Information processing device, information processing method, program, and information processing system

Abstract

The aim is to improve the accuracy of geofences. [Solution] The information processing device 2 of this embodiment has a memory unit 22 that stores candidate visit place data in which candidate visit places that are candidates for the user to visit are associated with geofences, which are geographical areas surrounded by virtual borders that correspond to the candidate visit places; an acquisition unit 231 that acquires the places and stay positions where the user has stayed; an identification unit 232 that refers to the candidate visit place data to identify a target geofence, which is a geofence associated with the acquired place of stay; and an adjustment unit 233 that adjusts the center position and size of the target geofence based on the relationship between the area corresponding to the target geofence and the acquired stay position.

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, a program, and an information processing system. [Background technology]

[0002] Conventionally, there is known a method for identifying a spot corresponding to a geofence as a visited spot when entry into a geofence that is virtually set corresponding to one of multiple tourist spots is detected (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-110984 Summary of the Invention [Problem to be solved by the invention]

[0004] However, if the radius of the geofence is fixed, if the radius is too large, the user may be detected as having visited the destination even though the user merely passed through the vicinity of the destination, whereas if the radius is too small, the user may not be detected as having visited the destination.

[0005] Therefore, the present invention has been made in consideration of these points, and aims to improve the accuracy of geofences. [Means for solving the problem]

[0006] An information processing device according to a first aspect of the present invention includes a memory unit that stores candidate visit location data in which candidate visit locations that are candidates for a user to visit are associated with geofences, which are geographical areas surrounded by virtual boundaries corresponding to the candidate visit locations; an acquisition unit that acquires the stay locations and stay positions where the user has stayed; an identification unit that refers to the candidate visit location data to identify a target geofence, which is the geofence associated with the acquired stay location; and an adjustment unit that adjusts the center position and size of the target geofence based on the relationship between the area corresponding to the target geofence and the acquired stay position.

[0007] If the acquired stay location is outside the area corresponding to the target geofence, the adjustment unit may adjust the size of the target geofence so that the acquired stay location is included inside the target geofence.

[0008] When the acquired stay location is located within an area corresponding to the target geofence, the adjustment unit may adjust the size of the target geofence so that the acquired stay location is maintained within the target geofence.

[0009] The adjustment unit may adjust the center position and size of the target geofence based on a first value calculated based on target positions, which are multiple stay positions acquired by the acquisition unit in association with a target location for which the center position and size of the geofence are to be adjusted, and a second value calculated based on non-target positions, which are multiple stay positions acquired by the acquisition unit in association with locations other than the target location.

[0010] The adjustment unit may adjust the center position and size of the target geofence to a center position and size of the geofence such that the sum of the first value, which is a negative value calculated based on the target position included within the target geofence, and the second value, which is a positive value calculated based on the non-target position included within the target geofence, is minimized.

[0011] The adjustment unit may adjust the center position and size of the target geofence based on the output results output by the mathematical model by inputting the area corresponding to the target geofence and the acquired stay location into the mathematical model.

[0012] The acquisition unit may acquire a first location and a second location where the user is present, and if a value calculated based on a distance between the first location and the second location and a time difference between a first time when the first location is acquired and a second time when the second location is acquired satisfies a predetermined condition, determine that the first location and the second location are the user's staying locations.

[0013] The acquisition unit may acquire, as the place where the user is staying, a location that an information terminal used by the user has transmitted to the information processing device.

[0014] The storage unit may further store planned visit data that associates the user with planned visit locations that the user plans to visit and planned visit times to the planned visit locations, and the acquisition unit may refer to the planned visit data and acquire, as the user's staying location, the planned visit locations that are associated with the user using the information terminal that transmitted the staying location and the planned visit time that includes the time when the information terminal transmitted the staying location.

[0015] An information processing method according to a second aspect of the present invention includes the steps of: acquiring a place and a position where a user has stayed, executed by a computer; identifying a target geofence, which is a geofence associated with the acquired place of stay, by referring to candidate place to visit data in which candidate places to visit that are candidates for the user to visit and a geofence, which is a geographical area surrounded by a virtual boundary line corresponding to the candidate place to visit; and adjusting a center position and a size of the target geofence based on the relationship between the area corresponding to the target geofence and the acquired position of stay.

[0016] A program according to a third aspect of the present invention causes a processor of an information processing device to function as an acquisition unit that acquires the places and positions where a user has stayed, an identification unit that identifies a target geofence, which is a geofence associated with the acquired places of stay, by referring to candidate visit place data that associates candidate visit places that the user may visit with geofences, which are geographical areas surrounded by virtual boundaries corresponding to the candidate visit places, and an adjustment unit that adjusts the center position and size of the target geofence based on the relationship between the area corresponding to the target geofence and the acquired positions of stay.

[0017] An information processing system according to a fourth aspect of the present invention includes an information processing device and an information terminal used by a user that can communicate with the information processing device. The information processing device includes a memory unit that stores candidate visit locations data that associate candidate visit locations that the user may visit with geofences, which are geographical areas surrounded by virtual boundaries corresponding to the candidate visit locations; an acquisition unit that acquires the stay locations and stay positions where the user stayed; an identification unit that identifies a target geofence, which is the geofence associated with the acquired stay locations, by referring to the candidate visit location data; and an adjustment unit that adjusts the center position and size of the target geofence based on the relationship between the area corresponding to the target geofence and the acquired stay position. The information terminal includes a terminal communication unit that transmits the user's stay locations and stay positions to the information processing device. [Effects of the Invention]

[0018] According to the present invention, it is possible to improve the accuracy of a geofence. [Brief explanation of the drawings]

