JP2018077608A - Base estimation device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To accurately estimate purposes of staying at multiple bases where a user stays.SOLUTION: A base estimation device 100 comprises: a base location estimation unit 102 that estimates locations of multiple bases of a user on the basis of movement history data; a base classification unit 106 that aggregates characteristic amounts showing time trends when the user is located in the bases on the basis of the movement history data and the locations of the multiple bases and groups the multiple bases on the basis of similarity of the characteristic amounts of the multiple bases; and a base group type estimation unit 108 that estimates types of the bases on the basis of the movement history data or the characteristic amount, for each of the grouped multiple bases.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a site estimation apparatus that estimates the type of a user's site.

  As described in Patent Document 1 below, based on the stay position data indicating the stay position of the user, the movement graph data indicating the movement direction and the number of movements between the stay clusters is created, and each stay cluster is based on the movement graph data. An estimation device has been devised for estimating the purpose of staying. In addition, as shown in Patent Document 2 below, storing residence point information including a residence start date and time and a residence end date and time at the residence point of the user, and based on that, the residence point with the most residence days is set as the home residence point, A positioning device that extracts a stay point with the second most stay days as a workplace stay point is being studied.

JP2015-82137A Republished patent WO2011 / 102541

  However, in the above-described conventional apparatus, when a plurality of bases for the same staying purpose are generated for the same user within a specific period due to moving, single assignment, or decentralization of the workplace, a plurality of staying times of the user There was a tendency that the purpose of staying could not be accurately estimated by dispersing the bases.

  Therefore, the present invention has been made in view of such a problem, and an object of the present invention is to provide a site estimation device capable of accurately estimating the purpose of staying at a plurality of sites where a user stays.

  In order to solve the above-described problem, a site estimation apparatus according to one aspect of the present invention estimates the positions of a plurality of sites that are locations where a user stays based on movement history data representing a user's location at each time. Based on the base location estimation unit, the movement history data, and the locations of multiple locations, the values that indicate the temporal trends that the user is located at each of the multiple locations are aggregated, and the aggregated values for multiple locations Based on the similarity, the site classification unit that groups multiple sites, and the site type estimation unit that estimates the type of sites based on movement history data or aggregated values for each grouped multiple sites And comprising.

  According to the above aspect, after a plurality of bases where the user stays are estimated, values indicating a temporal tendency of the user being located at the plurality of bases are aggregated, and based on the similarity of the aggregated results Multiple locations are grouped. Further, the type of the site is estimated for each grouped site. Thereby, even if the same bases for staying purposes are dispersed in a plurality, it is possible to accurately estimate the types of the plurality of bases of the user.

  According to the present invention, it is possible to accurately estimate the staying purpose of a plurality of bases where a user stays.

It is a block diagram which shows the structure of the base estimation apparatus 100 concerning suitable one Embodiment of this invention. It is a figure which shows an example of a data structure of the movement history data memorize | stored in the position data storage part 101 of FIG. It is a figure which shows an example of a data structure of the position data of the base memorize | stored in the base position memory | storage part 103 of FIG. It is a figure which shows the image of the matrix data for every some base produced | generated by the base feature-value production | generation part 104 of FIG. It is a figure which shows the image of the feature-value for every some base produced | generated based on matrix data by the base feature-value production | generation part 104 of FIG. It is a figure which shows the data structure of the feature-value memorize | stored in the base feature-value memory | storage part 105 of FIG. It is a figure which shows the data structure of the base information memorize | stored in the base group memory | storage part 107 of FIG. It is a figure which shows the data structure of the classification information of the group memorize | stored in the base group classification memory | storage part 109 of FIG. It is a figure which shows the data structure of the information of the base classification memorize | stored in the base memory | storage part 111 of FIG. It is a flowchart which shows the operation | movement procedure of the estimation process of the base classification by the base estimation apparatus 100 of this embodiment. It is a figure which shows an example of the hardware constitutions of the base estimation apparatus 100 which concerns on this embodiment. It is a block diagram which shows the structure of 100 A of base estimation apparatuses concerning another side surface of this invention. It is a figure which shows the data structure of the group information memorize | stored in the user group classification memory | storage part 113 of FIG. It is a flowchart which shows the operation | movement procedure of the estimation process of a base classification by 100A of base estimation apparatuses of FIG.

  Embodiments of the present invention will be described with reference to the accompanying drawings. Where possible, the same parts are denoted by the same reference numerals, and redundant description is omitted.

  FIG. 1 is a block diagram showing a configuration of a site estimation apparatus 100 according to a preferred embodiment of the present invention. As shown in FIG. 1, the site estimation device 100 estimates information on the positions of a plurality of sites where the user stays based on the movement history data indicating the location history of the user at each time. System. The site estimation apparatus 100 is configured to be able to transmit / receive data to / from an external apparatus 200 such as an external server apparatus or terminal apparatus via a communication network such as a mobile communication network.

