisfies the expected stay time of 1 hour or more and less than 2 hours in the observation target period. This represents the number of mobile terminals acquired.
- the terminal number estimation unit 20B obtains an expression L (t) for obtaining the number of mobile terminals in the location registration signal stay time distribution shown in FIG.
- This expression L (t) corresponds to the bar graph shown in FIG. 25 and can be obtained as a function with the stay time t as a variable.
- the estimation target terminal selection unit 19B performs grouping for each stay time using the expected stay time based on the GPS signal calculated by the expected stay time calculation unit 18B. Specifically, the estimation target terminal selection unit 19B first performs the expected stay time calculated by the expected stay time calculation unit 18B, as in the case where the grouping is performed using the expected stay time based on the location registration signal.
- the mobile terminals are grouped for each expected stay time, such as a group of 5 minutes mobile terminals, a group of mobile terminals with an expected stay time of 10 minutes, a group of mobile terminals with an expected stay time of 15 minutes, and so on. In this case, it is considered appropriate to perform grouping in units of 5 minutes in consideration of the timing at which GPS position data is generated.
- the time width of grouping is not limited to 5 minutes, and grouping can be performed with an appropriate time width.
- the terminal number estimation unit 20B estimates the number of mobile terminals for each group that has been grouped.
- the number of units is estimated using the feature amount within the estimation target period, similarly to the number of units estimation process in the terminal number estimation unit 20 of the first embodiment.
- the estimation target period used when the terminal number estimation unit 20B estimates the number of mobile terminals is the observation target period acquired by the observation target period acquisition unit 13.
- the terminal number estimation unit 20B displays a GPS signal stay time distribution (relationship between the stay time of mobile terminals staying in the observation area and the number of each stay time ( (Second stay time distribution) is calculated.
- the GPS signal stay time distribution can be represented by a bar graph in which the horizontal axis is the stay time and the vertical axis is the number of mobile terminals.
- the stay time on the horizontal axis corresponds to the expected stay time.
- the bar graph Y1 indicating the number of mobile terminals having a stay time of 5 minutes is an estimate of mobile terminals satisfying an expected stay time of 0 minutes to less than 5 minutes in the observation target period. This represents the number of mobile terminals using GPS within the target period.
- the bar graph Y2 indicating the number of mobile terminals with a stay time of 10 minutes uses the GPS within the estimation target period among the mobile terminals that satisfy the expected stay time of 5 minutes to less than 10 minutes in the observation target period. This represents the number of mobile terminals.
- the number of bar graphs is shown to be smaller than the actual number (12 per hour when grouping is performed in units of 5 minutes) for easy viewing of the graph.
- the terminal number estimation unit 20B obtains an approximate curve G (t) for the number of mobile terminals for each stay time in the GPS signal stay time distribution.
- the GPS signal position data is a mobile terminal equipped with a GPS function and can be acquired when the mobile terminal uses GPS, the number of acquired data is small and the variation is large. is assumed. Thus, by obtaining an approximate curve, it is possible to suppress the influence of variation and the like.
- the approximate curve G (t) can be obtained as a function having the stay time t as a variable.
- the position registration signal stay time distribution based on the position registration signal position data (see FIG. 25) and the GPS signal stay time distribution based on the GPS signal position data (see FIG. 27) are obtained. It is done. As will be described in detail later, the location registration signal stay time distribution and the GPS signal stay time distribution are used for calculating a correction coefficient for correcting the number of mobile terminals. In addition, the GPS signal stay time distribution is used as basic data for calculating the number of mobile terminals for each stay time, and is corrected by a correction coefficient to be the number of mobile terminals for each stay time after correction. Is.
- the correction coefficient calculation unit 60 calculates a correction coefficient for correcting the number of mobile terminals based on the correlation between the location registration signal stay time distribution and the GPS signal stay time distribution obtained by the terminal number estimation unit 20B. .
- the mobile terminal that has transmitted the location registration signal is a parameter
- the mobile terminal using GPS can be considered as a sample for the parameter. For this reason, it is generated based on the location registration signal stay time distribution generated based on the location registration signal transmitted from the mobile terminal as a parameter and the fact that the mobile terminal as a sample for the parameter uses GPS.
- the GPS signal stay time distribution has a correlation.
- the correction coefficient calculation unit 60 first determines a correction coefficient calculation target period used for calculating a correction coefficient from the position registration signal stay time distribution and the GPS signal stay time distribution.
- the correction coefficient calculation target period for example, a period in which the number of mobile terminals is large is set with reference to the location registration signal stay time distribution (FIG. 25).
- the correction coefficient calculation target period is 1 hour or more and less than 3 hours.
- the correction coefficient calculation target period is not limited to this, and a value not based on the GPS signal stay time distribution can be set.
- the correction coefficient calculation unit 60 obtains the total number of mobile terminals whose stay time is the correction coefficient calculation target period (1 hour or more and less than 3 hours) in the location registration signal stay time distribution. When this is expressed using an equation L (t) for determining the number of mobile terminals, it is represented by the left side of the following equation (7).
- the area of the bar graph X2 representing the number of mobile terminals whose stay time is 1 hour or more and less than 2 hours, and the stay time is 2 hours or more and 3 hours.
- the sum of the area and the area of the bar graph X3 representing the number of mobile terminals less than that is obtained.
- the correction coefficient calculation unit 60 obtains the total number of mobile terminals whose stay time is the correction coefficient calculation target period (1 hour or more and less than 3 hours) in the GPS signal stay time distribution.
- this is expressed using the approximate curve G (t)
- it is expressed by an expression excluding “k” in the right side of the above expression (7). That is, in the graph showing the approximate curve G (t) shown in FIG. 28B, the area of the region Y between the approximate curve G (t) and the horizontal axis when the stay time is 1 to 3 hours is obtained. .
- the correction coefficient calculation unit 60 obtains a value of the coefficient k that satisfies the above equation (7) in order to obtain a correlation between the position registration signal stay time distribution and the GPS signal stay time distribution.
- This coefficient k is a correction coefficient k for correcting the number of mobile terminals based on the correlation between the location registration signal stay time distribution and the GPS signal stay time distribution.
- the correction coefficient calculation unit 60 outputs the calculated correction coefficient to the number correction unit 50 after calculating the correction coefficient k.
- the number correction unit 50 acquires the correction coefficient k calculated by the correction coefficient calculation unit 60 and the approximate curve G (t) in the GPS signal stay time distribution obtained by the terminal number estimation unit 20B.
- the distribution of the number of mobile terminals for each staying time after correction can also be expressed by the graph shown in FIG.
- the terminal number output unit 21B outputs the number distribution for each staying time corrected by the number correction unit 50.
- the position data acquisition unit 11 acquires position data including position registration signal position data and GPS signal position data from the outside, and stores them in the storage unit 12 (step S81).