[0019] [Figure 1] FIG. 2 is a diagram for explaining an outline of the operation of the information processing system S. [Figure 2] 1 is a diagram illustrating an example of the configuration of an information terminal 1. FIG. [Figure 3] FIG. 2 is a diagram illustrating an example of the configuration of an information processing device 2. [Figure 4] FIG. 10 is a diagram illustrating an example of candidate visit place data. [Figure 5] FIG. 10 is a diagram illustrating an example of geofence data. [Figure 6] FIG. 2 is a diagram illustrating an example of visit schedule data. [Figure 7] FIG. 10 is a diagram illustrating an example of stay position data. [Figure 8] FIG. 10 is a diagram illustrating an example of stay location data. [Figure 9] FIG. 10 is a diagram illustrating an example of combination data. [Figure 10] FIG. 10 is a diagram illustrating an example of adjusting the radius of a target geofence. [Figure 11] 10 is a flowchart illustrating an example of a process flow for determining a center position. [Figure 12] 10 is a flowchart illustrating an example of a process flow for determining a radius. DETAILED DESCRIPTION OF THE INVENTION

[0020] [Outline of Information Processing System S] FIG. 1 is a diagram for explaining an overview of the operation of an information processing system S. The information processing system S is a system for adjusting the center position and size of a geofence. A geofence is a geographical area surrounded by a virtual boundary. The center position of a geofence is defined, for example, by coordinates (latitude and longitude) indicating the center of the geofence. The size of a geofence is defined, for example, by the radius or area of ​​the geofence. In the following, an example will be described in which the size of a geofence is defined by the radius.

[0021] When detecting entry into or exit from a geofence, fixed values ​​were previously used for the center position and radius of the geofence, which resulted in the following issues: First, there was the issue of false positives, where a time different from the actual start or end time of a stay was detected as the start or end time of the stay. This was because it was not possible to detect multiple stays within the geofence independently, or because the geofences for multiple stays overlapped, resulting in the detection of a destination different from the actual destination.

[0022] Second, if the radius is too large, there is a problem of false positives, where the system detects that the user stayed at the destination even though the user only passed through the destination. Third, if the radius is too small, there is a problem of non-detection, where the system cannot detect that the user stayed at the destination or that the user left the destination.

[0023] To solve these problems, the information processing system S is configured to dynamically adjust the center position and radius of the geofence based on the location where the user actually stayed. The information processing system S includes an information terminal 1 and an information processing device 2. The information terminal 1 is a portable information terminal used by a user U who is a person visiting a customer (e.g., a sales representative), and is, for example, a tablet or a smartphone. The information processing device 2 is a computer that adjusts the center position and radius of the geofence, and is, for example, a server. The information processing device 2 is capable of sending and receiving data to and from the information terminal 1.

[0024] Hereinafter, the basic operation of the information processing system S will be described with reference to FIG. 1. A plurality of information terminals 1 transmit the stay places and stay positions of a plurality of users U to the information processing device 2. The stay places are, for example, customer names, building names, etc. indicating the places where the users U stayed, and are input into the information terminal 1 when the users U complete their stay at the stay places. The stay positions are, for example, latitude and longitude indicating the positions where the users U actually stayed, and are identified by a GPS (Global Positioning System) or the like. In this way, the information processing device 2 acquires a plurality of combinations of the stay places and stay positions of the users U (see (1) in FIG. 1).

[0025] The information processing device 2 uses the acquired stay location to identify a target geofence, which is a geofence of a target location for which the center position and radius of the geofence are to be adjusted (see (2) in FIG. 1). For example, the information processing device 2 refers to candidate visit location data in which the planned visit locations of the user U are associated with the geofences before the center position and radius are adjusted, and identifies the geofence associated with the stay location that is the target location as the target geofence.

[0026] The information processing device 2 adjusts the center position of the target geofence based on the multiple stay positions acquired in (1) and the target geofence identified in (2) (see (3) in Figure 1). The information processing device 2, for example, creates a target normal distribution indicating the distribution of target positions, which are stay positions acquired in association with the target location in (1). In the target normal distribution, the center position in the target geofence before adjustment becomes the center of the normal distribution. In addition, the information processing device 2, for example, creates an asymmetric normal distribution indicating the distribution of non-target positions, which are stay positions acquired in association with locations other than the target location in (1). In the asymmetric normal distribution, the center position in a geofence that is not the target geofence becomes the center of the normal distribution. In this way, the information processing device 2 creates multiple normal distributions corresponding to each of the multiple locations.

[0027] Then, the information processing device 2 creates a mixed normal distribution by combining, for example, a target normal distribution based on a target position, which is a stay position associated with a target place whose center position and radius are to be adjusted, and a non-target normal distribution based on a non-target position, which is a stay position associated with a place other than the target place. The information processing device 2 adjusts the center position of the target geofence by updating the most probable position as the center position of the target geofence to a new center position using, for example, MAP estimation (maximum a posteriori probability estimation) based on the mixed normal distribution.

[0028] Next, the information processing device 2 adjusts the radius of the target geofence based on the multiple stay locations acquired in (1) and the target geofence identified in (2) (see (4) in FIG. 1). For example, the information processing device 2 determines, among the stay locations present inside the target geofence, the stay locations acquired in (1) in association with the target location to be negative potential, and determines the stay locations acquired in (1) in association with a location other than the target location to be positive potential. Then, the information processing device 2 adjusts the radius of the target geofence by, for example, updating the radius to a new radius that minimizes the total potential obtained by adding up all the negative potentials and positive potentials.