  As shown in FIG. 1, the site estimation apparatus 100 includes, as functional components, a location data storage unit 101, a site location estimation unit 102, a site location storage unit 103, a site feature quantity generation unit (site classification unit) 104, A site feature amount storage unit 105, a site classification unit 106, a site group storage unit 107, a site group type estimation unit (site type estimation unit) 108, a site group type storage unit 109, a combining unit 110, and a site storage unit 111 are included. It is configured. Hereinafter, each component will be described.

  The position data storage unit 101 is a functional unit that stores movement history data related to a plurality of users. The movement history data is acquired by the external device 200 and stored in the position data storage unit 101. The movement history data acquired by the external device 200 may be actively acquired from the external device 200 by the site estimation device 100 and stored in the position data storage unit 101, or may be passively acquired from the external device 200. It may be stored in the position data storage unit 101. There are various methods for acquiring movement history data by the external device 200. For example, there is a method of acquiring movement history data using a location registration signal transmitted from a terminal device such as a mobile phone terminal possessed by a user to a base station constituting a mobile communication network. In this method, for example, the position of the terminal apparatus is estimated using the position of the antenna of the base station and the delay time of communication between the terminal apparatus and the base station, and the estimation of the position is continuous in time. Thus, movement history data is acquired.

  FIG. 2 shows an example of the data configuration of movement history data stored in the position data storage unit 101. As shown in FIG. 2, in the movement history data, a “terminal identifier” that identifies the terminal device of the user, a “time” that indicates the time at which the position is estimated, and a “longitude,” that indicates the estimated position of the user. "Latitude" is associated with the position of the user for each of a plurality of times. Specifically, for the user identified by “terminal identifier: U1”, a plurality of times “2016/12/01 10:00”, “2016/12/01 12:00”, and “2016/12/01 As the position corresponding to “14:00”, “longitude: 140.0, latitude: 35.0”, “longitude: 140.0, latitude: 35.0”, and “longitude: 140.0, latitude: 35.1” are associated. Further, the position data storage unit 101 can store movement history data related to a plurality of users.

  Returning to FIG. 1, the base position estimation unit 102 is a functional unit that reads movement history data from the position data storage unit 101 and estimates the positions of a plurality of bases where the user stays based on the movement history data. . The base position estimation unit 102 estimates the positions of a plurality of bases for each of a plurality of users. There are various methods for estimating the position of the base by the base position estimation unit 102. For example, the base position estimation unit 102 totals the number of visits of a user within a predetermined period for each of a plurality of areas set in advance by dividing into mesh shapes, and corresponds to an area where the total number of visits is a predetermined threshold or more. The position is estimated as the position of the base. Specifically, the base position estimation unit 102 counts the number of times the user has entered the area from the outside of the area based on the movement history data, and sets the number as the number of visits corresponding to the area. The base position estimation unit 102 stores the base position information for each user estimated within a predetermined period in the base position storage unit 103.

  In addition to the above estimation method, the base position estimation unit 102 may employ the following method. That is, if it can be determined that the same user is located in the same area at the continuous time based on the movement history data, it is estimated that the user stayed in the area for the continuous time. For example, if you are located in the same area at two consecutive times of “10:00” and “12:00”, you will stay in that area for two hours across those two times. Estimated. And the base position estimation part 102 estimates the area where the estimated residence time is more than a threshold value as a base of an applicable user. According to such an estimation method, it is possible to prevent a place that does not correspond to the user's base such as a station from being erroneously estimated as the base due to the large number of visits by the user. Further, as described in Japanese Patent Application Laid-Open No. 2015-82137, the base position estimation unit 102 uses a clustering technique by machine learning such as k-Means method or GMM (Gaussian mixture model) as a user. An area where the positions of the areas are concentrated may be calculated, and a representative point of the area may be estimated as the position of the base.

  FIG. 3 shows an example of the data structure of the location data of the location stored in the location location storage unit 103. As shown in FIG. 3, in the location data of the base, a “terminal identifier” that identifies the terminal device of the user is associated with a “position identifier” that identifies the location of the estimated base. The location of the base is shown. Specifically, “53391234”, “53392345”, and “53393456” are included as position identifiers for identifying the positions of a plurality of locations of the user identified by “terminal identifier: U1”. Further, the base position storage unit 103 can store base position data regarding a plurality of users.