- the observation target period acquisition unit 13 acquires observation target period information including a set of start time and end time, and the observation area acquisition unit 14 correlates with one or more pieces of position information. Is acquired (step S82).
- the observation target acquisition unit 15B registers the position where the position acquisition time is within the observation target period and the position information is within the observation area to be observed from the GPS signal position data stored in the storage unit 12.
- Signal position data and GPS signal position data are acquired (step S83).
- steps S84 to S87 are executed for each of the acquired position registration signal position data and GPS signal position data.
- step S4 for acquiring front and rear position data step S5 for calculating feature values, and calculation of feature values for all position data in the first embodiment are determined. This is the same as the process of step S6 and step S7 for calculating the expected stay time, and a description thereof will be omitted.
- the estimation target terminal selection unit 19B performs grouping for each stay time using the expected stay time based on the position registration signal, and performs grouping for each stay time using the expected stay time based on the GPS signal.
- the terminal number estimation unit 20B estimates the number of portable terminals for each group, and calculates an expression L (t) representing the location registration signal stay time distribution and an approximate curve G (t) of the GPS signal stay time distribution. (Step S89).
- the correction coefficient calculation unit 60 calculates a correction coefficient based on the expression L (t) representing the position registration signal stay time distribution and the approximate curve G (t) of the GPS signal stay time distribution (step S90).
- the number correction unit 50 corrects the number distribution for each staying time of the mobile terminal using the correction coefficient k and the approximate curve G (t) (step S91).
- the terminal number output part 21B outputs the number distribution for every stay time after the correction
- the correction coefficient calculation unit 60 determines a correction coefficient calculation target period used for calculating the correction coefficient (step S101). Next, the correction coefficient calculation unit 60 acquires L (t) representing the location registration signal stay time distribution and the approximate curve G (t) of the GPS signal stay time distribution from the terminal number estimation unit 20B (step S102, S103).
- the correction coefficient calculation unit 60 calculates the correction coefficient k according to the above equation (7) using the correction coefficient calculation target period, the equation L (t), and the approximate curve G (t) (Ste S104). After calculating the correction coefficient k, the correction coefficient calculation unit 60 outputs the calculated correction coefficient k to the number correction unit 50 (step S105).
- the terminal number estimation unit 20B calculates the position registration signal stay time distribution based on the position registration signal position data and the GPS signal stay time distribution based on the GPS signal position data. Then, the correction coefficient calculation unit 60 calculates the correction coefficient k using the equation L (t) representing the location registration signal stay time distribution and the approximate curve G (t) of the GPS signal stay time distribution.
- the correction coefficient k can correct the number of portable terminals for each staying time estimated based on the GPS signal position data based on the position registration signal position data. Therefore, the number correction unit 50 uses the correction coefficient k to correct the number of mobile terminals for each stay time calculated based on the GPS signal position data, thereby further increasing the number distribution for each stay time of the mobile terminal. Accurate estimation is possible.
- the terminal number estimation apparatus 10B according to the fourth embodiment described above estimates the population in the observation area during the estimation target period, as shown in FIG. 32, as in the modification of the terminal number estimation apparatus 10 according to the first embodiment.
- a population estimation unit (population estimation means) 22 may be further provided.
- the population estimation unit 22 is a ratio of the number of terminals in a predetermined wide area that has one administrative division area as address information to the population based on statistical data in one administrative division area included in the wide area.
- the “terminal contract rate” which is the ratio of “the number of contracted terminals of a specific communication carrier from which location data is obtained” in the “population in a predetermined area” It may be used.
- the ratio for each region the ratio for each gender, the ratio for each age group, and the like to estimate the population.
- the population may be estimated by obtaining the ratio between the number of areas in the country and the population during the estimation target period or a certain number. Moreover, you may use the ratio calculated
- the address information of the user of the portable terminal corresponding to the identification information included in the position data is further associated with the position data and stored in the storage unit 12.
- the number distribution for each staying time of the mobile terminal can be estimated, and the population can be estimated based on the estimated number distribution.
- the number correction unit 50 corrects the GPS signal stay time distribution using the correction coefficient k.
- the position registration signal stay time distribution may be corrected.
- the stay time distribution can be corrected by dividing the position registration signal stay time distribution by the correction coefficient k.
- the terminal number estimation unit 20B calculates a GPS signal stay time distribution indicating the relationship between the stay time of the mobile terminal and the number of mobile terminals for each stay time, and the number correction unit 50 uses the correction coefficient.
- this correction target is not limited to the GPS signal stay time distribution indicating the relationship between the stay time of the mobile terminal and the number of each stay time.
- a distribution indicating how many mobile terminals staying in the observation area for a predetermined time were present at each time during the observation target period may be used. That is, in FIG. 33, only the mobile terminal staying for a predetermined time is shown. This distribution can be obtained as a function having time t as a variable.
- the estimation target terminal selection unit 19B uses the expected stay time generated based on the GPS position data, and has stayed for a predetermined time (for example, 1 to 3 hours). Mobile terminal).
- the number-of-terminals estimation unit 20B estimates the number of units using the feature amount within the estimation target period, as in the number-of-units estimation process in the number-of-terminals estimation unit 20 of the first embodiment. Note that the estimation target period used when the terminal number estimation unit 20B estimates the number of mobile terminals is set at a 5-minute interval, and the number of mobile terminals is estimated while shifting the estimation target period at 5-minute intervals within the observation period.
- a correction coefficient k is obtained by using a predetermined time (for example, 1 to 3 hours) during which the mobile terminal that has obtained the number distribution at each time stays in the observation area. Thereby, the number distribution at each time in the observation target time in the mobile terminal staying in the observation area for a predetermined time can be obtained more accurately.
- the number distribution of mobile terminals for each staying time can be obtained as in the position registration signal staying time distribution shown in FIG. 25 obtained in the fourth embodiment.
- the passage stay terminal selection unit 19 according to the first embodiment uses the expected stay time for each portable terminal calculated by the expected stay time calculation unit 18 for each stay time (for example, every hour). Perform grouping. And the terminal number estimation part 20 estimates the number of portable terminals for every group. Note that the estimation target period used when the terminal number estimation unit 20 estimates the number of mobile terminals is the observation target period. Thereby, as shown in FIG. 34, also in the terminal number estimation apparatus 10 of 1st Embodiment, the number distribution for every staying time of a portable terminal can be obtained.
- the number distribution at each time as shown in FIG. 33 can be obtained for each of the staying portable terminal and the passing portable terminal.
- the terminal number estimation unit 20 estimates the number of staying portable terminals at each time, for example, the estimation target period is shifted every five minutes, for example.
- the number of mobile terminals for each time zone can be estimated.
- FIG. 35 it is possible to obtain a distribution indicating how many mobile terminals staying in the observation area existed at each time during the observation target time. By performing the same processing, the number distribution at each time can also be obtained for the passing portable terminal.