[0029] In this way, the information processing system S repeatedly updates the pre-adjustment center position and radius of the target geofence to more appropriate center position and radius based on the actual location of the user U. This reduces the occurrence of false detection or non-detection of the geofence compared to the conventional case where fixed values ​​are used as the center position and radius of the geofence. As a result, the accuracy of the geofence can be improved, resulting in a more accurate record of the user U's sales activity. The configurations and operations of the information terminal 1 and the information processing device 2 will be described in detail below.

[0030] [Configuration of Information Terminal 1] 2 is a diagram showing an example of the configuration of information terminal 1. Information terminal 1 includes a terminal communication unit 11, a display unit 12, an operation unit 13, a storage unit 14, and a control unit 15. Control unit 15 includes a display processing unit 151 and an operation receiving unit 152.

[0031] The terminal communication unit 11 is a communication interface for communicating with the information processing device 2 via a communication network such as the Internet. The terminal communication unit 11 receives screen information showing an input screen for prompting the user U to input a place of stay, and inputs the received screen information to the display processing unit 151. The terminal communication unit 11 transmits the place of stay of the user U input from the operation reception unit 152 to the information processing device 2. The terminal communication unit 11 transmits the position of stay of the user U identified by GPS or the like to the information processing device 2.

[0032] The display unit 12 is configured by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display. The display unit 12 displays various information under the control of the display processing unit 151. The display unit 12 displays, for example, a screen for inputting a place of stay. The operation unit 13 is a device that receives operations from the user U, and is, for example, a keyboard, a mouse, or a touch panel.

[0033] The storage unit 14 is a storage medium including a ROM (Read Only Memory), a RAM (Random Access Memory), etc. The storage unit 14 stores a program executed by the control unit 15. For example, the storage unit 14 stores a program that causes the control unit 15 to function as a display processing unit 151 and an operation receiving unit 152.

[0034] The control unit 15 is, for example, a CPU (Central Processing Unit). The control unit 15 executes a program stored in the storage unit 14, thereby functioning as a display processing unit 151 and an operation receiving unit 152.

[0035] The display processing unit 151 displays various types of information on the display unit 12. For example, the display processing unit 151 displays an input screen for a place of stay on the display unit 12 based on screen information input from the device communication unit 11. The display processing unit 151 may display an input screen that allows the user U to manually input a character string indicating the place of stay, or may display an input screen that allows the user U to select a place where the user U stayed from among a plurality of options for places of stay.

[0036] The operation receiving unit 152 receives various operations from the user U. For example, the operation receiving unit 152 receives a place of stay input by the user U and inputs the received place of stay to the terminal communication unit 11.

[0037] [Configuration of information processing device 2] 3 is a diagram showing an example of the configuration of the information processing device 2. The information processing device 2 includes a device communication unit 21, a storage unit 22, and a control unit 23. The control unit 23 includes an acquisition unit 231, an identification unit 232, and an adjustment unit 233.

[0038] The device communication unit 21 is a communication interface for communicating with the information terminal 1 via a communication network such as the Internet. The device communication unit 21 transmits screen information showing an input screen for the place of stay to the information terminal 1. The screen information may be information required to display the input screen (for example, HyperText Markup Language, etc.). The device communication unit 21 inputs the place of stay and the position of stay of the user U received from the information terminal 1 to the acquisition unit 231.

[0039] The storage unit 22 is a storage medium including a ROM, a RAM, etc. The storage unit 22 stores a program executed by the control unit 23. For example, the storage unit 22 stores an information processing program that causes the control unit 23 to function as an acquisition unit 231, an identification unit 232, and an adjustment unit 233. The storage unit 22 stores candidate visit location data, geofence data, and planned visit data.

[0040] FIG. 4 is a diagram showing an example of candidate visit location data. In the candidate visit location data, a customer ID, GIS information, customer attributes, candidate visit locations, and a geofence ID are associated with each other. The customer ID is information for identifying a customer. The GIS information is information obtained from a geographic information system (GIS) that indicates the geographic structure within and around the customer's premises. For example, Open Street MAP (registered trademark) can be used as the GIS.

[0041] Customer attributes include industry type, location, location environment, company size, capital structure, etc. Candidate visit locations are locations that user U may visit, such as the name of the customer or the name of a building on the customer's premises. As shown in FIG. 4, multiple candidate visit locations may be set for one customer. The geofence ID is information for identifying a geofence, and is set for each of multiple candidate visit locations.

[0042] FIG. 5 is a diagram illustrating an example of geofence data. In the geofence data, a geofence ID, a geofence center position (latitude and longitude), and a geofence radius are associated with each other. The center position and radius in the geofence data are updated as needed by the adjustment unit 233 (described later), and may be values ​​that have been adjusted at least once, or may be values ​​that have never been adjusted (initial values). The initial values ​​of the center position and radius are, for example, the center position and radius of the smallest circle that can encompass the building of the candidate visit location indicated by the GIS. The initial values ​​of the center position and radius may be set based on customer attributes; for example, a relatively small radius may be set for customers whose candidate visit locations are in urban areas to reduce false positives.

[0043] FIG. 6 is a diagram showing an example of visit schedule data. In the visit schedule data, a user ID, a planned visit location, and a planned visit time are associated with each other. The user ID is information for identifying a user. The planned visit location is the name of a customer that the user U plans to visit, the name of a building on the customer's premises, etc. The planned visit time is the time period during which the user U plans to visit the planned visit location.

[0044] The control unit 23 is, for example, a CPU. The control unit 23 executes an information processing program stored in the storage unit 22, thereby functioning as an acquisition unit 231, a specification unit 232, and an adjustment unit 233.

[0045] The acquisition unit 231 acquires the stay position where the user U stayed. The acquisition unit 231 acquires the stay position by receiving, for example, the latitude and longitude indicating the stay position of the user U identified by GPS from the information terminal 1.