  Returning to FIG. 1, the site feature value generation unit 104 reads the movement history data from the position data storage unit 101 and also reads the location data of the site from the site position storage unit 103, and reads the read movement history data and the location data of the site. Based on this, the vector values (feature quantities) indicating the temporal distribution tendency where each user is located at each of the plurality of bases are totaled. That is, the site feature value generation unit 104 extracts “time” information within a predetermined period (for example, for a certain month) included in the movement history data for each site indicated in the location data of the site for one user. Then, by summing up the extracted “time” information, a time distribution in which the user is located in the vicinity of the base is generated as matrix data. The matrix data to be generated shows a frequency distribution in a 24-hour period (for example, a period from midnight to 12:00 pm) divided by “1 hour” in the direction between columns, and the frequency distribution in the direction between rows. The data is repeatedly arranged in units of “1 day”. Therefore, this matrix data shows a temporal distribution tendency for each time zone and each day. Further, the site feature value generation unit 104 generates day vector data by aggregating the generated matrix data in the direction between the columns. The day vector data is data in which numerical values indicating a temporal distribution tendency for each day within a predetermined period are arranged. In addition, the site feature value generation unit 104 generates time vector data by aggregating the generated matrix data in the direction between rows. This time vector data is data in which numerical values indicating a temporal distribution tendency for each time zone within a predetermined period (for example, a time zone dividing a period from midnight to 12:00 pm) are arranged. Then, the site feature value generation unit 104 generates day vector data and time vector data as feature values for each of a plurality of sites of all users. The site feature value generation unit 104 stores the generated feature value in the site feature value storage unit 105.

  Here, the predetermined period for aggregation of the day vector data and the time vector data is set to a period of one month from the viewpoint that the calculation load is not so high and the type of the base can be estimated more accurately. Is preferred. The predetermined period may be set to a period of one week from the viewpoint that the calculation load can be further reduced if the estimation accuracy of the base type is acceptable. In addition, the site feature value generation unit 104 may generate the day vector data and the time vector data by normalization. For example, normalization may be performed so that the sum of the squares of the components of the vector becomes a predetermined value (for example, “1”), or the sum of the sum of the components of the vector is a predetermined value (for example, “1”). You may normalize so that.

FIG. 4 shows an image of matrix data for each of a plurality of bases generated by the base feature amount generation unit 104. FIG. 5 shows a plurality of base points generated by the base feature amount generation unit 104 based on the matrix data. The image of each feature amount is shown. FIGS. 4A to 4C show matrix data images M ₀₁ , M ₀₂ , and M ₀₃ generated for each of the three sites for a certain user, and FIGS. 5A to 5C. _Includes combinations of images of the day vector data and the time vector data (V ₀₁ , V ₁₁ ), (V ₀₂ , V ₁₂ ), which are generated based on the matrix data of FIGS. (V ₀₃ , V ₁₃ ) is shown. In the matrix data images M ₀₁ , M ₀₂ , and M ₀₃ , the horizontal direction indicates a direction D ₁ between columns, and the vertical direction indicates a direction D ₂ between rows. Also, in each matrix data, day vector data, and time vector data image, the white portion indicates a portion having a value of zero, and the shaded portion is a portion having a value that is greater than or equal to zero but relatively small A black-out portion indicates a portion having a relatively large value.

  FIG. 6 shows an example of the data structure of the feature values generated by the site feature value generation unit 104 and stored in the site feature value storage unit 105. As illustrated in FIG. 6, the site feature quantity storage unit 105 includes a “terminal identifier” that identifies the terminal device of the user, a “position identifier” that identifies the location of the site, and a “feature quantity” that indicates the type of the feature quantity. The “type” and the vector value (numerical string) as the feature quantity are stored in association with each other. For example, two types of feature quantities “time vector” and “day vector” are provided as feature quantities corresponding to each of a plurality of user bases “53391234” and “53392345” identified by “terminal identifier: U1”. It is remembered.

  It can be assumed that the feature quantity for each of the plurality of bases of the user generated in this way has the following properties. That is, a certain user tends to stay in the same time zone at a plurality of bases of the same type, but tends not to stay on the same day. Specifically, even if the home has been changed to two locations within a certain period of time due to moving, users who work during the day are more likely to stay in both homes at night. It is assumed that they rarely stay in both homes on the same day. Also, as another case, a user who has a home and a single residence for a certain period of time due to a single appointment, and a user who works in the daytime has a strong tendency to stay at both the home and the residence at night. It can be assumed that there is almost no residence at the same day in both home and dormitory. From such a tendency, while the same user has the same distribution of time vector data of feature quantities related to the same type of base, the distribution of the day vector data of feature quantities related to the same type of base differs. It will be. As a result, in the same user, the inner product value of the time vector data of the two bases of the same type is relatively large, while the inner product value of the day vector data of the two bases is relatively small.