- the terminal number estimation units 20 and 20B divide each feature quantity wij for each position data by 2, and ( The sum total of the feature amounts wij / 2) may be obtained, and a numerical value obtained by dividing the obtained sum by the estimation target period length T may be estimated as the number of terminals.
- the calculation method in which the total sum of the feature values wij for each position data is divided by twice the estimation target period length T as in each of the above-described embodiments requires an extremely small number of divisions. There is an advantage that the load can be reduced.
- the feature value calculation method for calculating the expected staying time is not limited to the method described above.
- the position data acquired in each time length from 0 o'clock to 1 o'clock, 1 o'clock to 2 o'clock, ..., 23 o'clock to 24 o'clock is counted for each mobile terminal, and the position in each time length for each mobile terminal
- the reciprocal of the number of data is set as the weight of the position data within each time length.
- the weight value can also be used as the feature amount described in each embodiment.
- the time difference (time difference between the second position data and the third position data) before and after the position data (first position data) for which the feature amount is to be obtained is calculated using the first
- An example of calculating the feature value of the position data has been shown.
- the feature amount can be expressed by the following equation (9).
- equation (9) is only the deformation
- w ij u i (j + 1) ⁇ u i (j ⁇ 1) (9)
- This modification shows another variation of the feature amount calculation method calculated by the feature amount calculation unit 17.
- the feature quantity calculation unit 17 obtains the type information (for example, position data generation factors described later) for the second position data and the third position data when obtaining the feature quantity of the first position data. (Generation timing)). Specifically, the feature amount calculation unit 17 calculates a correction coefficient ⁇ corresponding to the type information (generation factor here) of the third position data with respect to the time difference between the third position data and the first position data. A value obtained by multiplying the time difference between the first position data and the second position data by a correction coefficient ⁇ corresponding to the type information (generation factor in this case) of the second position data is calculated. calculate.
- the feature amount calculation unit 17 may determine the correction coefficient ⁇ or ⁇ according to the type information of the first position data, or may use the type information of the first and second position data. Accordingly, the correction coefficient ⁇ may be determined or the correction coefficient ⁇ may be determined according to the type information of the first and third position data. And the feature-value calculation part 17 makes the value which added the value obtained by these multiplications the feature-value of 1st position data.
- the type information about the second position data and the third position data for example, when the position data is position registration information, information on the generation factor of the position registration information can be cited. It is included in the generated location registration information. Factors for generating location registration information include that the terminal has crossed the location registration area (Location Area) boundary, that it has been generated based on location registration that is performed periodically, that the attachment process is performed by powering on the terminal, etc. For example, the detachment process is executed when the power is turned off.
- the set values of the correction coefficients ⁇ and ⁇ are determined in advance corresponding to these generation factors.
- the feature amount calculation unit 17 sets the correction coefficient ⁇ for the third position data according to the information regarding the generation factor of the third position data, and sets the correction coefficient ⁇ for the third position data according to the information regarding the generation factor of the second position data.