[0046] The acquisition unit 231 may acquire location information indicating the location of the user U, which is transmitted from the information terminal 1 periodically (for example, every five minutes). The acquisition unit 231 may acquire location information indicating the location of the user U, which is transmitted from the information terminal 1 when the acceleration measured by an acceleration sensor mounted on the information terminal 1 becomes equal to or greater than a threshold. However, when these methods are used, the transmitted multiple pieces of location information may include location information indicating the location of the user U while he is moving. If such location information of the user U while he is moving is used to adjust the geofence, the accuracy of the geofence may be reduced. Therefore, the acquisition unit 231 may identify location information indicating the location where the user U is staying from the multiple pieces of location information, as described below.

[0047] The acquisition unit 231 acquires, for example, a first location and a second location where the user U is present. Then, for example, when a value calculated based on a point-to-point distance between the first location and the second location and a time difference between a first time when the first location is acquired and a second time when the second location is acquired satisfies a predetermined condition, the acquisition unit 231 determines the first location and the second location as the user U's stay location. The acquisition unit 231 may determine the first location and the second location as the user U's stay location when a moving distance per unit time calculated by dividing the point-to-point distance by the time difference is less than a threshold (i.e., when the user U has not moved at all or has not moved much). This operation of the acquisition unit 231 increases the probability that the positions where the user U actually stays at the planned visit location can be acquired as the stay location, thereby improving the accuracy of geofence adjustment. The acquisition unit 231 stores the stay location data updated by acquiring the stay location in the storage unit 22.

[0048] FIG. 7 is a diagram showing an example of stay location data. In the stay location data, a user ID, a time, a location, and a stay location flag are associated with each other. The time is the time when the acquisition unit 231 acquires location information indicating the location of the user U. The location is the location of the user U indicated by the location information acquired by the acquisition unit 231. The stay location flag is a flag indicating the stay location of the user U (i.e., a location excluding a location when moving, etc.). In FIG. 7, a location where the stay flag is "◯" is the stay location of the user U.

[0049] The acquisition unit 231 acquires the place where the user U stayed (for example, customer name, address, building name). For example, the acquisition unit 231 acquires the place transmitted to the information processing device 2 by the information terminal 1 used by the user U as the place where the user U stayed. As described above, the display processing unit 151 of the information terminal 1 displays an input screen for the place of stay on the display unit 12, so that the user U can input the place of stay on the input screen when the user U completes their stay at the place of stay. The acquisition unit 231 may acquire the place of stay by receiving the place of stay input by the user U in this way from the information terminal 1. The acquisition unit 231 stores the place of stay data updated by acquiring the place of stay in the storage unit 22.

[0050] FIG. 8 is a diagram showing an example of stay location data. In the stay location data, time, a user ID, and a stay location are associated with each other. The time may be the time when the acquisition unit 231 acquires the stay location input by the user U, or may be the time when the user U reports the time when he or she stayed at the stay location (after finishing his or her stay at the stay location and returning to the office, for example). The stay location is the stay location input by the user U. Every time the acquisition unit 231 acquires a stay location, it adds a record indicating the acquired stay location to the stay location data.

[0051] However, there is a possibility that the user U may forget or neglect to input the place of stay in the information terminal 1. Therefore, the acquisition unit 231 may refer to the visit schedule data ( FIG. 6 ) in which the user ID, the planned visit place, and the planned visit time are associated with each other, and acquire, as the place of stay of the user U, the planned visit place associated with the user ID of the user who uses the information terminal 1 that transmitted the stay location and the planned visit time to which the time when the information terminal 1 transmitted the stay location belongs. In this way, even if the user U forgets or neglects to input the place of stay, the acquisition unit 231 can acquire the place of stay, and the adjustment unit 233 can adjust the geofence.

[0052] To adjust the geofence, the acquisition unit 231 may acquire a combination of the stay position and the stay place by associating the stay position and the stay place acquired as described above. Specifically, the acquisition unit 231 refers to the stay place data (FIG. 8), identifies a time closest to the time associated with the stay position in the stay position data (FIG. 7), and identifies the stay place associated with the identified time, thereby acquiring the combination of the stay position and the stay place.

[0053] The acquisition unit 231 may acquire a combination of a stay location and a stay location by referring to the visit schedule data (FIG. 6) and identifying, as a stay location, a planned visit location associated with a planned visit time to which the time associated with a stay location in the stay location data (FIG. 7) belongs. The acquisition unit 231 stores, in the storage unit 22, the combination data updated by acquiring the combination of the stay location and the stay location.

[0054] 9 is a diagram showing an example of combination data. In the combination data, a user ID, a combination ID, a stay position, and a stay location are associated with each other. The combination ID is information for identifying a combination of a stay location and a stay location of a user U.

[0055] The acquisition unit 231 inputs the acquired location of the user U to the identification unit 232. The acquisition unit 231 also inputs the acquired location of the user U to the adjustment unit 233.

[0056] The identification unit 232 refers to candidate visit place data in which candidate visit places and geofences are associated with each other, and identifies a target geofence that is a geofence associated with the acquired place of stay. The identification unit 232, for example, refers to the candidate visit place data (FIG. 6), and identifies, as the target geofence, a geofence associated with a place of stay that is a target place for adjusting the center position and radius of the geofence, from among the multiple places of stay input from the identification unit 232. The target place is, for example, a place included in an area designated by the user U as a target for adjusting the geofence.

[0057] The adjustment unit 233 adjusts the center position and size of the target geofence based on the relationship between the area corresponding to the target geofence identified by the identification unit 232 and the stay position acquired by the acquisition unit 231. For example, the adjustment unit 233 adjusts the center position and size of the target geofence based on the output result output by a mathematical model by inputting the area corresponding to the target geofence and the acquired stay position into the mathematical model. The mathematical model may be a known statistical method, or may be a machine learning model using machine learning technology that learns how to adjust the center position and size of the target geofence.