Returning to FIG. 1, the site classification unit 106 reads the feature value data stored in the site feature value storage unit 105, and for each user, based on the similarity of the feature values between the sites, Group. Specifically, the site classification unit 106 classifies a plurality of sites for one user into two groups, a group whose type is “home” and a group whose type is “work”. First, the base classifying unit 106 estimates that the type of the base is “home” because it is difficult to assume that the user does not have a home when there is only one base associated with the user. The user is excluded from the base type estimation targets described later. On the other hand, when there are two or more bases associated with the user, the base classifying unit 106 classifies the plurality of bases into two groups as follows. First, the numerical value of each component of the time vector data at each base is replaced with a value obtained by subtracting the numerical value from 1. By doing so, the time vector data also has the property that the inner product value between the same type of bases becomes relatively small as in the case of the day vector data. Next, the base classifying unit 106 calculates an inner product value between the day vector data of two bases selected from a plurality of bases, and an inner product value between the time vector data of the two bases. Then, the site classification unit 106 calculates a scalar quantity that represents the similarity between the two sites by calculating the product of the two inner product values between the two sites. The base classifying unit 106 calculates the scalar quantity for two bases in all combinations that can be selected from a plurality of bases, and creates dissimilarity table data in which the scalar quantities between the two bases are arranged. To do. For example, when there are four bases for a certain user, the scalar quantity is calculated corresponding to ₄ C ₂ = 6 combinations of bases. Here, the site classification unit 106 may calculate the scalar quantity by taking the sum of two inner product values, or by selecting the larger one of the two inner product values.

  Further, the site classification unit 106 performs clustering based on the created dissimilarity table data and classifies a plurality of sites into two groups. The base classifying unit 106 clusters a plurality of bases by judging the similarity of the feature quantity based on the scalar quantity in the dissimilarity table data. Specifically, the Ward method is adopted as a clustering method. The Ward method is a clustering method in which a tree diagram is created using a difference table as an input, and items having a small difference in the tree diagram are associated with similar items. The site classification unit 106 classifies a plurality of sites into two groups for each user based on the dissimilarity table data using this Ward method. The site classification unit 106 may use other methods such as non-hierarchical clustering as the clustering method in addition to the Ward method. The base classifying unit 106 groups the plurality of bases for all users with respect to the feature quantity data of all users stored in the base feature quantity storage unit 105. Then, the site classification unit 106 stores the grouped site information in the site group storage unit 107.

  FIG. 7 shows an example of the data configuration of the base information stored in the base group storage unit 107. As shown in FIG. 7, the base group storage unit 107 includes a “terminal identifier” that identifies the terminal device of the user, a “position identifier” that identifies the location of the base, and a “group identifier” that indicates the group into which the base is classified. “Group name” is stored in association with each other. For example, the name “group 1” of the group into which the base is classified is stored in association with the base “53391234” of the user identified by “terminal identifier: U1”.

  Returning to FIG. 1 again, the site group type estimation unit 108 is based on the feature quantity data stored in the site feature quantity storage unit 105 for each of the two groups classified by the site classification unit 106 for each user. Estimate the types of bases included in each of the two groups. The type of base to be estimated is either “home” or “workplace”, and the concept of “workplace” type includes “destination” that can be included in the base when the user is a student or a student. And Here, it is assumed that the number of times that the user visits the home is greater than the number of times that the user visits the workplace in the predetermined period, which is the feature amount aggregation period. For example, in the case of a user working on weekdays, it is generally assumed that 31 days stays at home and 22 days at work during one month, and the number of days staying at home is larger. As another example, in the case of a weekday working user who moved in the middle of a month, it is assumed that he / she stays at home before moving, stays at home after moving for 16 days, and stays at work for 22 days. There are more days staying at home. Using this, the site group type estimation unit 108 refers to the day vector data that is the feature quantity stored in the site feature quantity storage unit 105 and totals the stay days of the bases included in each of the two groups. To do. Then, the base group type estimation unit 108 compares the stay days of the two groups, estimates the base type of the group with the longer stay days as “home”, and sets the base type of the group with the less stay days as “ Estimated as “workplace”. At this time, the site group type estimation unit 108 may count the staying days for each group using the matrix data generated by the site feature value generation unit 104, or the movement history stored in the position data storage unit 101. The data may be used directly to count the stay days for each group. The base group type estimation unit 108 stores information on two types of groups estimated for each user in the base group type storage unit 109.

  FIG. 8 shows an example of the data configuration of the group type information stored in the base group type storage unit 109. As shown in FIG. 8, the base group type storage unit 109 includes a “terminal identifier” that identifies a user terminal device, a “group name” that identifies a group, and a type of base included in the group “ “Location type” is stored in association with each other. For example, the name “home” of the base type of the group is stored in association with the group “group 1” of the user identified by “terminal identifier: U1”.