- the correction coefficient ⁇ for the position data 2 may be set. Both the correction coefficients ⁇ and ⁇ may be set in advance to a value of 0 or more and 2 or less. However, this numerical range is not essential.
- the expectation of the time spent in the current sector The value is considered to be the same before and after the location registration information is generated.
- location registration information generated by a terminal straddling a location registration area boundary it can be determined that the terminal has not stayed in the current sector at least before the location registration information is generated.
- the time that the terminal stayed in the current sector before the location registration information is generated is considered as 0, and the type information (generation factor) of the first location data is “location registration area boundary straddle”
- the correction coefficient ⁇ in the above equation (10) that is, the correction coefficient ⁇ related to the time difference from the previous position data
- the feature amount calculation unit 17 calculates the feature amount for the target position data (first position data), the second and third positions which are position data before and after the first position data.
- the time difference between the second position data and the third position data is corrected according to the type information about the data (for example, the generation factor of the position data), and the feature amount is calculated using the corrected time difference.
- the feature amount can be calculated with higher accuracy based on the type information of the position data.
- Estimated residence terminal list creation section (estimation target terminal selection means), 33 ... Analysis target acquisition section (analysis target acquisition means), 34 ... Analysis target terminal extraction section (analysis) Elephant terminal extraction means), 35 ... estimation target terminal selection section (estimation target terminal selection means), 36 ... terminal number estimation section (terminal number estimation means), 38 ... difficult to return home estimation section (difficult to return home estimation means) 50... Number correction unit (number correction unit) 60.
- Correction coefficient calculation unit correctionion coefficient calculation unit
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
- Mobile Radio Communication Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Navigation (AREA)
Abstract
Description
[通信システムの構成]
図1は、第1実施形態の通信システム1のシステム構成図である。図1に示すように、この通信システム1は、携帯端末100、BTS(基地局)200、RNC(無線制御装置)300、交換機400、各種処理ノード700、及び管理センタ500を含んで構成されている。また、この管理センタ500は、社会センサユニット501、ペタマイニングユニット502、モバイルデモグラフィーユニット503、及び可視化ソリューションユニット504から構成されている。
次に、第1実施形態に係る端末数推計装置について説明する。図2に、端末数推計装置10の機能ブロック構成を示す。図2に示すように、端末数推計装置10は、位置データ取得部(位置データ取得手段)11、蓄積部12、観測対象期間取得部13、観測エリア取得部14、観測対象取得部(観測対象取得手段)15、前後位置データ取得部(前後位置データ取得手段)16、特徴量算出部(特徴量算出手段)17、期待滞在時間算出部(期待滞在時間算出手段)18、通過滞留端末選択部(推計対象端末選択手段)19、端末数推計部(端末数推計手段)20、及び端末数出力部21を含んで構成される。
次に、端末数推計の考え方及び計算方法を説明する。図5に示すモデルのように、ある推計対象期間(長さT)の間に、n個の端末a1,a2,…,anがセクタSを通過し、各端末aiの推計対象期間内のセクタSの滞在時間がti(0<ti≦T)であったとする。このとき、セクタSに存在する端末数m(実際にはセクタSに存在する端末数mの推計対象期間内における平均値)は、以下の式(1)で表わされる。
即ち、各端末aiの推計対象期間内のセクタSの滞在時間tiの総和を推計対象期間の長さTで除した結果を、端末数mとして推計する。ただし、端末aiの推計対象期間内のセクタSの滞在時間tiの真の値は観測不能であるが、各端末aiは信号(例えば位置登録情報を含む位置登録信号)を発信し、それらの信号は観測可能である。
(xiは、端末aiが推計対象期間内にセクタSで発信した信号の総数)とすると、端末数の推計とは、観測された信号qij(jは1以上xi以下の整数)からmの値を推計することに他ならない。
E(ti)=xi/pi (2)
ここで、信号qijの送信時刻をuijとしたとき、信号qijの密度pijは、以下の式(3)で与えられる。
pij=2/(ui(j+1)-ui(j-1)) (3)
ここで、信号qijを第1の位置データに係る信号とすると、信号qi(j-1)は第2の位置データに係る信号、信号qi(j+1)は第3の位置データに係る信号に相当する。本実施形態では、第2の位置データに係る信号qi(j-1)の送信時刻ui(j-1)と第3の位置データに係る信号qi(j+1)の送信時刻ui(j+1)の差、即ち、上記式(3)の(ui(j+1)-ui(j-1))を、第1の位置データについての特徴量wijとする(特徴量wij=ui(j+1)-ui(j-1))。そのため、上記式(3)は、以下となる。
pij=2/(ui(j+1)-ui(j-1))=2/wij (4)
以下、本発明の端末数推計方法に係る端末数推計処理を説明する。ここでは、携帯端末の位置データに含まれる位置情報には、一例として、当該携帯端末が在圏するセクタのセクタ番号が与えられているものとする。
条件1:位置取得時刻が、開始時刻t0以降であり且つ終了時刻t1以前である。即ち、観測対象期間内に含まれる。
条件2:位置情報がセクタSである。
次に、通過携帯端末及び滞留携帯端末の台数推計処理の変形例について説明する。上述した通過携帯端末及び滞留携帯端末の台数推計処理では、特徴量を計算する対象の位置データを観測対象位置データに絞ったが、この変形例として、取得された全ての位置データを対象として特徴量を計算した後、推計で利用する特徴量を絞ってもよい。本変形例に係る端末数推計装置10の構成例を図9に、携帯端末の台数推計処理内容を図10に、それぞれ示す。
前述した第1実施形態の端末数推計装置10は、図11に示すように、推計対象期間中の観測エリアにおける人口を推計する人口推計部(人口推計手段)22を更に備えてもよい。この人口推計部22は、予め定められた広域エリアにおける一のユーザ属性を有する端末の在圏数と当該広域エリアに含まれる一のユーザ属性における統計データに基づく人口との比率と、に基づいて一のユーザ属性の人口を推計する。ここでの一のユーザ属性には、性別、年代などのほか、住所属性をも含むものとする。