[0058] The adjustment unit 233 may determine the center position of the target geofence before determining the radius of the target geofence. The adjustment unit 233, for example, creates a target normal distribution indicating the distribution of target positions, which are stay positions associated with the target location, among the multiple stay positions input from the acquisition unit 231. In the target normal distribution, the center position of the target geofence before adjustment becomes the center of the normal distribution. Furthermore, the adjustment unit 233, for example, creates an asymmetric normal distribution indicating the distribution of non-target positions, which are stay positions associated with locations other than the target location, among the multiple stay positions input from the acquisition unit 231. The probability density functions of the target normal distribution and the asymmetric normal distribution are expressed by the following Equation 1, which uses two variables (X, Y) that uniquely determine coordinates on a two-dimensional map. In the following Equation 1, the observed value of the random variable X is x, and the observed value of the random variable Y is y.

[0059]

number

[0060] Then, the adjustment unit 233 creates a two-dimensional mixed normal distribution that combines, for example, a target normal distribution and a non-target normal distribution. The adjustment unit 233 may create the two-dimensional mixed normal distribution by adding a value indicating the target normal distribution and a value indicating the non-target normal distribution with opposite signs. The adjustment unit 233 adjusts the center position of the target geofence by, for example, determining the most likely position as the center position of the target geofence using MAP estimation (maximum a posteriori probability estimation) based on the created two-dimensional mixed normal distribution.

[0061] The adjustment unit 233 determines the radius of the target geofence. When the stay position acquired by the acquisition unit 231 is outside the area corresponding to the target geofence identified by the identification unit 232, the adjustment unit 233 may adjust the radius of the target geofence so that the acquired stay position is included inside the target geofence. For example, when the number of stay positions existing outside the area corresponding to the target geofence is equal to or greater than a threshold, the adjustment unit 233 increases the radius of the target geofence. By operating in this manner, it is possible to increase the probability that the presence of the user U in the geofence corresponding to a customer when the user U is visiting the customer is correctly detected.

[0062] On the other hand, when the stay position acquired by the acquisition unit 231 is located inside an area corresponding to the target geofence identified by the identification unit 232, the adjustment unit 233 may adjust the radius of the target geofence so as to maintain a state in which the acquired stay position is included inside the target geofence. For example, when a predetermined percentage or more of the stay positions among the multiple stay positions acquired by the acquisition unit 231 are included in a predetermined area within the target geofence, the adjustment unit 233 reduces the radius of the target geofence so as to maintain a state in which the predetermined area is included inside the target geofence.

[0063] That is, the adjustment unit 233 reduces the radius of the target geofence when the stay positions reported by the user U are concentrated in a certain location within the target geofence. By operating in this manner, the adjustment unit 233 can reduce the probability that the user U is mistakenly detected to be within the geofence corresponding to a customer when the user U is not visiting that customer in a customer-dense area such as an urban area.

[0064] However, even if multiple stay positions exist within the area corresponding to the target geofence, if a value indicating the degree of dispersion of the multiple stay positions within the target geofence is equal to or greater than a threshold, the adjustment unit 233 may increase the radius of the target geofence. By operating in this manner, even if the stay position of the user U changes each time because the user U visits a customer with a large site area, such as a factory in the suburbs, the probability of correctly detecting that the user U is within the geofence corresponding to the customer can be increased.

[0065] The adjustment unit 233 may determine the radius of the target geofence based on the above-mentioned two-dimensional mixed normal distribution. The adjustment unit 233 calculates a first value based on, for example, target positions which are multiple stay positions associated with the target place and acquired by the acquisition unit 231. The first value is, for example, a negative value indicating the probability that one target position exists inside the target geofence, and the smaller the first value, the higher the probability that the target position exists inside the target geofence.

[0066] The adjustment unit 233 may calculate a first negative value based on a target position included inside the target geofence. The adjustment unit 233 calculates the first negative value, for example, by substituting each of coordinates indicating a plurality of target positions included inside the target geofence into a first calculation formula. The first calculation formula is, for example, a calculation formula in which the calculated negative value becomes smaller as the coordinates are closer to the center position of the target geofence. Note that the adjustment unit 233 may determine the first value by setting each of the plurality of target positions included inside the target geofence to a fixed negative value.

[0067] The adjustment unit 233 calculates the second value based on, for example, non-target locations, which are multiple stay locations associated with locations other than the target location and acquired by the acquisition unit 231. The second value is, for example, a positive value indicating the probability that one non-target location exists inside the target geofence, and the larger the second value is, the lower the probability that the non-target location exists inside the target geofence.

[0068] The adjustment unit 233 may calculate the second positive value based on non-target positions included inside the target geofence. The adjustment unit 233 calculates the second positive value, for example, by substituting each of coordinates indicating multiple target positions included inside the target geofence into a second calculation formula. The second calculation formula is, for example, a calculation formula in which the calculated positive value increases as the coordinates become farther from the center position of the target geofence. Note that the adjustment unit 233 may determine the second value by setting each of multiple non-target positions included inside the target geofence to a fixed positive value.

[0069] The adjustment unit 233 adjusts the radius of the target geofence based on, for example, the calculated first value and the calculated second value. The adjustment unit 233 may adjust the radius of the target geofence to a radius of the geofence that minimizes the sum of the negative first value and the positive second value.