  Returning to FIG. 1, the combining unit 110 combines all the base information stored in the base group storage unit 107 and the group type information stored in the base group type storage unit 109, thereby The base type information related to the base is generated, and the base type information is stored in the base storage unit 111. The base type information stored in the base storage unit 111 can be referred to as appropriate from an external device such as a terminal device.

  FIG. 9 shows an example of the data configuration of the base type information stored in the base storage unit 111. As shown in FIG. 9, the base storage unit 111 includes a “terminal identifier” that identifies the terminal device of the user, a “position identifier” that identifies the location of the base, and a “base type” that indicates the type of the base. Are stored in association with each other. For example, information “home” of the type of the base is stored in association with the base “53391234” of the user identified by “terminal identifier: U1”.

  Next, processing of the site estimation apparatus 100 having the above-described configuration will be described. FIG. 10 is a flowchart illustrating an operation procedure of the base type estimation process performed by the base location estimation apparatus 100.

  First, when the base type estimation process is started at a predetermined timing, the base position estimation unit 102 estimates the positions of a plurality of bases of the user (step S101; base position estimation process). Next, the site feature value generation unit 104 generates a feature value indicating a temporal distribution tendency in which each user is located at each of the plurality of sites (step S102; site feature value generation process). Thereafter, the base classification unit 106 classifies a plurality of bases for each user (step S103; base classification processing).

  Furthermore, the base group type estimation unit 108 estimates the type of base group classified for each user (step S104; base group type estimation process). Finally, the combination unit 110 generates information on the type of each site regarding all the sites of each user (step S105; combining process).

  Below, the effect of the base estimation apparatus 100 of this embodiment is demonstrated. In the base estimation apparatus 100, after a plurality of bases where the user stays is estimated, values indicating the temporal tendency of the user being located at the bases are tabulated, and based on the similarity of the tabulation results Multiple locations are grouped. Further, the type of the site is estimated for each grouped site. Thereby, even if the same bases for staying purposes are dispersed in a plurality, it is possible to accurately estimate the types of the plurality of bases of the user.

  Moreover, in the said embodiment, the base feature-value production | generation part 104 totals the vector data which shows a time tendency for every time slot | zone and every day. By doing this, it is possible to correctly group the units by the bases having the same retention purpose. As a result, it is possible to estimate the types of a plurality of bases of the user more accurately.

  Furthermore, in the above-described embodiment, the site feature value generation unit 104 calculates vector data in which values aggregated for each period are arranged, and the site classification unit 106 calculates an inner product value of vector data between a plurality of sites. The similarity of vector data is determined based on the inner product value. By doing so, it is possible to correctly perform grouping by the unit of the base where the purpose of residence is the same by a simple calculation.

  In addition, the block diagram used in the description of the above embodiment shows functional unit blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Further, the means for realizing each functional block is not particularly limited. That is, each functional block may be realized by one device physically and / or logically coupled, and two or more devices physically and / or logically separated may be directly and / or indirectly. (For example, wired and / or wireless) and may be realized by these plural devices.

  For example, the site estimation apparatus 100 according to an embodiment of the present invention may function as a computer that performs processing of the site estimation apparatus 100 according to the present embodiment. FIG. 11 is a diagram illustrating an example of a hardware configuration of the site estimation apparatus 100 according to the present embodiment. The site estimation apparatus 100 described above may be physically configured as a computer apparatus including a processor 1001, a memory 1002, a storage 1003, a communication apparatus 1004, an input apparatus 1005, an output apparatus 1006, a bus 1007, and the like.

  Note that in the description in this specification, the term “apparatus” can be read as a circuit, a device, a unit, or the like. The hardware configuration of the site estimation device 100 may be configured to include one or a plurality of devices illustrated in the figure, or may be configured not to include some devices.

  Each function in the base location estimation apparatus 100 reads predetermined software (program) on hardware such as the processor 1001 and the memory 1002, so that the processor 1001 performs calculation, and communication by the communication apparatus 1004, memory 1002, and storage This is realized by controlling reading and / or writing of data in 1003.

  For example, the processor 1001 controls the entire computer by operating an operating system. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, a register, and the like. For example, the base position estimation unit 102, the base feature value generation unit 104, the base classification unit 106, the base group type estimation unit 108, the combining unit 110, and the like may be realized by the processor 1001.

  Further, the processor 1001 reads a program (program code), software module, and data from the storage 1003 and / or the communication device 1004 to the memory 1002, and executes various processes according to these. As the program, a program that causes a computer to execute at least a part of the operations described in the above embodiments is used. For example, the base position estimation unit 102 of the base estimation apparatus 100 may be realized by a control program stored in the memory 1002 and operated by the processor 1001, and may be realized similarly for other functional blocks. Although the above-described various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. Note that the program may be transmitted from a network via a telecommunication line.