次に、第2実施形態について説明する。本実施形態は、ある分析対象エリアから他のエリアへ帰宅する帰宅困難者を推定するものである。なお、帰宅困難者とは、現在の位置から居住地(自宅)までの距離が遠く、災害発生時に公共交通機関等が利用できないために帰宅が困難になる者をいう。また、第2実施形態の通信システムのシステム構成は、図1の第1実施形態におけるシステム構成と同様であるため、同システム構成の説明を省略する。
図12に、端末数推計装置10Aの機能ブロック構成を示す。図12に示すように端末数推計装置10Aは、位置データ取得部(位置データ取得手段)11A、蓄積部12A、観測対象期間取得部13、観測エリア取得部14、観測対象取得部(観測対象取得手段)15、前後位置データ取得部(前後位置データ取得手段)16A、特徴量算出部(特徴量算出手段)17A、期待滞在時間算出部(期待滞在時間算出手段)18A、推定居住地端末リスト作成部(推計対象端末選択手段)25、推定居住地端末リスト保管部26、分析対象期間取得部31、分析対象エリア取得部32、分析対象取得部(分析対象取得手段)33、分析対象端末抽出部(分析対象端末抽出手段)34、推計対象端末選択部(推計対象端末選択手段)35、端末数推計部(端末数推計手段)36、人数推計部(人数推計手段)37、帰宅困難者数推定部(帰宅困難者数推定手段)38、及び出力部39を含んで構成される。
以下、第2実施形態に係る推定居住地端末リスト作成処理を説明する。図17に示すように、まず、位置データ取得部11Aが位置データを取得し蓄積部12Aに保存する(図17のステップS51)。これにより、蓄積部12Aは、多数のユーザ(携帯端末)についての複数の時刻にわたる位置データを保存することとなる。なお、ステップS51の処理実行後、ステップS52以降の処理は、時間をおいて実行してもよい。即ち、ステップS52以降の処理の事前準備として、ステップS51を実行してもよい。
以下、第2実施形態に係る帰宅困難者推定処理を説明する。帰宅困難者推定処理は、上述の推定居住地端末リスト作成処理の後で行われるものである。図18に示すように、まず、分析対象期間取得部31が、帰宅困難者の推定を行う開始時刻と終了時刻との組を含む分析対象期間情報を取得するとともに、分析対象エリア取得部32が、帰宅困難者の推定を行う対象となる分析対象エリア情報(本実施形態では観測エリア情報と同じ)を取得する(ステップS61)。次に、分析対象取得部33が、蓄積部12Aから、位置取得時刻情報が分析対象期間内であり、且つ位置情報が分析対象エリア内である位置データを、分析対象位置データとして取得する(ステップS62)。続いて、分析対象端末抽出部34が、分析対象取得部33で取得された分析対象位置データに基づいて、帰宅困難者についての分析を行う対象となる分析対象端末を抽出する(ステップS63)。
次に、第3実施形態について説明する。本実施形態は、ある観測エリアに居住する住民が、分析対象期間内に、どの分析対象エリアに何人滞留しているかを推計するものである。また、第3実施形態の通信システムのシステム構成は、図1の第1実施形態におけるシステム構成と同様であるため、同システム構成の説明を省略する。
第3実施形態の端末数推計装置10Aの機能構成は、図12の第2実施形態における機能構成とほぼ同様であるため、ここでは、第2実施形態に係る端末数推計装置10Aとの相違点を中心に説明する。第3実施形態の端末数推計装置10Aでは、第2実施形態の端末数推計装置10Aに対し、特に、分析対象エリア取得部32が分析対象エリアとして取得する情報、及び推計対象端末選択部35の処理内容が異なる。なお、推計対象端末選択部35は、分析対象エリア取得部32が分析対象エリア情報として取得した情報が観測エリア情報と同一である場合には、第2実施形態で説明した処理を行い、分析対象エリア取得部32が分析対象エリア情報として取得した情報が観測エリア情報と異なる場合には、本実施形態における処理を行う。また、第2実施形態の構成と同様の処理を行う構成要素については、詳細な説明を省略する。なお、推定居住地端末リスト作成部25が、位置データに基づいて推定居住地端末リストを作成する構成は、第2実施形態と同じである。以下においては、推定居住地端末リスト作成部25で作成された推定居住地端末リストを用いて、帰宅困難者を推定する構成について説明する。
第3実施形態に係る推定居住地端末リスト作成処理は、図17を用いて説明した、第2実施形態に係る推定居住地端末リスト作成処理と同じであり、説明を省略する。
以下、第3実施形態に係る帰宅困難者推定処理を説明する。図21に示すように、まず、分析対象期間取得部31が、帰宅困難者の推定を行うための開始時刻と終了時刻との組を含む分析対象期間情報を取得するとともに、分析対象エリア取得部32が、帰宅困難者の推定を行う対象となる分析対象エリア情報を取得する(ステップS71)。次に、分析対象取得部33が、蓄積部12Aから、位置取得時刻情報が分析対象期間内であり、且つ位置情報が分析対象エリア内である位置データを、分析対象位置データとして取得する(ステップS72)。続いて、分析対象端末抽出部34が、分析対象取得部33で取得された分析対象位置データに基づいて、帰宅困難者についての分析を行う対象となる分析対象端末を抽出する(ステップS73)。
次に、第4実施形態について説明する。本実施形態は、位置登録信号を含む位置データと、GPS信号を含む位置データと、に基づいて補正係数を算出し、算出した補正係数を用いて、GPS信号に基づく位置データより推計される携帯端末の台数を補正するものである。第4実施形態の通信システムのシステム構成は、図1の第1実施形態におけるシステム構成と同様であるため、同システム構成の説明を省略する。
次に、第4実施形態に係る端末数推計装置について説明する。図22に、第4実施形態に係る端末数推計装置10Bの機能ブロック構成を示す。図22に示すように、端末数推計装置10Bは、位置データ取得部(位置データ取得手段)11、蓄積部12、観測対象期間取得部13、観測エリア取得部14、観測対象取得部(観測対象取得手段)15B、前後位置データ取得部(前後位置データ取得手段)16B、特徴量算出部(特徴量算出手段)17B、期待滞在時間算出部(期待滞在時間算出手段)18B、推計対象端末選択部(推計対象端末選択手段)19B、端末数推計部(端末数推計手段、第1滞在時間分布算出手段、第2滞在時間分布算出手段)20B、台数補正部(台数補正手段)50、端末数出力部21B、及び補正係数算出部(補正係数算出手段)60を含んで構成される。
以下、本実施形態における携帯端末の滞在時間毎の台数分布算出処理を説明する。図30に示すように、まず、位置データ取得部11が、位置登録信号位置データとGPS信号位置データとを含む位置データを外部から取得し、蓄積部12に保存する(ステップS81)。
以下、図30のステップS90において補正係数kを算出する処理の詳細を説明する。図31に示すように、補正係数算出部60は、補正係数を算出するために用いられる補正係数算出対象期間を決定する(ステップS101)。次に、補正係数算出部60は、端末数推計部20Bから、位置登録信号滞在時間分布を表すL(t)とGPS信号滞在時間分布の近似曲線G(t)とを取得する(ステップS102,S103)。
前述した第4実施形態の端末数推計装置10Bは、第1実施形態における端末数推計装置10の変形例と同様に、図32に示すように、推計対象期間中の観測エリアにおける人口を推計する人口推計部(人口推計手段)22を更に備えてもよい。この人口推計部22は、予め定められた広域エリアにおける一の行政区画エリアを住所情報とする端末の在圏数と当該広域エリアに含まれる一の行政区画エリアにおける統計データに基づく人口との比率(例えば、推計対象期間中の観測エリアを含む広域エリア(例えば日本全国)における携帯端末の在圏数と、この行政区画エリア(例えば、東京都)人口との比率)と、台数補正部50により得られた端末数と、に基づいて人口を推計する。これにより、携帯端末の滞在時間毎の台数分布から、滞在時間毎の人数を推計することができる。
wij=ui(j+1)-ui(j-1) (9)
本変形例は、特徴量算出部17において算出される特徴量の算出方法の別のバリエーションを示すものである。
wij=α(ui(j+1)-uij)+β(uij-ui(j-1)) (10)
Claims (19)
- 携帯端末を識別する識別情報、前記携帯端末の位置に関する位置情報、及び前記位置情報が取得された位置取得時刻情報を含む位置データを取得する位置データ取得手段と、
前記位置取得時刻情報が滞在を観測すべき観測対象期間内であり、且つ前記位置情報が観測すべき観測エリア内である位置データを、観測対象位置データとして取得する観測対象取得手段と、
前記観測対象取得手段で取得された前記観測対象位置データに含まれる前記位置取得時刻情報に基づいて、当該観測対象位置データについての特徴量を算出する特徴量算出手段と、
携帯端末の識別情報毎に、前記特徴量算出手段で算出された特徴量の合計値を、滞在時間を表す期待滞在時間として算出する期待滞在時間算出手段と、
前記期待滞在時間に基づいて、台数の推計対象となる携帯端末を選択する推計対象端末選択手段と、
前記推計対象端末選択手段によって選択された携帯端末の台数の推計を行う端末数推計手段と、
を備えることを特徴とする端末数推計装置。 - 前記推計対象端末選択手段は、前記期待滞在時間が予め定められた通過滞留判定閾値未満の携帯端末を、前記観測エリアを通過する通過携帯端末として抽出すると共に、抽出した前記通過携帯端末を前記台数の推計対象となる携帯端末として選択することを特徴とする請求項1に記載の端末数推計装置。
- 前記推計対象端末選択手段は、前記期待滞在時間が予め定められた通過滞留判定閾値以上の携帯端末を、前記観測エリアに滞留する滞留携帯端末として抽出すると共に、抽出した前記滞留携帯端末を前記台数の推計対象となる携帯端末として選択することを特徴とする請求項1又は2に記載の端末数推計装置。