[0070] FIG. 10 is a diagram illustrating an example of adjusting the radius of a target geofence. The circle indicates the target geofence (the geofence whose radius is to be adjusted). The "-" sign indicates the target location (the location where a user U who reported visiting the target location stayed), and in the example of FIG. 10, one "-" sign means "-1." The "+" sign indicates a non-target location (the location where a user U who reported visiting a location other than the target location stayed), and in the example of FIG. 10, one "+" sign means "+1." As shown in FIG. 10, the closer to the center position of the target geofence, the more users U(-) who reported staying at the target location, and conversely, the farther away from the center position of the target geofence, the more users U(+) who reported staying at the non-target location.

[0071] As shown in Figure 10(a), if the radius of the target geofence is too large, the number of "+" signs will be greater than the number of "-" signs within the target geofence, resulting in a large sum of the negative value obtained by summing up the "-" signs and the positive value obtained by summing up the "+" signs. This radius is prone to false positives, where user U is mistakenly detected as having visited a certain customer even though he or she did not. On the other hand, as shown in Figure 10(b), if the radius of the target geofence is too small, the number of "-" signs will be greater than the number of "+" signs within the target geofence, but the number of "-" signs is less than the threshold, resulting in a medium sum of the negative value obtained by summing up the "-" signs and the positive value obtained by summing up the "+" signs. This radius is prone to false negatives, where user U is not correctly detected as having visited a certain customer even though he or she did visit that customer.

[0072] By adjusting the radius in this manner, as shown in FIG. 10(c), at a certain radius, the number of "-" signs becomes greater than the number of "+" signs, and the number of "-" signs becomes equal to or greater than a threshold value, so the sum of the negative value obtained by adding up the "-" signs and the positive value obtained by adding up the "+" signs becomes the smallest. This radius is an appropriate radius because it is a radius where false detections and non-detections are unlikely to occur. In this way, the adjustment unit 233 determines an appropriate radius.

[0073] However, the target geofence defined by the center position and radius determined in this manner may overlap with another geofence. In this case, a false detection may occur in which user U is mistakenly detected as having visited a second customer despite having visited a first customer. Therefore, if the target geofence after the center position and radius are adjusted overlaps with another geofence, the adjustment unit 233 may reduce the radius of the target geofence so that the target geofence does not overlap with the other geofence. For example, the adjustment unit 233 determines a radius that minimizes the sum of the negative first value and the positive second value within the target geofence, among radii that can eliminate the overlap between the target geofence and the other geofence. By operating in this manner, the adjustment unit 233 can suppress the occurrence of false detection.

[0074] When the target geofence after the center position and radius have been adjusted overlaps with another geofence, the adjustment unit 233 may reduce the radius of the target geofence so that the area of ​​the overlapping region becomes smaller. For example, the adjustment unit 233 may reduce the radius of the target geofence so that the area of ​​the overlapping region becomes less than a threshold. By operating in this manner, the adjustment unit 233 can increase the probability of correctly detecting that the user U has visited the first customer corresponding to the target geofence while suppressing erroneous detection that the user U has visited the second customer corresponding to the other geofence.

[0075] When the target geofence overlaps with another geofence, the adjustment unit 233 may reduce the radius of the geofence corresponding to a customer who has a lower priority for the organization to which the user U belongs. By operating in this manner, the adjustment unit 233 does not need to reduce the radius of the geofence corresponding to an important customer who has a higher priority for the organization to which the user U belongs, and this can prevent a situation from occurring in which the user U visits an important customer but the visit is not detected. As a result, the organization to which the user U belongs can appropriately analyze sales to important customers.

[0076] If the radius of the target geofence is reduced, it becomes more likely that user U's visit to a customer will not be detected properly, so the adjustment unit 233 may execute the following process, which does not require reducing the radius of the geofence.

[0077] For example, when the user U stays in an area where the target geofence and another geofence overlap for a certain period of time or more, the adjustment unit 233 transmits screen information to the information terminal 1 of the user U, which screen information indicates a selection screen that allows the user U to select whether the user U visited a place corresponding to the target geofence or a place corresponding to another geofence. This allows the user U to select a place that the user U actually visited on the selection screen. By operating the adjustment unit 233 in this manner, it is possible to suppress the occurrence of false detections caused by the target geofence overlapping with another geofence, while also suppressing the occurrence of non-detection caused by a small radius of the target geofence.

[0078] Furthermore, the target geofence may overlap with an area corresponding to a public space (such as a road, sidewalk, bridge, or public facility). In this case, a false positive may occur, in which the user U is detected as having visited a customer even though he or she merely passed through the public space. Therefore, if the target geofence after the center position and radius are adjusted overlaps with an area corresponding to a public space, the adjustment unit 233 may reduce the radius of the target geofence so that the target geofence does not overlap with the area corresponding to the public space. For example, the adjustment unit 233 determines a radius that minimizes the sum of the first negative value and the second positive value within the target geofence, among radii that can eliminate the overlap between the target geofence and the area corresponding to the public space. By operating in this manner, the adjustment unit 233 can suppress the occurrence of false positives.

[0079] When the target geofence after the center position and radius have been adjusted overlaps with an area corresponding to a public space, the adjustment unit 233 may reduce the radius of the target geofence so that the area of ​​the overlapping area becomes smaller. For example, the adjustment unit 233 may reduce the radius of the target geofence so that the area of ​​the overlapping area becomes less than a threshold. By operating in this manner, the adjustment unit 233 can increase the probability of correctly detecting that the user U has visited a customer corresponding to the target geofence, while suppressing the possibility of the user U being erroneously detected as having visited a customer corresponding to the target geofence when the user U has only passed through a public space.

[0080] [Variations] In the above example, a target position within the target geofence is set to a negative value and a non-target position within the target geofence is set to a positive value. However, a target position within the target geofence may be set to a positive value and a non-target position within the target geofence may be set to a negative value. In other words, in the example shown in FIG. 10, the "+" and "-" may be reversed. In this case, the adjustment unit 233 may adjust the radius of the target geofence to a radius of the geofence that maximizes the sum of the negative and positive values.

[0081] In the above example, the center position is determined using a statistical method such as MAP estimation, and then the radius is determined based on the total value inside the target geofence. However, the adjustment unit 233 may determine the center position and the radius based on the total value inside the target geofence. Specifically, the adjustment unit 233 may adjust the center position and the radius of the target geofence to a center position and a radius such that the total value of a first value that is a negative value corresponding to a target position inside the target geofence and a second value that is a positive value corresponding to a non-target position inside the target geofence is minimum.

[0082] [Flow of processing executed by information processing device 2] 11 is a flowchart showing an example of the flow of a process for determining a center position. The acquisition unit 231 acquires an area to be updated, which is a target for updating the center position and radius of a geofence (S1). The area to be updated is, for example, an area selected by the user U on a map displayed on the information terminal 1. Since it is preferable that the center position and radius of the geofence be updated as needed, the acquisition unit 231 acquires the area to be updated periodically (for example, once a week).

[0083] The identification unit 232 refers to the geofence data (FIG. 5) and identifies one or more geofences (GF) whose center positions are included in the area to be updated acquired in S1 as target geofences whose center positions and radiuses are to be determined (S2). The adjustment unit 233 determines whether or not the user U has a history of visiting a customer corresponding to the target geofence identified in S2 (S3).

[0084] If the adjustment unit 233 determines that there is no visit history to the customer (S3: NO), it determines the center position of the target geofence based on the customer position indicated by the GIS (S4).On the other hand, if the adjustment unit 233 determines that there is a visit history to the customer (S3: YES), it determines the center position using the above-mentioned MAP estimation based on the customer position indicated by the GIS and the stay position transmitted from the information terminal 1 of the user U (S5).

[0085] The adjustment unit 233 determines whether the determination of the center position of the target geofence has been completed for all customers in the area to be updated acquired in S1 (S6). If the adjustment unit 233 determines that the determination of the center position for all customers has not been completed (S6: NO), the adjustment unit 233 returns to S3 and determines the center position of the geofence corresponding to the customer whose center position has not been determined. On the other hand, if the adjustment unit 233 determines that the determination of the center position for all customers has been completed (S6: YES), the adjustment unit 233 proceeds to the processing of S7 to determine the radius of the target geofence.

[0086] 12 is a flowchart showing an example of the process flow for determining the radius. The adjustment unit 233 determines the radius for each of the one or more target geofences identified in S2 such that the total potential inside the target geofence is the smallest (S7).

[0087] The adjustment unit 233 determines whether one or more target geofences defined by the radii identified in S7 overlap each other (S8). If the adjustment unit 233 determines that the target geofences overlap each other (S8: YES), the adjustment unit 233 reduces the radius of at least one of the overlapping target geofences so that the target geofences do not overlap each other or so that the area of ​​the overlapping region of the target geofences is reduced (S9). By operating in this manner, the adjustment unit 233 can reduce the occurrence of false detection in which a customer different from the customer who actually stayed at the user U is detected as the stay destination, particularly in a customer-dense area such as an urban area.

[0088] On the other hand, when the adjustment unit 233 determines that the target geofences do not overlap each other (S8: NO), it determines whether each of the one or more target geofences defined by the latest radius overlaps with an area indicating a public space (S10). When the adjustment unit 233 determines that the target geofence overlaps with an area indicating a public space (S10: YES), it reduces the radius of the target geofence so that the overlap with the public space disappears or the area of ​​the overlapping area between the target geofence and the public space decreases (S11). By operating in this manner, the adjustment unit 233 can reduce the occurrence of false detection in which the user U is detected as having stayed with a customer even though the user U merely passed through a public space near the customer.

[0089] On the other hand, when the adjustment unit 233 determines that the target geofence does not overlap with the area indicating the public space (S10: NO), it determines whether the number of undetected cases where the user U's stay location is not included inside the target geofence corresponding to the stay location even though the stay location was transmitted from the information terminal 1 of the user U is equal to or greater than a threshold (S12).When the adjustment unit 233 determines that the number of undetected cases is equal to or greater than the threshold (S12: YES), it increases the radius of the target geofence (S13).

[0090] In order to increase the radius of the target geofence whose center position and radius are to be adjusted, the adjustment unit 233 may use, for example, the above-mentioned formula 1, which indicates that, among multiple stay locations reported in association with the target geofence, stay locations that are outside the target geofence and indicate undetection have a greater impact on the adjustment of the radius than stay locations that are inside the target geofence. Formula 1 is, for example, a formula in which the value of the variance correction parameter β (>0) decreases as the number of undetection increases.

[0091] The adjustment unit 233 increases the radius of the target geofence, for example, by substituting coordinates corresponding to each of the multiple stay locations reported in association with the target geofence into the above-mentioned formula 1. By operating in this manner, the adjustment unit 233 can prevent the occurrence of undetected stays of the user U despite the user U staying at a customer's location. Furthermore, when a location that should be reported in association with the target geofence is outside the target geofence, the location can be reported in association with the target geofence.

[0092] However, as a result of the adjustment unit 233 increasing the radius of the target geofence based on the number of undetected locations in this manner, an area where the target geofences overlap with each other or an area where the target geofence overlaps with a public space may occur. In this case, the adjustment unit 233 may reduce the radius of the target geofence so as to reduce the area of ​​the overlapping area within a range including a concentrated area where reports are concentrated among the multiple stay locations reported in association with the target geofence.

[0093] On the other hand, if the adjustment unit 233 determines that the number of undetected points is less than the threshold (S12: NO), it determines whether or not the determination of the radius of the target geofence has been completed for all customers in the area to be updated acquired in S1 (S14). If the adjustment unit 233 determines that the determination of the radius for all customers has not been completed (S14: NO), it returns to S7 and determines the radius of the geofence corresponding to the customer for which the determination of the radius has not been completed. On the other hand, if the adjustment unit 233 determines that the determination of the radius for all customers has been completed (S14: YES), it ends the processing.

[0094] [Effects of information processing device 2] As described above, the adjustment unit 233 adjusts the center position and size of the target geofence based on the relationship between the area corresponding to the target geofence and the user U's stay location. This improves the accuracy of the geofence compared to the conventional case in which fixed values ​​are used as the center position and radius of the geofence. As a result, the occurrence of false detections or non-detections can be reduced, resulting in a more accurate record of user U's business activities.

[0095] The present invention has been described above using embodiments, but the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of the gist of the present invention. For example, all or part of the device can be configured by functionally or physically distributing or integrating any unit. Furthermore, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effects of the new embodiments resulting from the combination also have the effects of the original embodiments. [Explanation of symbols]

[0096] 1. Information terminal 11. Terminal communication unit 12 Display section 13 Control section 14 Storage section 15 Control Unit 151 Display processing unit 152 Operation reception unit 2. Information processing equipment 21 Device communication unit 22 Memory section 23 Control Unit 231 Acquisition Department 232 Specific part 233 Adjustment section S Information Processing System

Claims

1. a storage unit that stores candidate visit place data in which candidate visit places that are candidates for a user to visit are associated with geofences that are geographical areas surrounded by virtual boundaries corresponding to the candidate visit places; an acquisition unit that acquires the place and location where the user stayed; an identification unit that refers to the candidate visit place data and identifies a target geofence that is the geofence associated with the acquired place of stay; An adjustment unit that adjusts a center position and a size of the target geofence based on a relationship between an area corresponding to the target geofence and the acquired stay position; An information processing device having the above.

2. When the acquired stay position is outside the area corresponding to the target geofence, the adjustment unit adjusts the size of the target geofence so that the acquired stay position is included inside the target geofence. The information processing device according to claim 1 .

3. When the acquired stay position is within an area corresponding to the target geofence, the adjustment unit adjusts the size of the target geofence so that the acquired stay position is maintained within the target geofence. The information processing device according to claim 1 .

4. The adjustment unit adjusts the center position and size of the target geofence based on a first value calculated based on target positions that are the stay positions acquired by the acquisition unit in association with a target location whose center position and size are to be adjusted, and a second value calculated based on non-target positions that are the stay positions acquired by the acquisition unit in association with locations other than the target location, The information processing device according to claim 1 .

5. The adjustment unit adjusts the center position and size of the target geofence to a center position and size of the geofence such that the sum of the first value, which is a negative value calculated based on the target position included inside the target geofence, and the second value, which is a positive value calculated based on the non-target position included inside the target geofence, is minimized. The information processing device according to claim 4 .

6. The adjustment unit adjusts the center position and size of the target geofence based on the output result output by the mathematical model by inputting the area corresponding to the target geofence and the acquired stay position into a mathematical model. The information processing device according to claim 1 .

7. the acquisition unit acquires a first location and a second location where the user is present, and determines the first location and the second location as the user's stay location if a value calculated based on a distance between the first location and the second location and a time difference between a first time when the first location is acquired and a second time when the second location is acquired satisfies a predetermined condition. The information processing device according to claim 1 .

8. The acquisition unit acquires, as the location of the user, a location transmitted from an information terminal used by the user to the information processing device. The information processing device according to claim 1 .

9. the storage unit further stores visit schedule data in which the user, a planned visit place that the user plans to visit, and a planned visit time to the planned visit place are associated with each other; the acquisition unit refers to the visit schedule data and acquires, as the stay location of the user, the planned visit location associated with the user using the information terminal that transmitted the stay location and a planned visit time that includes a time when the information terminal transmitted the stay location. The information processing device according to claim 1 .

10. The computer executes acquiring a place and a location where the user stayed; A step of referring to candidate visit place data in which candidate visit places that are candidates to be visited by the user and geofences that are geographical areas surrounded by virtual boundaries corresponding to the candidate visit places are associated with each other, and identifying a target geofence that is the geofence associated with the acquired place of stay; adjusting a center position and a size of the target geofence based on a relationship between an area corresponding to the target geofence and the acquired stay position; An information processing method comprising:

11. The processor of the information processing device is an acquisition unit that acquires the place and location where the user stayed; an identification unit that identifies a target geofence, which is the geofence associated with the acquired place of stay, by referring to candidate place visit data in which candidate places to be visited by the user are associated with geofences, which are geographical areas surrounded by virtual boundaries corresponding to the candidate places to be visited; An adjustment unit that adjusts a center position and a size of the target geofence based on a relationship between an area corresponding to the target geofence and the acquired stay position. A program to function as a

12. An information processing device and an information terminal used by a user that is capable of communicating with the information processing device, The information processing device includes: a storage unit that stores candidate visit place data in which candidate visit places that are candidates for the user to visit are associated with geofences that are geographical areas surrounded by virtual boundaries corresponding to the candidate visit places; an acquisition unit that acquires the place and location where the user stayed; an identification unit that refers to the candidate visit place data and identifies a target geofence that is the geofence associated with the acquired place of stay; An adjustment unit that adjusts a center position and a size of the target geofence based on a relationship between an area corresponding to the target geofence and the acquired stay position; and the information terminal has a terminal communication unit that transmits the place and position of the user to the information processing device; Information processing system.

Images