  The memory 1002 is a computer-readable recording medium and includes, for example, at least one of ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), and the like. May be. The memory 1002 may be called a register, a cache, a main memory (main storage device), or the like. The memory 1002 can store a program (program code), a software module, and the like that can be executed to execute the base type estimation process according to the embodiment of the present invention.

  The storage 1003 is a computer-readable recording medium, such as an optical disc such as a CD-ROM (Compact Disc ROM), a hard disc drive, a flexible disc, a magneto-optical disc (eg, a compact disc, a digital versatile disc, a Blu-ray). (Registered trademark) disk, smart card, flash memory (for example, card, stick, key drive), floppy (registered trademark) disk, magnetic strip, and the like. The storage 1003 may be referred to as an auxiliary storage device. The storage medium described above may be, for example, a database, server, or other suitable medium including the memory 1002 and / or the storage 1003. For example, the location data storage unit 101, the site location storage unit 103, the site feature amount storage unit 105, the site group storage unit 107, the site group type storage unit 109, the site storage unit 111, and the like may be realized by the storage 1003.

  The communication device 1004 is hardware (transmission / reception device) for performing communication between computers via a wired and / or wireless network, and is also referred to as a network device, a network controller, a network card, a communication module, or the like.

  The input device 1005 is an input device that accepts input from the outside, and the output device 1006 is an output device that performs output to the outside. The input device 1005 and the output device 1006 may be realized by a touch panel display in which both are integrated.

  Each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured with a single bus or may be configured with different buses between apparatuses.

  The site estimation apparatus 100 includes hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), and a field programmable gate array (FPGA). A part or all of each functional block may be realized by the hardware. For example, the processor 1001 may be implemented by at least one of these hardware.

  Although the present embodiment has been described in detail above, it will be apparent to those skilled in the art that the present embodiment is not limited to the embodiment described in this specification. The present embodiment can be implemented as a modification and change without departing from the spirit and scope of the present invention defined by the description of the scope of claims. Therefore, the description of the present specification is for illustrative purposes and does not have any limiting meaning to the present embodiment.

  For example, in the above embodiment, the base position estimation unit 102 estimates the base position in units of a plurality of areas divided into mesh shapes. As another form, fitting to a normal distribution may be performed for the user's position distribution, and the representative point obtained as a result may be estimated as the position of the base.

  In addition, when the user position is observed in an adjacent area during a predetermined period (for example, the same time period), the base position estimation unit 102 regards that the position measurement error has occurred and observes it. The locations may be added together (eg, averaged) and estimated as the location of the base.

  In addition, the site feature quantity generation unit 104 generates day vector data obtained by tabulating matrix data in a period from midnight to 12 pm. In addition, when targeting users who work at night from 8 pm to 4 am, the site feature generation unit 104 performs a period from 4 am on the current day to 4 am on the next day. Day vector data obtained by tabulating the matrix data may be generated. As a result, in the day vector data, the frequency of the same working hours is prevented from being distributed and counted across multiple days, and the base type can be accurately estimated according to the user's lifestyle. Become.

  In addition, the site feature value generation unit 104 generates time vector data by counting and dividing one day by a time zone, but also reflects the total value of the time zones around (before and after) the corresponding time zone. Thus, the time vector data may be calculated. For example, a value obtained by multiplying a total value at 9 o'clock in vector data by a predetermined coefficient (for example, “0.6”), a value obtained by multiplying a total value at 8 o'clock by a predetermined coefficient (for example, “0.2”), and 10:00 A value obtained by adding a value obtained by multiplying the total value of the table by a predetermined coefficient (for example, “0.2”) may be used as the value of the 9 o'clock element of the time vector data.

  Further, as another aspect of the present invention, the configuration of the site estimation device 100A shown in FIG. 12 may be adopted. The difference of the configuration of the base estimation apparatus 100A shown in FIG. 12 from the above-described base estimation apparatus 100 is that the base estimation apparatus 100A includes, as constituent elements, a user classification unit 112, a user group type storage unit 113, and a user group type estimation. (User base type estimation unit) 114 is further provided. Location data storage unit 101, site location estimation unit 102, site location storage unit 103, site feature quantity generation unit 104, site feature quantity storage unit 105, site group storage unit 107, site group type estimation unit provided in site estimation apparatus 100A 108, the base group type storage unit 109, the combining unit 110, and the base storage unit 111 are configured in the same manner as the base estimation apparatus 100. Hereinafter, differences in configuration of the site estimation device 100A, which is another aspect of the present invention, from the site estimation device 100 will be described.