- 前記推計対象端末選択手段は、前記期待滞在時間が予め定められた2つの通過滞留判定閾値の間に含まれる携帯端末を、前記観測エリアに滞留する滞留携帯端末として抽出すると共に、抽出した前記滞留携帯端末を前記台数の推計対象となる携帯端末として選択することを特徴とする請求項1又は2に記載の端末数推計装置。
- 前記端末数推計手段は、前記携帯端末の台数を推計するときに、予め定められた推計対象期間内における台数の推計を行うことを特徴とする請求項1~4のいずれか一項に記載の端末数推計装置。
- 前記端末数推計手段で推計された携帯端末の台数と、予め定められた広域エリアにおける一のユーザ属性を有する端末の在圏数と当該広域エリアに含まれる前記一のユーザ属性における統計データに基づく人口との比率と、に基づいて前記一のユーザ属性の人口を推計する人口推計手段を、更に備えることを特徴とする請求項5に記載の端末数推計装置。
- 前記端末数推計手段で推計された携帯端末の台数と、予め定められた広域エリアにおける一の行政区画エリアを住所情報とする端末の在圏数と当該広域エリアに含まれる一の行政区画エリアにおける統計データに基づく人口との比率と、に基づいて当該一の行政区画エリアの人口を推計する人口推計手段を、更に備えることを特徴とする請求項5に記載の端末数推計装置。
- 前記位置取得時刻情報が分析すべき分析対象期間内であり、且つ前記位置情報が前記観測エリア内である位置データを、分析対象位置データとして取得する分析対象取得手段と、
前記分析対象取得手段で取得された分析対象位置データに基づいて、分析すべき分析対象端末を抽出する分析対象端末抽出手段と、を更に備え、
前記推計対象端末選択手段は、
前記期待滞在時間に基づいて、前記観測エリア内に居住するユーザの携帯端末を推定し、
前記分析対象端末抽出手段で抽出された分析対象端末から、前記観測エリア内に居住するものとして推定されたユーザの携帯端末を除いた携帯端末を、前記端末数推計手段による台数の推計対象となる携帯端末として選択する、
ことを特徴とする請求項1に記載の端末数推計装置。 - 前記位置データは、前記携帯端末のユーザの住所情報を更に含み、
前記端末数推計手段は、前記携帯端末の台数の推計を行う際に、携帯端末に対応する位置データの住所情報に基づいて推計対象エリア毎に台数を推計するものであり、
前記推計対象エリア毎に推計された携帯端末の台数と、予め定められた広域エリアにおける一の推計対象エリアを住所情報とする端末の在圏数と当該広域エリアに含まれる一の推計対象エリアにおける統計データに基づく人口との比率と、に基づいて、推計対象エリア毎の人数を推計する人数推計手段を、更に備える、
ことを特徴とする請求項8に記載の端末数推計装置。 - 前記人数推計手段によって推計された推計対象エリア毎の人数と、前記観測エリアと、に基づいて、前記観測エリアから前記推計対象エリアへの帰宅が困難となる帰宅困難者の人数を推定する帰宅困難者数推定手段を更に備える、
ことを特徴とする請求項9に記載の端末数推計装置。 - 前記推計対象端末選択手段は、前記分析対象端末の中から、前記観測エリア内に居住するものとして推定されたユーザの携帯端末、又は前記分析対象端末に対応する前記位置データの住所情報が前記観測エリア内である分析対象端末、を除いた携帯端末を、前記端末数推計手段による台数の推計対象となる携帯端末として選択する、
ことを特徴とする請求項9又は10に記載の端末数推計装置。 - 前記位置取得時刻情報が分析すべき分析対象期間内であり、且つ前記位置情報が分析すべき分析対象エリア内である位置データを、分析対象位置データとして取得する分析対象取得手段と、
前記分析対象取得手段で取得された分析対象位置データに基づいて、分析すべき分析対象端末を抽出する分析対象端末抽出手段と、を更に備え、
前記推計対象端末選択手段は、
前記期待滞在時間に基づいて、前記観測エリア内に居住するユーザの携帯端末を推定し、
前記分析対象端末抽出手段で抽出された分析対象端末から、前記観測エリア内に居住するものとして推定されたユーザの携帯端末を抽出し、抽出した携帯端末を前記端末数推計手段による台数の推計対象となる携帯端末として選択する、
ことを特徴とする請求項1に記載の端末数推計装置。 - 前記端末数推計手段で推計された携帯端末の台数と、予め定められた広域エリアにおける一の観測対象エリアを住所情報とする端末の在圏数と当該広域エリアに含まれる一の観測対象エリアにおける統計データに基づく人口との比率と、に基づいて、前記分析対象期間内に前記分析対象エリア内に存在する人の中で、前記観測エリア内に居住する人数を推計する人数推計手段を、更に備えることを特徴とする請求項12に記載の端末数推計装置。
- 前記人数推計手段によって推計された、前記分析対象期間内に分析対象エリアに存在する人の中で前記観測エリア内に居住する人数と、前記分析対象エリアと、に基づいて、前記分析対象エリアから前記観測エリアまでの帰宅が困難となる帰宅困難者の人数を推定する帰宅困難者数推定手段を更に備える、
ことを特徴とする請求項13に記載の端末数推計装置。 - 前記位置データは、前記携帯端末のユーザの住所情報を更に含み、
前記推計対象端末選択手段は、前記分析対象端末の中から、前記観測エリア内に居住するものとして推定されたユーザの携帯端末、又は前記分析対象端末に対応する前記位置データの住所情報が前記観測エリア内である分析対象端末、を抽出し、抽出した携帯端末を前記端末数推計手段による台数の推計対象となる携帯端末として選択する、
ことを特徴とする請求項12~14のいずれか一項に記載の端末数推計装置。 - 前記位置データ取得手段が取得する前記位置データは、前記携帯端末が登録した第1位置情報を含む第1登録位置データと、前記携帯端末が登録した第2位置情報を含む第2登録位置データと、を含み、
前記観測対象取得手段は、前記位置取得時刻情報が滞在を観測すべき観測対象期間内であり、且つ前記位置情報が観測すべき観測エリア内である前記第2登録位置データを、前記観測対象位置データとして取得するものであり、
前記第1登録位置データに基づいて、前記観測エリア内に滞在する携帯端末の滞在時間と滞在時間毎の台数との関係を示す第1滞在時間分布を算出する第1滞在時間分布算出手段と、
前記第2登録位置データに基づいて、前記観測エリア内に滞在する携帯端末の滞在時間と滞在時間毎の台数との関係を示す第2滞在時間分布を算出する第2滞在時間分布算出手段と、
前記第1滞在時間分布と前記第2滞在時間分布との相関関係に基づいて、前記携帯端末の台数を補正する補正係数を算出する補正係数算出手段と、
前記補正係数算出手段で算出された補正係数を用いて、前記端末数推計手段で推計された携帯端末の台数の補正を行う台数補正手段と、を更に備える、
ことを特徴とする請求項1に記載の端末数推計装置。 - 前記端末数推計手段で推計された携帯端末の台数と、予め定められた広域エリアにおける一のユーザ属性を有する端末の在圏数と当該広域エリアに含まれる前記一のユーザ属性における統計データに基づく人口との比率と、に基づいて前記一のユーザ属性の人口を推計する人口推計手段を、更に備えることを特徴とする請求項16のいずれか一項に記載の端末数推計装置。
- 前記観測対象位置データのある第1の位置データについて、当該第1の位置データと同一の識別情報を含む位置データのうち、当該第1の位置データの直前の位置データである第2の位置データの位置取得時刻情報、及び当該第1の位置データの直後の位置データである第3の位置データの位置取得時刻情報を取得する前後位置データ取得手段を更に備え、
前記特徴量算出手段は、前記第1の位置データの位置取得時刻、前記第2の位置データの位置取得時刻、および前記第3の位置データの位置取得時刻のうち2つ以上に基づいて、前記第1の位置データについての特徴量を算出することを特徴とする請求項1~17のいずれか一項に記載の端末数推計装置。 - 端末数推計装置で実行される端末数推計方法であって、
携帯端末を識別する識別情報、前記携帯端末の位置に関する位置情報、及び前記位置情報が取得された位置取得時刻情報を含む位置データを取得する位置データ取得ステップと、
前記位置取得時刻情報が滞在を観測すべき観測対象期間内であり、且つ前記位置情報が観測すべき観測エリア内である位置データを、観測対象位置データとして取得する観測対象取得ステップと、
前記観測対象取得ステップで取得された前記観測対象位置データに含まれる前記位置取得時刻情報に基づいて、当該観測対象位置データについての特徴量を算出する特徴量算出ステップと、
携帯端末の識別情報毎に、前記特徴量算出ステップで算出された特徴量の合計値を、滞在時間を表す期待滞在時間として算出する期待滞在時間算出ステップと、
前記期待滞在時間に基づいて、台数の推計対象となる携帯端末を選択する推計対象端末選択ステップと、
前記推計対象端末選択ステップによって選択された携帯端末の台数の推計を行う端末数推計ステップと、
を有することを特徴とする端末数推計方法。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020137008675A KR20130052014A (ko) | 2011-01-31 | 2012-01-30 | 단말기 수 추계 장치 및 단말기 수 추계 방법 |
US13/878,316 US20130203377A1 (en) | 2011-01-31 | 2012-01-30 | Terminal quantity estimation device and terminal quantity estimation method |
EP12742407.5A EP2672737A1 (en) | 2011-01-31 | 2012-01-30 | Terminal quantity estimation device and terminal quantity estimation method |
CN2012800051303A CN103299659A (zh) | 2011-01-31 | 2012-01-30 | 终端数量推算装置和终端数量推算方法 |