  The base classifying unit 106 of the base estimating apparatus 100A executes a base grouping function for users other than two bases, and the function is the same as the base classifying unit 106 of the base estimating apparatus 100A. In addition to the group type information read from the base group type storage unit 109, the combining unit 110 of the base point estimation apparatus 100A uses the base type information output from the user group type estimation unit 114 to determine each user's type. The base type information regarding all the bases is generated and stored in the base storage unit 111.

  The user classifying unit 112 is a functional unit that reads out the feature quantity of each site for the user having 2 sites from the site feature value storage unit 105 and groups the users based on the read feature value. That is, the user classifying unit 112 calculates the inner product value between the day vector data of the two bases and the inner product value between the time vector data of the two bases for the feature amount of each user. Then, the user classification unit 112 groups a plurality of users based on two inner product values related to each user. For example, the user classifying unit 112 uses a clustering technique based on machine learning such as GMM to identify a user with a group “A” having a large inner product value between the time vector data and a small inner product value between the day vector data and the time. Classification is made into a group “B” in which the inner product value of the vectors is small and the inner product value of the day vector data is large. This group “A” is estimated to be a group in which two bases are a combination of types (home, home), and group “B” is a group in which two bases are a combination of types (home, work). Will be estimated. The user classifying unit 112 stores information related to the group to which the grouped user belongs in the user group type storage unit 113.

  FIG. 13 shows an example of the data configuration of group information stored in the user group type storage unit 113. As shown in FIG. 13, in the user group type storage unit 113, a “terminal identifier” that identifies a user terminal device and a “user group name” that identifies a grouped group are stored in association with each other. Is done. For example, information indicating that the user identified by “terminal identifier: U3” is classified into the group “A” is stored.

  Returning to FIG. 12, the user group type estimation unit 114 reads the group information from the user group type storage unit 113, and sets the group “B” in the same manner as the base group type estimation unit 108 based on the group information. For the grouped users, the types of the two bases that the user has are estimated. Specifically, of the two bases, the type of the base with the longer staying days is estimated as “home”, and the base type with the fewer staying days is estimated as “workplace”. If the staying days become the same, the time base data is referred to, and the type of the base having a larger total value in the midnight time zone is estimated as “home”. Then, the user group type estimation unit 114 outputs information regarding the types of the two bases regarding all users having two bases to the combining unit 110.

  FIG. 14 is a flowchart illustrating an operation procedure of the base type estimation process performed by the base location estimation apparatus 100A.

  First, when the base type estimation process is started at a predetermined timing, the base position estimation process, the base feature value generation process, the base classification process, and the base group type estimation process are sequentially executed in the same manner as the base estimation apparatus 100. (Steps S201 to S204). After that, the user classifying unit 112 groups the users whose number of bases is 2 (step S205; user grouping process). Next, the user group type estimation unit 114 estimates the types of the two bases that the user has for the user grouped into the group “B” having the base of the type (home, work) (step S206). ; User group type estimation processing). Lastly, the combination unit 110 generates information on the types of bases related to all the bases of each user (step S207; combining process).

  According to the base estimation apparatus 100A of the above embodiment, a plurality of users are grouped on the basis of the feature amount indicating the temporal tendency aggregated for each of the plurality of users. Are assumed to be the same. Thereby, the type of two bases which a user has can be estimated more correctly by considering the time tendency of the whole user.

  The notification of information is not limited to the aspect / embodiment described in the present specification, and may be performed by other methods. For example, information notification includes physical layer signaling (for example, DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (for example, RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling), It may be implemented by broadcast information (MIB (Master Information Block), SIB (System Information Block))), other signals, or a combination thereof. The RRC signaling may be referred to as an RRC message, and may be, for example, an RRC connection setup message, an RRC connection reconfiguration message, or the like.

  Each aspect / embodiment described herein includes LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA. (Registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB (Ultra-WideBand), The present invention may be applied to a Bluetooth (registered trademark), a system using another appropriate system, and / or a next generation system extended based on the system.

  As long as there is no contradiction, the order of the processing procedures, sequences, flowcharts, and the like of each aspect / embodiment described in this specification may be changed. For example, the methods described herein present the elements of the various steps in an exemplary order and are not limited to the specific order presented.

  Information or the like can be output from the upper layer (or lower layer) to the lower layer (or upper layer). Input / output may be performed via a plurality of network nodes.

  Input / output information and the like may be stored in a specific location (for example, a memory) or may be managed by a management table. Input / output information and the like can be overwritten, updated, or additionally written. The output information or the like may be deleted. The input information or the like may be transmitted to another device.

  The determination may be performed by a value represented by 1 bit (0 or 1), may be performed by a true / false value (Boolean: true or false), or may be performed by comparing numerical values (for example, a predetermined value) Comparison with the value).

  Each aspect / embodiment described in this specification may be used independently, may be used in combination, or may be switched according to execution. In addition, notification of predetermined information (for example, notification of being “X”) is not limited to explicitly performed, but is performed implicitly (for example, notification of the predetermined information is not performed). Also good.

  Software, whether it is called software, firmware, middleware, microcode, hardware description language, or other names, instructions, instruction sets, codes, code segments, program codes, programs, subprograms, software modules , Applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc. should be interpreted broadly.

  Also, software, instructions, etc. may be transmitted / received via a transmission medium. For example, software may use websites, servers, or other devices using wired technology such as coaxial cable, fiber optic cable, twisted pair and digital subscriber line (DSL) and / or wireless technology such as infrared, wireless and microwave. When transmitted from a remote source, these wired and / or wireless technologies are included within the definition of transmission media.

  Information, signals, etc. described herein may be represented using any of a variety of different technologies. For example, data, commands, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description are voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any of these May be represented by a combination of

  Note that the terms described in this specification and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meaning.

  In addition, information, parameters, and the like described in this specification may be represented by absolute values, may be represented by relative values from a predetermined value, or may be represented by other corresponding information. . For example, the radio resource may be indicated by an index.

  The names used for the parameters described above are not limiting in any way.

  As used herein, the terms “determining” and “determining” may encompass a wide variety of actions. “Judgment”, “decision” can be, for example, calculating, computing, processing, deriving, investigating, looking up (eg, table, database or another (Searching in the data structure), and confirming (ascertaining) what has been confirmed may be considered as “determining” or “determining”. In addition, “determination” and “determination” include receiving (for example, receiving information), transmitting (for example, transmitting information), input (input), output (output), and access. (accessing) (e.g., accessing data in a memory) may be considered as "determined" or "determined". In addition, “determination” and “decision” means that “resolving”, “selecting”, “choosing”, “establishing”, and “comparing” are regarded as “determining” and “deciding”. May be included. In other words, “determination” and “determination” may include considering some operation as “determination” and “determination”.

  The terms “connected”, “coupled”, or any variation thereof, means any direct or indirect connection or coupling between two or more elements and It can include the presence of one or more intermediate elements between two “connected” or “coupled” elements. The coupling or connection between the elements may be physical, logical, or a combination thereof. As used herein, the two elements are radio frequency by using one or more wires, cables and / or printed electrical connections, and as some non-limiting and non-inclusive examples By using electromagnetic energy, such as electromagnetic energy having a wavelength in the region, microwave region, and light (both visible and invisible) region, it can be considered to be “connected” or “coupled” to each other.

  As used herein, the phrase “based on” does not mean “based only on,” unless expressly specified otherwise. In other words, the phrase “based on” means both “based only on” and “based at least on.”

  As long as “include”, “comprising”, and variations thereof, are used in the specification or claims, these terms are similar to the term “comprising”. It is intended to be comprehensive. Furthermore, the term “or” as used herein or in the claims is not intended to be an exclusive OR.

  In this specification, a plurality of devices are also included unless there is only one device that is clearly present in context or technically.

  Throughout this disclosure, the plural is included unless the context clearly indicates one.

DESCRIPTION OF SYMBOLS 100,100A ... Base estimation apparatus, 102 ... Base position estimation part, 104 ... Base feature-value production | generation part (base classification part, user classification part), 106 ... Base classification part, 108 ... Base group type estimation part (base type estimation part) , 112... User classification unit, 114... User group type estimation unit (user base type estimation unit).

Claims (4)

Based on the movement history data representing the position of the user for each time, a base position estimation unit that estimates the positions of a plurality of bases where the user stays,
Based on the movement history data and the positions of the plurality of bases, the user aggregates values indicating a temporal tendency located at each of the plurality of bases, and the values of the summed values for the plurality of bases A base classifying unit that groups the plurality of bases based on the similarity;
For each of the plurality of bases grouped, the base type estimation unit that estimates the base type based on the movement history data or the aggregated value;
A site estimation apparatus comprising: The site classification unit
Aggregate values indicating the above-mentioned seasonal trends for each time zone and each day,
The site estimation apparatus according to claim 1. The site classification unit
Calculating a vector in which the aggregated values are arranged for each period, calculating an inner product value of the vector between the plurality of bases, and determining a similarity of the value based on the inner product value;
The site estimation apparatus according to claim 1 or 2. Based on the movement history data for each of a plurality of users and the positions of the plurality of bases estimated for each of the plurality of users, the values indicating the temporal trends for the plurality of users are aggregated, A user classifying unit that groups the plurality of users on the basis of the values aggregated for each user;
For each of the grouped users, a user base type estimation unit that estimates the types of the bases based on the aggregated values;
Further comprising
The base estimation apparatus of any one of Claims 1-3.

Images