JP2012555871A JP5553913B2 (ja) | 2011-01-31 | 2012-01-30 | 端末数推計装置及び端末数推計方法 |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2011-018867 | 2011-01-31 | ||
JP2011018867 | 2011-01-31 | ||
JP2011-127492 | 2011-06-07 | ||
JP2011127492 | 2011-06-07 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2012105516A1 true WO2012105516A1 (ja) | 2012-08-09 |
Family
ID=46602730
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2012/052030 WO2012105516A1 (ja) | 2011-01-31 | 2012-01-30 | 端末数推計装置及び端末数推計方法 |
Country Status (6)
Country | Link |
---|---|
US (1) | US20130203377A1 (ja) |
EP (1) | EP2672737A1 (ja) |
JP (1) | JP5553913B2 (ja) |
KR (1) | KR20130052014A (ja) |
CN (1) | CN103299659A (ja) |
WO (1) | WO2012105516A1 (ja) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014048935A (ja) * | 2012-08-31 | 2014-03-17 | Zenrin Datacom Co Ltd | 情報処理装置、情報処理方法及びプログラム |
CN104103271A (zh) * | 2013-04-05 | 2014-10-15 | 国际商业机器公司 | 用于适配语音识别声学模型的方法和系统 |
WO2015018346A1 (zh) * | 2013-08-07 | 2015-02-12 | Wang Fangqi | 一种信息处理方法及装置 |
JP2015055930A (ja) * | 2013-09-10 | 2015-03-23 | 株式会社ゼンリンデータコム | 推定値算出装置、推定値算出方法及びプログラム |
CN104486773A (zh) * | 2014-12-05 | 2015-04-01 | 中国联合网络通信集团有限公司 | 一种预测基站下终端数的方法及装置 |
JP2015191542A (ja) * | 2014-03-28 | 2015-11-02 | 株式会社ゼンリンデータコム | 情報処理装置、情報処理方法及びプログラム |
JP2015201802A (ja) * | 2014-04-09 | 2015-11-12 | 富士通株式会社 | 基地局、及び基地局制御方法 |
JP2016167149A (ja) * | 2015-03-09 | 2016-09-15 | Kddi株式会社 | 商圏に応じて店舗の期待成約人数を推定するプログラム、装置及び方法 |
JP2017175625A (ja) * | 2017-03-30 | 2017-09-28 | 株式会社ゼンリンデータコム | 推定値算出装置、推定値算出方法及びプログラム |
JP2021005167A (ja) * | 2019-06-25 | 2021-01-14 | Kddi株式会社 | 時間帯毎に各エリアに滞在するユーザ数を推定するプログラム、装置及び方法 |
JP7549483B2 (ja) | 2020-08-21 | 2024-09-11 | 株式会社日立製作所 | ソーシャルキャピタルインデックス計測システム及びソーシャルキャピタルインデックス計測方法 |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9179185B2 (en) * | 2013-03-14 | 2015-11-03 | The Nielsen Company (Us), Llc | Methods and apparatus to determine a number of people in an area |
US9781180B2 (en) * | 2013-12-20 | 2017-10-03 | Verizon Patent And Licensing Inc. | Redistributing broadcasted content |
CN104950716B (zh) * | 2015-06-12 | 2017-11-14 | 广东欧珀移动通信有限公司 | 一种设备控制方法及装置 |
DE102016110331B3 (de) * | 2016-06-03 | 2017-06-22 | CooDriver GmbH | Verfahren und System zum Ermitteln von Risikobereichen im Straßenverkehr |
CN109388684B (zh) * | 2018-10-23 | 2020-07-07 | 百度在线网络技术(北京)有限公司 | 用于生成信息的方法和装置 |
US11012163B1 (en) * | 2019-03-08 | 2021-05-18 | The Governors Of The University Of Alberta | Apparatus and methods for fast and accurate near-field measurement |
WO2021033316A1 (ja) * | 2019-08-22 | 2021-02-25 | 日本電信電話株式会社 | 人数推定装置、人数推定方法、及び人数推定プログラム |
CN110969361B (zh) * | 2019-12-06 | 2024-05-14 | 深圳前海微众银行股份有限公司 | 空置率评估方法、装置、设备及计算机可读存储介质 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003044969A (ja) | 2001-08-01 | 2003-02-14 | Marubeni Energy Corp | 緊急対策用ネットワークシステム |
JP2003091629A (ja) * | 2001-09-18 | 2003-03-28 | Matsushita Electric Ind Co Ltd | マーケティング情報作成装置及びマーケティング情報作成方法 |
JP2003122877A (ja) * | 2001-10-09 | 2003-04-25 | Oki Electric Ind Co Ltd | 地域内人口算出システム |
JP2010221456A (ja) | 2009-03-23 | 2010-10-07 | Konica Minolta Business Technologies Inc | 画像形成装置 |
WO2010113699A1 (ja) * | 2009-04-01 | 2010-10-07 | 株式会社エヌ・ティ・ティ・ドコモ | 移動機、通信システムおよび通信方法 |
WO2010116900A1 (ja) * | 2009-04-06 | 2010-10-14 | 株式会社エヌ・ティ・ティ・ドコモ | 通信システム、情報分析装置、及び情報分析方法 |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1316897A4 (en) * | 2000-08-07 | 2007-03-28 | Sharp Kk | SERVER DEVICE FOR PROCESSING INFORMATION ACCORDING TO END DEVICE POSITION INFORMATION |
JP2002342557A (ja) * | 2001-05-14 | 2002-11-29 | Nippon Telegr & Teleph Corp <Ntt> | 携帯端末の位置情報に基づく人口分布統計処理システム |
KR100608776B1 (ko) * | 2004-04-27 | 2006-08-08 | 엘지전자 주식회사 | 무선통신네트워크에서의 위치등록 영역 설정 방법 |
JP4389987B2 (ja) * | 2007-09-12 | 2009-12-24 | ソニー株式会社 | 情報配信装置、情報受信装置、情報配信方法、情報受信方法及び情報配信システム |
-
2012
- 2012-01-30 JP JP2012555871A patent/JP5553913B2/ja active Active
- 2012-01-30 US US13/878,316 patent/US20130203377A1/en not_active Abandoned
- 2012-01-30 EP EP12742407.5A patent/EP2672737A1/en not_active Withdrawn
- 2012-01-30 KR KR1020137008675A patent/KR20130052014A/ko active IP Right Grant
- 2012-01-30 WO PCT/JP2012/052030 patent/WO2012105516A1/ja active Application Filing
- 2012-01-30 CN CN2012800051303A patent/CN103299659A/zh active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003044969A (ja) | 2001-08-01 | 2003-02-14 | Marubeni Energy Corp | 緊急対策用ネットワークシステム |
JP2003091629A (ja) * | 2001-09-18 | 2003-03-28 | Matsushita Electric Ind Co Ltd | マーケティング情報作成装置及びマーケティング情報作成方法 |
JP2003122877A (ja) * | 2001-10-09 | 2003-04-25 | Oki Electric Ind Co Ltd | 地域内人口算出システム |
JP2010221456A (ja) | 2009-03-23 | 2010-10-07 | Konica Minolta Business Technologies Inc | 画像形成装置 |
WO2010113699A1 (ja) * | 2009-04-01 | 2010-10-07 | 株式会社エヌ・ティ・ティ・ドコモ | 移動機、通信システムおよび通信方法 |
WO2010116900A1 (ja) * | 2009-04-06 | 2010-10-14 | 株式会社エヌ・ティ・ティ・ドコモ | 通信システム、情報分析装置、及び情報分析方法 |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014048935A (ja) * | 2012-08-31 | 2014-03-17 | Zenrin Datacom Co Ltd | 情報処理装置、情報処理方法及びプログラム |
CN104103271A (zh) * | 2013-04-05 | 2014-10-15 | 国际商业机器公司 | 用于适配语音识别声学模型的方法和系统 |
CN104103271B (zh) * | 2013-04-05 | 2017-05-10 | 国际商业机器公司 | 用于适配语音识别声学模型的方法和系统 |
WO2015018346A1 (zh) * | 2013-08-07 | 2015-02-12 | Wang Fangqi | 一种信息处理方法及装置 |
JP2015055930A (ja) * | 2013-09-10 | 2015-03-23 | 株式会社ゼンリンデータコム | 推定値算出装置、推定値算出方法及びプログラム |
JP2015191542A (ja) * | 2014-03-28 | 2015-11-02 | 株式会社ゼンリンデータコム | 情報処理装置、情報処理方法及びプログラム |
JP2015201802A (ja) * | 2014-04-09 | 2015-11-12 | 富士通株式会社 | 基地局、及び基地局制御方法 |
CN104486773A (zh) * | 2014-12-05 | 2015-04-01 | 中国联合网络通信集团有限公司 | 一种预测基站下终端数的方法及装置 |
CN104486773B (zh) * | 2014-12-05 | 2018-09-11 | 中国联合网络通信集团有限公司 | 一种预测基站下终端数的方法及装置 |
JP2016167149A (ja) * | 2015-03-09 | 2016-09-15 | Kddi株式会社 | 商圏に応じて店舗の期待成約人数を推定するプログラム、装置及び方法 |
JP2017175625A (ja) * | 2017-03-30 | 2017-09-28 | 株式会社ゼンリンデータコム | 推定値算出装置、推定値算出方法及びプログラム |
JP2021005167A (ja) * | 2019-06-25 | 2021-01-14 | Kddi株式会社 | 時間帯毎に各エリアに滞在するユーザ数を推定するプログラム、装置及び方法 |
JP7229863B2 (ja) | 2019-06-25 | 2023-02-28 | Kddi株式会社 | 時間帯毎に各エリアに滞在するユーザ数を推定するプログラム、装置及び方法 |
JP7549483B2 (ja) | 2020-08-21 | 2024-09-11 | 株式会社日立製作所 | ソーシャルキャピタルインデックス計測システム及びソーシャルキャピタルインデックス計測方法 |
Also Published As
Publication number | Publication date |
---|---|
JP5553913B2 (ja) | 2014-07-23 |
CN103299659A (zh) | 2013-09-11 |
KR20130052014A (ko) | 2013-05-21 |
US20130203377A1 (en) | 2013-08-08 |
JPWO2012105516A1 (ja) | 2014-07-03 |
EP2672737A1 (en) | 2013-12-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5553913B2 (ja) | 端末数推計装置及び端末数推計方法 | |
CN109982366B (zh) | 基于大数据的目标价值区域分析方法、装置、设备及介质 | |
Xiao et al. | A secure mobile crowdsensing game with deep reinforcement learning | |
US8942724B2 (en) | Number of terminal estimation device and number of terminal estimation method | |
JP5442751B2 (ja) | 位置情報分析装置及び位置情報分析方法 | |
EP3241368B1 (en) | Method and system for a real-time counting of a number of participants at a public happening | |
Calabrese et al. | Estimating Origin-Destination flows using opportunistically collected mobile phone location data from one million users in Boston Metropolitan Area | |
EP3241366B1 (en) | Method and system for estimating a number of persons in a crowd | |
JP5653647B2 (ja) | 移動体ユーザ装置の存在の予測 | |
US20130176433A1 (en) | Unique-terminal-count estimation device and unique-terminal-count estimation method | |
RU2527754C2 (ru) | Система генерирования статистической информации и способ генерирования статистической информации | |
CN109195219B (zh) | 服务器确定移动终端位置的方法 | |
JP2013153286A (ja) | 情報処理装置およびクラスタ生成方法 | |
EP2875623A1 (en) | Method and system for traffic estimation | |
Eagle | Behavioral inference across cultures: Using telephones as a cultural lens | |
Huang et al. | Interest-driven outdoor advertising display location selection using mobile phone data | |
US20120135749A1 (en) | Position information analysis device and position information analysis method | |
JP2012054921A (ja) | 移動機分布算出システム及び移動機分布算出方法 | |
CN111598188B (zh) | 目标门店位置的识别的方法和装置、存储介质和电子设备 | |
JP5797120B2 (ja) | 情報分析装置および人口分布算出方法 | |
JP5543619B2 (ja) | 端末数推計装置および端末数推計方法 | |
WO2014187476A1 (en) | Method and system for predicting mobility demand of users | |
Xie et al. | Pattern mining, semantic label identification and movement prediction using mobile phone data | |
JP2013138417A (ja) | 情報分析装置および情報分析方法 | |
CN116723234A (zh) | 推送处理方法、相关装置和介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 12742407 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2012742407 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 20137008675 Country of ref document: KR Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13878316 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2012555871 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |