JP6878534B2 - Estimator system, estimator, estimation method and computer program - Google Patents

Description

The present invention relates to an estimation system, an estimation device, an estimation method and a computer program.

In recent years, it has been required to estimate the number of people who have visited the facility among those who have browsed online advertisements using a terminal device. As such a technique, there is a technique of estimating whether or not a user of the terminal device has visited the facility based on the position of the terminal device acquired from GPS (Global Positioning System). In the estimation technology using GPS, for example, when the acquired position of the terminal device is within the premises of the facility, the system estimates that the user of the terminal device has visited the facility. However, the estimation technique using GPS is easily affected by the error of GPS. Due to the influence of GPS error, it may be difficult to accurately estimate whether or not the user of the terminal device has visited the facility. For this reason, the system has been studied to improve the estimation accuracy, such as acquiring a plurality of positions of the terminal device and estimating whether or not the user has visited the facility based on the movement route of the terminal device.

Japanese Unexamined Patent Publication No. 2013-205226

However, due to the growing awareness of the protection of personal information, there are increasing cases where the location acquisition conditions differ for each terminal device. For this reason, terminal devices that can track the movement route and terminal devices that cannot track the movement route have come to coexist. In such a situation, it may be difficult to estimate the number of people who have visited a predetermined place such as a facility.

In view of the above circumstances, it is an object of the present invention to provide a technique capable of estimating the number of people who have visited a predetermined place with higher accuracy.

One aspect of the present invention is an information acquisition unit that acquires a plurality of position information indicating the position of a terminal device and transaction information indicating the content of a transaction performed by the owner of the terminal device, and the position information and the transaction information. Based on the above, the actual number of people who actually visited the predetermined facility where the transaction was performed and actually visited the facility shown in the transaction information was calculated, and the actual number of people who made the transaction was calculated and used in the location information . Based on the number of visitors estimated to have visited the predetermined facility with the terminal device and the actual number of transactions , statistical information regarding the number of people who visited the predetermined facility was generated. Based on the number of terminal identifiers indicating the number of terminal identifiers used for transactions at the predetermined facility based on the transaction information and the actual number of transactions , the actual operation was performed using the terminal device at the predetermined facility. It is located within the area of the facility that is the target of estimation processing among a plurality of location information including the calculation unit that generates comprehensive information indicating the ratio of transactions that can be covered and the information that is not used for the processing in the calculation unit. the number of location information, and the statistical information, and the exhaustive information, based on, and a estimation unit that estimates a real transaction number for definitive the subject to property of the estimation process, is the estimated system.

One aspect of the present invention is the above-described estimation system, the estimator is further based on the number of facilities near the predetermined facility region or the predetermined facility shown, actual transactions against the predetermined facility Estimate the number of people.

One aspect of the present invention is the above-described estimation system, the estimator is further based on said number of location information per capita owner of the terminal device, to estimate the actual transaction number against a predetermined facility ..

One aspect of the present invention is an information acquisition unit that acquires a plurality of position information indicating the position of a terminal device and transaction information indicating the content of a transaction performed by the owner of the terminal device, the position information, and the transaction information. Based on the above, the actual number of people who actually visited the predetermined facility where the transaction was performed and actually visited the facility shown in the transaction information was calculated, and the actual number of people who made the transaction was calculated and used in the location information. Based on the number of visitors estimated to have visited the predetermined facility with the terminal device and the actual number of transactions, statistical information regarding the number of people who visited the predetermined facility was generated. Based on the number of terminal identifiers indicating the number of terminal identifiers used for transactions at the predetermined facility based on the transaction information and the actual number of transactions, the actual operation was performed using the terminal device at the predetermined facility. It is located within the area of the facility that is the target of estimation processing among a plurality of location information including the calculation unit that generates comprehensive information indicating the ratio of transactions that can be covered and the information that is not used for the processing in the calculation unit. It is an estimation device including an estimation unit that estimates the actual number of transactions in a facility that is the target of the estimation process based on the number of position information, the statistical information, and the comprehensive information.

One aspect of the present invention is an information acquisition step in which the estimation device acquires a plurality of position information indicating the position of the terminal device and transaction information indicating the content of a transaction performed by the owner of the terminal device, and the estimation device. Based on the location information and the transaction information, it is estimated that the actual number of people who actually visited the terminal device and actually visited the predetermined facility where the transaction was performed, which is shown in the transaction information. The number of people who visited the predetermined facility based on the number of visitors who are estimated to have visited the predetermined facility with the terminal device based on the location information and the number of actual transactions. A terminal device at the predetermined facility based on the number of terminal identifiers indicating the number of terminal identifiers used for the transaction at the predetermined facility based on the transaction information and the actual number of transactions. A calculation step that generates comprehensive information indicating the percentage of transactions actually performed using the above, and an estimation device estimates out of a plurality of position information including those that are not used in the processing in the calculation step. Based on the number of location information located in the area of the facility to be processed, the statistical information, and the comprehensive information, an estimation step for estimating the actual number of transactions in the facility to be estimated. , Is an estimation method.

One aspect of the present invention is a computer program for operating a computer as the above estimation system.

According to the present invention, it is possible to estimate the number of people who have visited a predetermined place with higher accuracy.

It is a system configuration diagram which shows the system configuration of the estimation system 1 of embodiment. It is a functional block diagram which shows the functional structure of the terminal apparatus 100 of embodiment. It is a functional block diagram which shows the functional structure of the estimation apparatus 200 of embodiment. It is a figure which shows one specific example of the position information of an embodiment. It is a figure which shows a specific example of the transaction information of an embodiment. It is a figure which shows a specific example of the facility information of an embodiment. It is a figure which shows a specific example of the scatter plot which shows the relationship between the correct answer rate of an embodiment, and the number of facilities. It is a figure which shows a specific example of the scatter plot which shows the relationship between the coverage rate of an embodiment and a radius. It is a figure which shows a specific example of the scatter plot which shows the relationship between the correct answer rate of an embodiment, and the number of position information per day of a person who visited a facility. It is a figure which shows a specific example of the scatter plot which shows the relationship between the coverage rate of an embodiment, and the number of position information per day of a person who visited a facility. It is a flowchart which shows the process flow of the generation of the estimation means of embodiment. It is a flowchart which shows the flow of the process of estimating the number of people who visited the facility of embodiment.

FIG. 1 is a system configuration diagram showing a system configuration of the estimation system 1 of the embodiment. The estimation system 1 is provided in the network 400. The estimation system 1 includes a plurality of terminal devices 100, an estimation device 200, and a transaction information management device 300 that are communicably connected to each other via a network 400. The estimation system 1 estimates the number of people visited by the owner of the terminal device 100 in an area indicating a facility such as a retail store, an automobile dealer, a commercial facility, or a hospital. The network 400 may be constructed by any network. For example, the network 400 may be configured with the Internet. The target area will be described later.

The terminal device 100 is an information processing device such as a smartphone or a tablet computer. The terminal device 100 generates position information at a predetermined timing. The terminal device 100 transmits the generated position information to the estimation device 200. The position information will be described later.

The estimation device 200 is an information processing device such as a personal computer or a server. The estimation device 200 acquires position information from each terminal device 100. The estimation device 200 estimates the number of people who have visited an area indicating a facility such as a retail store, an automobile dealer, a commercial facility, or a hospital, based on the location information acquired from the terminal device 100.

The transaction information management device 300 is an information processing device such as a personal computer or a server. The transaction information management device 300 stores transaction information transmitted to the estimation device 200. Transaction information will be described later. The transaction information management device 300 transmits the transaction information to the estimation device 200 at a predetermined timing. The predetermined timing may be, for example, a predetermined date and time, or may be a timing requested by the estimation device 200.

FIG. 2 is a functional block diagram showing a functional configuration of the terminal device 100 of the embodiment. The terminal device 100 includes a CPU (Central Processing Unit), a memory, an auxiliary storage device, and the like connected by a bus, and by executing a position information generation program, the communication unit 101, the input unit 102, the output unit 103, and the terminal identifier storage. It functions as a device including a unit 104 and a control unit 105. All or part of the functions of the communication unit 101, the input unit 102, the output unit 103, the terminal identifier storage unit 104, and the control unit 105 are ASIC (Application Specific Integrated Circuit), PLD (Programmable Logic Device), FPGA ( It may be realized by using hardware such as Field Programmable Gate Array). The location information generation program may be recorded on a computer-readable recording medium. The computer-readable recording medium is, for example, a flexible disk, a magneto-optical disk, a portable medium such as a ROM or a CD-ROM, or a storage device such as a hard disk built in a computer system. The location information generation program may be transmitted via a telecommunication line.

The communication unit 101 is a network interface. The communication unit 101 communicates with the estimation device 200 and the transaction information management device 300 via the network 400. The communication unit 101 may communicate by a communication method such as a wireless LAN (Local Area Network), a wired LAN, LTE (Long Term Evolution) (registered trademark), or 5G.

The input unit 102 is configured by using an input device such as a touch panel, a mouse, and a keyboard. The input unit 102 may be an interface for connecting the input device to the terminal device 100. In this case, the input unit 102 generates input data (for example, instruction information indicating an instruction to the terminal device 100) from the input signal input in the input device, and inputs the input data to the terminal device 100.

The output unit 103 outputs data to the user of the terminal device 100 via an output device (not shown) connected to the terminal device 100. The output device may be configured by using, for example, a device that outputs an image or characters to the screen. For example, the output device can be configured by using an image display device such as a liquid crystal display, an organic EL (Electro Luminescence) display, an electrophoretic display, or a CRT (Cathode Ray Tube) display. Further, the output device may be configured by using a device that prints (prints) an image or characters on a sheet. For example, the output device can be configured by using an inkjet printer, a laser printer, or the like. Further, the output device may be configured by using a device that converts characters into voice and outputs the characters. In this case, the output device can be configured by using a voice synthesizer and a voice output device (speaker). The output device may be configured by using a light emitting device such as an LED (Light Emitting Diode). The output unit 103 may be an output device configured integrally with the terminal device 100.

The terminal identifier storage unit 104 is configured by using a storage device such as a magnetic hard disk device or a semiconductor storage device. The terminal identifier storage unit 104 stores the terminal identifier. The terminal identifier is information that can uniquely identify the terminal device 100. As the terminal identifier, for example, an advertising ID such as IDFA (Advertising Identifier) or AAID (Google Advertising ID) may be used. The terminal identifier is not limited to these. The terminal identifier may be any information as long as it does not overlap with the terminal identifier stored in the other terminal device 100, such as Cookie, telephone number, or address information on the network.

The control unit 105 controls the operation of each unit of the terminal device 100. The control unit 105 is executed by a device including a processor such as a CPU and a RAM (Random Access Memory), for example. The control unit 105 functions as a terminal position acquisition unit 151, a position information generation unit 152, and a transmission unit 153 by executing the position information generation program.

The terminal position acquisition unit 151 acquires the terminal position. The terminal position acquisition unit 151 may acquire the terminal position by, for example, a satellite positioning system such as GPS. The terminal position is information representing the position of the terminal device 100. The terminal position may be, for example, information indicating the latitude and longitude of the terminal device 100 (hereinafter referred to as “latitude / longitude information”). The terminal position may include, for example, information such as altitude or speed in addition to latitude / longitude information. The terminal position may be corrected by using the speed information and the acceleration information of the terminal device 100 in a place where radio waves from the satellite positioning system are hard to reach (for example, a mountainous area or a tunnel). The terminal position acquisition unit 151 may acquire the terminal position at a predetermined timing. The predetermined timing may be a predetermined time interval such as every minute or every two minutes. The predetermined timing may be every movement of a predetermined distance such as every 100 m or every 200 m. The predetermined timing may be when a predetermined application installed in the terminal device 100 is being started. The predetermined timing may be any timing as long as it is a predetermined timing. The terminal position may be acquired based on equipment other than the satellite positioning system such as GPS. For example, the terminal position may be acquired based on the map information provided by the company that handles the map information.

The position information generation unit 152 generates position information. The position information is information indicating the position of the terminal device 100 at a predetermined time. When the terminal position is acquired, the position information generation unit 152 acquires the terminal identifier from the terminal identifier storage unit 104. When the terminal position is acquired, the position information generation unit 152 acquires the time when the terminal position is acquired. The time may be the time indicated by the clock provided in the terminal device 100, or may be the time acquired from an external NTP (Network Time Protocol) server. The position information generation unit 152 generates position information by associating the terminal identifier with the terminal position and the time. The position information generation unit 152 outputs the generated position information to the transmission unit 153. The transmission unit 153 transmits the position information to the estimation device 200.

FIG. 3 is a functional block diagram showing a functional configuration of the estimation device 200 of the embodiment. The estimation device 200 includes a CPU, a memory, an auxiliary storage device, and the like connected by a bus, and by executing an estimation program, the communication unit 201, the input unit 202, the output unit 203, the position information storage unit 204, and the transaction information storage unit. It functions as a device including 205, a facility information storage unit 206, an estimation means storage unit 207, and a control unit 208. All or part of the functions of the communication unit 201, the input unit 202, the output unit 203, the position information storage unit 204, the transaction information storage unit 205, the facility information storage unit 206, the estimation means storage unit 207, and the control unit 208 are , ASIC, PLD, FPGA and the like may be used. The estimation program may be recorded on a computer-readable recording medium. The estimation program may be transmitted over a telecommunication line.

The communication unit 201 is a network interface. The communication unit 201 communicates with the terminal device 100 and the transaction information management device 300 via the network 400. The communication unit 201 may communicate by a communication method such as wireless LAN, wired LAN, LTE or 5G.

The input unit 202 is configured by using an input device such as a touch panel, a mouse, and a keyboard. The input unit 202 may be an interface for connecting the input device to the estimation device 200. In this case, the input unit 202 generates input data (for example, instruction information indicating an instruction to the estimation device 200) from the input signal input in the input device, and inputs the input data to the estimation device 200.

The output unit 203 outputs data to the user of the estimation device 200 via an output device (not shown) connected to the estimation device 200. The output device may be configured by using, for example, a device that outputs an image or characters to the screen. For example, the output device can be configured by using an image display device such as a liquid crystal display, an organic EL display, an electrophoretic display, or a CRT display. Further, the output device may be configured by using a device that prints (prints) an image or characters on a sheet. For example, the output device can be configured by using an inkjet printer, a laser printer, or the like. Further, the output device may be configured by using a device that converts characters into voice and outputs the characters. In this case, the output device can be configured by using a voice synthesizer and a voice output device (speaker). The output device may be configured by using a light emitting device such as an LED. The output unit 203 may transmit the estimation result to another information processing device via the communication device provided in the estimation device 200. The output unit 203 may be an output device configured integrally with the estimation device 200.

The position information storage unit 204 is configured by using a storage device such as a magnetic hard disk device or a semiconductor storage device. The position information storage unit 204 stores a plurality of position information. The position information recorded in the position information storage unit 204 is transmitted from the terminal device 100.

FIG. 4 is a diagram showing a specific example of the position information of the embodiment. According to FIG. 4, the position information indicates three types of information: the terminal identifier, the terminal position, and the time. Since the terminal identifier, the terminal position, and the time have already been explained, the description thereof will be omitted.

According to the position information shown in FIG. 4, the terminal identifier is “AD0000001”, the terminal position is “Location”, and the time is “2019/8/22 12:05:12”. Therefore, the position information is the position information generated by the terminal device 100 identified by the terminal identifier "AD00001", and the terminal device 100 sets the terminal position at 12:05:12 on August 22, 2019. You can see that it was acquired. Further, it can be seen that the terminal device 100 was in the "Location" position as the terminal position.

Returning to FIG. 3, the description of the estimation device 200 will be continued. The transaction information storage unit 205 is configured by using a storage device such as a magnetic hard disk device or a semiconductor storage device. The transaction information storage unit 205 stores a plurality of transaction information. The transaction information indicates the content of the transaction performed by the owner of the terminal device 100. The transaction information may be, for example, information regarding a receipt of a transaction performed at a store. The transaction information indicates the place where the transaction was made and the facility where the transaction was made. The transaction may be, for example, shopping at a retail store, shopping at a car dealer, or a medical examination at a hospital. The transaction may be any act as long as it is performed by the owner of the terminal device 100. The transaction information is transmitted from the transaction information management device 300. The transaction information management device 300 stores transaction information in advance. The transaction information management device 300 is managed by, for example, a company that sells transaction information.

FIG. 5 is a diagram showing a specific example of transaction information of the embodiment. According to FIG. 5, the transaction information shows four pieces of information: a terminal identifier, a facility identifier, a transaction content, and a transaction time. Since the terminal identifier has already been explained, the description thereof will be omitted. The facility identifier is information that can uniquely identify the facility where the transaction was conducted. The facility identifier indicates, for example, a facility where transactions are conducted, such as a retail store, an automobile dealer, a commercial facility, or a hospital. The facility identifier may be any information as long as it does not overlap with other facility identifiers. The transaction content indicates the content of the transaction performed by the owner of the terminal device 100. The transaction content may indicate the amount paid by the owner of the terminal device 100. The transaction content may indicate a product purchased by the owner of the terminal device 100. The transaction time indicates the time of the transaction performed by the owner of the terminal device 100.

According to the transaction information shown in FIG. 5, the terminal identifier is "AD00001", the facility identifier is "shop0001", the transaction content is "bread 200 yen", and the transaction time is "2019/8/22 12:12:31". .. Therefore, the transaction information indicates the content of the transaction performed by the terminal device 100 identified by the terminal identifier "AD00001". The transaction information indicates that the facility identifier is a transaction made at the facility identified by "shop0001". The transaction information indicates that the owner of the terminal device 100 purchased bread for 200 yen. Transaction information indicates that the transaction took place on August 22, 2019 at 12:12:31.

Returning to FIG. 3, the description of the estimation device 200 will be continued. The facility information storage unit 206 is configured by using a storage device such as a magnetic hard disk device or a semiconductor storage device. The facility information storage unit 206 stores facility information. Facility information is information about the facility where the transaction takes place. Facility information indicates information about the location and scope of the facility where the transaction takes place.

FIG. 6 is a diagram showing a specific example of facility information of the embodiment. According to FIG. 6, the facility information shows four pieces of information: the facility identifier, the location, the radius, and the number of facilities. Since the facility identifier has already been explained, the description will be omitted. The location indicates the location of the facility identified by the facility identifier. The location represents a place where the owner of the terminal device 100 and the facility identified by the facility identifier can conduct a transaction. The location may be, for example, information indicating the location of a facility such as a retail store, an automobile dealer, a commercial facility, or a hospital. The location is pre-specified depending on the facility identified by the facility identifier. The location may indicate one of the doorways of the facility. The location may indicate a predetermined position inside the facility, such as the center of the facility or the center of gravity. The location may be indicated by, for example, latitude / longitude information. The radius represents the radius of the circle centered on the trading place. The radius is specified in advance. Different values are specified for the radius depending on the size of the facility identified by the facility identifier. The radius may be set to be the same area as the area of the facility, for example. The radius may be set so that the facility fits inside the circle. The radius may be set so that the circle fits inside the facility. The number of facilities indicates the number of facilities in the vicinity of the facility identified by the facility identifier. The periphery may be within a predetermined range, for example, within 500 meters from the outer edge of the area indicating the facility.

According to the facility information shown in FIG. 6, the facility identifier is “shop0001”, the location is “P”, the radius is “R”, and the number of facilities is “N”. Therefore, the facility information indicates that the information is about the facility identified by the facility identifier "shop00001". The facility indicates that it is located at location "P". The facility indicates that it has a radius of "R". Indicates that there are "N" other facilities around the facility.

Returning to FIG. 3, the description of the estimation device 200 will be continued. The estimation means storage unit 207 is configured by using a storage device such as a magnetic hard disk device or a semiconductor storage device. The estimation means storage unit 207 stores the estimation means. The estimation means is information used to estimate the number of visitors to the facility.

The control unit 208 controls the operation of each unit of the estimation device 200. The control unit 208 is executed by a device including a processor such as a CPU and a RAM. By executing the estimation program, the control unit 208 functions as an information acquisition unit 281, an estimation means generation unit 282, and an estimation unit 283.

The information acquisition unit 281 acquires a plurality of predetermined information from the outside via the network 400. For example, the information acquisition unit 281 acquires the position information transmitted by the terminal device 100. The information acquisition unit 281 records the acquired position information in the position information storage unit 204. In addition, the information acquisition unit 281 may request transaction information from the transaction information management device 300. In this case, the information acquisition unit 281 acquires the transaction information stored in the transaction information management device 300. The information acquisition unit 281 records the acquired transaction information in the transaction information storage unit 205.

The estimation means generation unit 282 generates an estimation means for estimating the number of people who have visited the facility identified by the facility identifier. The estimation means may be, for example, a mathematical formula for estimating the number of people who have visited the facility. Hereinafter, a specific description will be given. The estimation means generation unit 282 determines a facility identifier indicating a predetermined facility. A predetermined facility is a facility for which the number of people who have visited the facility is estimated. The predetermined facility may be determined by the estimation means generation unit 282, or may be received and determined via the input unit 202. Next, the estimation means generation unit 282 acquires facility information indicating the determined facility identifier from the facility information storage unit 206. The estimation means generation unit 282 calculates the area indicating the facility based on the location and the radius indicated by the acquired facility information. Specifically, the estimation means generation unit 282 calculates the inside of the circle indicated by the radius value as the area indicating the facility, with the location as the center of the circle. The estimation means generation unit 282 acquires the position information in which the terminal position is inside the calculated area from the position information storage unit 204. It is determined that the terminal device 100 identified by the terminal identifier indicated by the acquired location information has visited a predetermined facility. The estimation means generation unit 282 acquires transaction information indicating the determined facility identifier from the transaction information storage unit 205. The estimation means generation unit 282 may be configured to acquire position information and transaction information included in a predetermined time. The defined time may be, for example, a date designated via the input unit 202. With this configuration, the estimation means generation unit 282 can estimate how many people visited on the designated day. The set time is not limited to the day. The defined time may be one week or two weeks.

The estimation means generation unit 282 calculates the correct answer rate based on the acquired position information and transaction information. The correct answer rate is a value indicating the ratio of the number of terminal identifiers possessed by the terminal device 100 actually visiting the predetermined facility to the number of terminal identifiers possessed by the terminal device 100 determined to have visited the predetermined facility. Actually visiting a predetermined facility means that, for example, in the facility, there is transaction information that has been traded between the time indicated by the acquired location information or the time indicated by the location information. It may be several minutes before and after the time indicated by the position information, or it may be several tens of minutes. Therefore, the estimation means generation unit 282 determines that the terminal device 100 identified by the terminal identifier indicated by the acquired transaction information is the terminal device 100 that actually visited a predetermined facility. The estimation means generation unit 282 counts the number of matching terminal identifiers of the location information determined to have visited a predetermined facility and the terminal identifiers of the acquired transaction information. The estimation means generation unit 282 uses the counted number as the number of terminal identifiers that have made a transaction at the facility among the terminal identifiers that have visited the facility. The estimation means generation unit 282 calculates the correct answer rate based on the following mathematical formula (1). The numerator of the formula (1) is the number of terminal identifiers that have made a transaction at the facility among the terminal identifiers that have visited the facility. The denominator of the formula (1) is the number of terminal identifiers that have traded at the facility. The correct answer rate is a specific example of statistical information. Statistical information is information about the number of people who have visited a given facility.

The estimation means generation unit 282 calculates the coverage rate based on the acquired position information and transaction information. The coverage rate is a value indicating the ratio of the identifier possessed by the terminal device 100 determined to have visited a predetermined facility among the terminal identifier possessed by the acquired transaction information. Specifically, the coverage rate is expressed by the following mathematical formula (2). The numerator of the formula (2) is the number of terminal identifiers determined to have visited the facility among the terminal identifiers that have traded at the facility. The denominator of the formula (2) is the number of terminal identifiers that have traded at the facility. Here, the numerator value of the formula (1) and the numerator value of the formula (2) have the same value. The coverage rate is a specific example of coverage information.

The estimation means generation unit 282 calculates the correct answer rate and the coverage rate for all or a predetermined number of facility identifiers stored in the facility information storage unit 206. The estimation means generation unit 282 generates an estimation means when all or a predetermined number of correct answer rates and coverage rates are calculated.

First, the estimation means generation unit 282 generates the correct answer rate estimation means. The correct answer rate estimation means is a means that can estimate the correct answer rate based on the number of facilities. The correct answer rate estimation means is, for example, an approximate expression (hereinafter, referred to as “correct answer rate approximate expression”) showing the relationship between the correct answer rate and the number of facilities. Hereinafter, the correct answer rate estimation means will be described as an approximate correct answer rate equation. The estimation means generation unit 282 generates an approximation formula for the correct answer rate based on the number of facilities in the facility information indicated by the facility identifier and the correct answer rate. The estimation means generation unit 282 may generate a correct answer rate approximation formula using a known formula. The estimation means generation unit 282 records the generated correct answer rate approximation formula (correct answer rate estimation means) in the estimation means storage unit 207.

FIG. 7 is a diagram showing a specific example of a scatter plot showing the relationship between the correct answer rate of the embodiment and the number of facilities. The vertical axis of FIG. 7 shows the correct answer rate. The horizontal axis in FIG. 7 shows the number of facilities. The number of facilities in FIG. 7 is the number of facilities within a predetermined range such as within 500 meters from the outer edge of the area indicating the facilities. FIG. 7 includes a curve 10 and a curve 11. The scatter plot shown in FIG. 7 is a scatter plot in which the correct answer rate of the facility identified by the facility identifier and the number of facilities indicated by the facility information identified by the facility identifier are plotted. Curves 10 and 11 show approximate curves generated based on the plotted scatter plot. The approximate curve is a curve related to the correct answer rate approximate expression generated by the estimation means generation unit 282. The estimation means generation unit 282 may generate different correct answer rate approximation formulas as in the curve 10 and the curve 11. Although the accuracy rate approximation formula shown in FIG. 7 has been described as being a curved line, it may be a formula representing a straight line.

According to FIG. 7, it can be seen that the correct answer rate decreases as the number of facilities increases. The reason for this is that as the number of other facilities increases in the vicinity of the facility, the number of owners of the terminal device 100 that visits the other facility increases, and it is more likely that the owner of the terminal device 100 visits the facility but is determined to have visited the facility. Because. Also, if there are no other facilities around the facility (for example, if there is only one facility on the top of a mountain or on a vast grassland), people who visit the area are aiming for that facility. You can judge. Therefore, it is considered that the owner of the terminal device 100 is visiting the facility. Therefore, the correct answer rate is expected to increase. Further, when affected by the GPS error included in the terminal device 100, the possibility that it is determined that the user has visited the facility even though he / she has visited another facility is further increased.

Next, the estimation means generation unit 282 generates the coverage rate estimation means. The coverage rate estimation means is a means that can estimate the coverage rate based on the number of facilities. The coverage rate estimation means is, for example, an approximate expression (hereinafter, referred to as “coverage rate approximate expression”) showing the relationship between the coverage rate and the radius. Hereinafter, the coverage rate estimation means will be described as a coverage rate approximation formula. The estimation means generation unit 282 generates a coverage rate approximation formula based on the radius of the facility information indicated by the facility identifier and the coverage rate. The estimation means generation unit 282 may generate a coverage rate approximation formula using a known formula. The estimation means generation unit 282 records the generated coverage rate approximation formula (coverage rate estimation means) in the estimation means storage unit 207.

FIG. 8 is a diagram showing a specific example of a scatter diagram showing the relationship between the coverage rate and the radius of the embodiment. The vertical axis of FIG. 8 shows the coverage rate. The horizontal axis of FIG. 8 indicates the radius. The radius is the radius that defines the area that indicates the facility. FIG. 8 includes a straight line 20. The scatter plot shown in FIG. 8 is a scatter plot in which the coverage rate of the facility identified by the facility identifier and the radius indicated by the facility information identified by the facility identifier are plotted. The straight line 20 shows an approximate straight line generated based on the plotted scatter plot. The approximate straight line is a straight line related to the coverage rate approximation formula generated by the estimation means generation unit 282. The estimation means generation unit 282 may generate different coverage approximation equations as in the straight line 20. Although the coverage rate approximation formula shown in FIG. 8 has been described as being a straight line, it may be a formula representing a curve.

According to FIG. 8, it can be seen that the coverage rate is a constant value regardless of the radius. Therefore, it is considered that the coverage rate can be set to a certain level regardless of the number of facilities in the vicinity of the facility if the radius of the facility can be set appropriately. For example, if the radius of the facility is made 10 times the actual radius, it is determined that all the people who came near the facility visited the facility, so that the coverage rate is considered to increase. It is considered that the coverage rate does not increase as the accuracy of the measurement position indicated by the position information improves (for example, the number of GPS satellites increases). Further, as for the coverage rate, it is conceivable that the coverage rate can be increased or decreased by shortening or lengthening the acquisition interval of the position information.

There are hundreds of position information per day, and the coverage rate is calculated by the terminal device 100, which can measure the movement trajectory of the terminal device 100 in units of several meters, and the number of position information per day is When the coverage rate is calculated with the terminal device 100 having only a few cases, it is considered that the calculated coverage rate deviates. Similarly, regarding the correct answer rate, the number of position information including errors increases in proportion to the number of position information, so that the correct answer rate may deviate.

FIG. 9 is a diagram showing a specific example of a scatter diagram showing the relationship between the correct answer rate of the embodiment and the number of position information per day for one person who visited the facility. The scatter plot shown in FIG. 9 is a scatter plot plotting the number of position information per day for each person who visited the facility and the correct answer rate calculated for the facility. The vertical axis of FIG. 9 shows the correct answer rate. The horizontal axis of FIG. 9 shows the number of location information per day for each person who visits the facility. According to the scatter plot shown in FIG. 9, it can be seen that the correct answer rate is approximately 0.04 to 0.07 regardless of the number of position information. Therefore, it can be seen that the correct answer rate is a constant value regardless of the number of position information, although it varies depending on the magnitude of the error of the terminal position indicated by the position information.

FIG. 10 is a diagram showing a specific example of a scatter diagram showing the relationship between the coverage rate of the embodiment and the number of position information per day for one person who visited the facility. The scatter plot shown in FIG. 10 is a scatter plot plotting the number of position information per day for each person who visited the facility and the coverage rate calculated for the facility. The vertical axis of FIG. 10 shows the coverage rate. The horizontal axis of FIG. 10 shows the number of location information per day for each person who visits the facility. According to the scatter plot shown in FIG. 10, the coverage rate sharply increases until the number of position information is about 100. The coverage rate becomes a constant value at about 0.7 when the number of position information exceeds 200. Therefore, the estimation system 1 can further improve the estimation accuracy by considering the number of position information when estimating the number of people who have visited the facility.

Therefore, the estimation means generation unit 282 may be configured to generate a predetermined correction coefficient. The predetermined correction coefficient is a coefficient based on the number of daily position information per owner of the terminal device 100. The predetermined correction factor is used to correct the number of people estimated to have visited the facility. The estimation means generation unit 282 records the generated predetermined correction coefficient in the estimation means storage unit 207. The estimation means generation unit 282 is a specific example of the calculation unit.

The estimation unit 283 estimates the number of people who have visited a predetermined facility based on the generated estimation means. Specifically, the estimation unit 283 receives the facility identifier. The estimation unit 283 may accept the facility identifier via the input unit 202. The estimation unit 283 may use any means as long as it can determine the facility to be estimated. The estimation unit 283 counts the number of terminal identifiers of the terminal device 100 that has visited the facility identified by the received facility identifier. Specifically, the estimation unit 283 acquires the facility information having the received facility identifier from the facility information storage unit 206. The estimation unit 283 calculates the area indicating the facility based on the location and the radius indicated by the facility information. The estimation unit 283 acquires position information having a terminal position indicating that it is inside the calculated area from the position information storage unit 204. The estimation unit 283 counts the number of terminal identifiers indicated by the acquired position information. At this time, the estimation unit 283 does not count the duplicate terminal identifiers.

Next, the estimation unit 283 estimates the estimated correct answer rate based on the number of facilities around the facility to be estimated and the correct answer rate estimating means. The estimated correct answer rate is the correct answer rate estimated by the correct answer rate estimating means. Specifically, the estimation unit 283 acquires the correct answer rate estimation means from the estimation means storage unit 207. The estimation unit 283 acquires the number of facilities from the acquired facility information. The estimation unit 283 estimates the estimated correct answer rate by inputting the acquired number of facilities into the correct answer rate estimating means.

Next, the estimation unit 283 estimates the estimated coverage rate based on the radius indicated by the facility information of the facility to be estimated and the coverage rate estimation means. The estimated coverage rate is the coverage rate estimated by the coverage rate estimation means. Specifically, the estimation unit 283 acquires the coverage rate estimation means from the estimation means storage unit 207. The estimation unit 283 acquires the radius from the acquired facility information. The estimation unit 283 estimates the estimated coverage rate by inputting the acquired radius into the coverage rate estimation means.

The estimation unit 283 estimates the number of people who have visited the facility (hereinafter referred to as "estimated number of people") based on the number of terminal identifiers determined to have visited the facility, the estimated correct answer rate, and the estimated coverage rate. Specifically, the estimation unit 283 estimates the estimated number of people using the following mathematical formula (3).

The estimation unit 283 determines the number of people who visited the facility (hereinafter referred to as "estimated number of people") based on the number of terminal identifiers determined to have visited the facility, the estimated correct answer rate, the estimated coverage rate, and the correction coefficient. You may estimate. Specifically, the estimation unit 283 estimates the estimated number of people using the following mathematical formula (4).

FIG. 11 is a flowchart showing a flow of processing for generating the estimation means of the embodiment.
The generation of the estimation means is executed at a predetermined timing. The predetermined timing may be once a day or once a month. Further, the predetermined timing may be the timing specified by the user of the estimation system 1. In FIG. 11, the estimation means will be described as being an accuracy rate approximation formula and a coverage rate approximation formula. The estimation means generation unit 282 of the estimation device 200 determines a facility identifier indicating a facility for which the number of people who have visited the facility is to be estimated (step S101). The estimation means generation unit 282 acquires position information indicating the terminal position indicating the inside of the area indicating the facility (step S102). Specifically, the estimation means generation unit 282 acquires facility information indicating the facility identifier from the facility information storage unit 206. The estimation means generation unit 282 calculates the area indicating the facility based on the location and the radius indicated by the facility information. The estimation means generation unit 282 acquires position information having a terminal position indicating that it is inside the calculated area from the position information storage unit 204. The estimation means generation unit 282 acquires transaction information indicating the determined facility identifier from the transaction information storage unit 205 (step S103).

The estimation means generation unit 282 calculates the correct answer rate based on the acquired position information, transaction information, and the mathematical formula (1) (step S104). The estimation means generation unit 282 calculates the coverage rate based on the acquired position information, transaction information, and the mathematical formula (2) (step S105). The estimation means generation unit 282 determines whether or not a predetermined number of correct answer rates and coverage rates have been calculated (step S106). When the estimation means generation unit 282 has not calculated a predetermined number of correct answer rates and coverage rates (step S106: NO), the process proceeds to step S101 to determine the next facility identifier.

When the estimation means generation unit 282 calculates a predetermined number of correct answer rates and coverage rates (step S106: YES), the estimation means generation unit 282 generates estimation means (step S107). Specifically, the estimation means generation unit 282 generates a correct answer rate approximation formula based on the number of facilities in the facility information indicated by the facility identifier and the correct answer rate. The estimation means generation unit 282 generates a coverage rate approximation formula based on the radius of the facility information indicated by the facility identifier and the coverage rate. The estimation means generation unit 282 records the generated accuracy rate approximation formula in the estimation means storage unit 207 (step S108). The estimation means generation unit 282 records the generated coverage rate approximation formula in the estimation means storage unit 207.

FIG. 12 is a flowchart showing a flow of processing for estimating the number of people who visited the facility of the embodiment. The estimation of the number of visitors to the facility is carried out at a predetermined timing. The predetermined timing may be once a day or once a month. Further, the predetermined timing may be the timing specified by the user of the estimation system 1. The estimation unit 283 of the estimation device 200 receives the facility identifier (step S201). The estimation unit 283 counts the number of terminal identifiers of the terminal device 100 that visited the facility identified by the received facility identifier (step S202).

Next, the estimation unit 283 estimates the estimated correct answer rate based on the number of facilities around the facility to be estimated and the correct answer rate estimating means (step S203). The estimation unit 283 estimates the estimated coverage rate based on the radius indicated by the facility information of the facility to be estimated and the coverage rate estimation means (step S204). The estimation unit 283 estimates the number of people who visited the facility based on the number of terminal identifiers determined to have visited the facility, the estimated correct answer rate, the estimated coverage rate, and the mathematical formula (3) (step S205).

In the estimation system 1 configured in this way, the estimation means generation unit 282 estimates the number of people visited by the owner of the terminal device 100 at the place where the transaction was made based on the position information and the transaction information. Generate means. The estimation unit 283 estimates the number of people who have visited a predetermined place based on the location information, the transaction information, and the estimation means. Therefore, the estimation system 1 can estimate the number of people who have visited a predetermined place with higher accuracy by using the transaction information.

In the above-described embodiment, the estimation means generation unit 282 is configured to calculate an approximate expression for determining the correct answer rate and the coverage rate as the estimation means, but is not limited thereto. For example, the estimation means generation unit 282 may be configured to generate estimation means based on a learning model generated by a predetermined machine learning algorithm. Hereinafter, a specific description will be given.

The estimation means generation unit 282 may be configured to generate, for example, a mathematical formula as shown in the following mathematical formula (5) as the estimation means. The estimation means generation unit 282 generates a learning model for determining each term shown in the mathematical formula (5). In the formula (5), the number of terminal identifiers determined to have visited the facility has already been explained, so the description thereof will be omitted.

The coefficient considering the number of surrounding facilities is a coefficient determined based on the number of other facilities around the facility. The estimation means generation unit 282 generates a peripheral facility number learning model based on predetermined teacher data and a predetermined machine learning algorithm. The peripheral facility number learning model generates a coefficient based on the number of facilities and the correct answer rate. The predetermined teacher data may be, for example, data in which the number of other facilities in the vicinity, the accuracy rate, and the coefficient are combined. The predetermined machine learning algorithm may be any known machine learning algorithm such as SGD (Stochastic Gradient Descent), random forest, linear regression, decision tree, or CNN (Convolutional Neural Network). The estimation means generation unit 282 records the generated peripheral facility number learning model as a generation means in the estimation means storage unit 207.

The coefficient considering the radius is a coefficient determined based on the radius that defines the area indicating the facility. The estimation means generation unit 282 generates a radius learning model based on predetermined teacher data and a predetermined machine learning algorithm. The radius learning model generates coefficients based on radius and coverage. The predetermined teacher data may be, for example, data in which a radius, a coverage rate, and a coefficient are combined. The predetermined machine learning algorithm may be any known machine learning algorithm such as SGD, random forest, linear regression, decision tree or CNN. The estimation means generation unit 282 records the generated radius learning model as a generation means in the estimation means storage unit 207.

The coefficient considering the number of logs per person is a coefficient determined based on the number of logs per person. The number of logs is, for example, the number of acquired location information. The estimation means generation unit 282 generates a log number learning model based on predetermined teacher data and a predetermined machine learning algorithm. The log number learning model generates a coefficient based on the number of logs per person, the correct answer rate, and the coverage rate. The predetermined teacher data may be, for example, data in which the number of logs per person, the correct answer rate, the coverage rate, and the coefficient are combined. The predetermined machine learning algorithm may be any known machine learning algorithm such as SGD, random forest, linear regression, decision tree or CNN. The estimation means generation unit 282 records the generated log number learning model as a generation means in the estimation means storage unit 207.

The estimation unit 283 determines a coefficient in consideration of the number of peripheral facilities based on the above-mentioned learning model of the number of peripheral facilities. The estimation unit 283 determines a coefficient in consideration of the radius based on the radius learning model described above. The estimation unit 283 determines a coefficient in consideration of the number of logs per person based on the above-mentioned log number learning model. The estimation unit 283 estimates the number of people who have visited the facility based on the number of terminal identifiers determined to have visited the facility and the determined coefficient. With this configuration, the estimation system 1 can estimate the number of people who have visited the facilities in all the other facilities by generating the learning model once. For this reason, it is possible to estimate the number of people who have visited a facility that is unlikely to lead to a transaction even if the facility is visited, or a facility for which transaction information does not exist.

The estimation device 200 may be implemented by using a plurality of information processing devices that are communicably connected via a network. In this case, each functional unit included in the estimation device 200 may be distributed and mounted in a plurality of information processing devices. For example, the estimation means generation unit 282 and the estimation unit 283 may be mounted on different information processing devices.

In the above-described embodiment, the transaction information has been described as indicating the content of the transaction, but the transaction information is not limited to the content of the transaction. For example, the transaction information may be information regarding the use of point cards or electronic money. The transaction information may be any information as long as it can be determined that the person has actually visited the facility.

Although the embodiments of the present invention have been described in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and includes designs and the like within a range that does not deviate from the gist of the present invention.

1 ... estimation system, 100 ... terminal device, 101 ... communication unit, 102 ... input unit, 103 ... output unit, 104 ... terminal identifier storage unit, 105 ... control unit, 151 ... terminal position acquisition unit, 152 ... position information generation unit , 153 ... Transmitter, 200 ... Estimator, 201 ... Communication, 202 ... Input, 203 ... Output, 204 ... Location information storage, 205 ... Transaction information storage, 206 ... Facility information storage, 207 ... Estimate Means storage unit, 208 ... control unit, 281 ... information acquisition unit, 282 ... estimation means generation unit, 283 ... estimation unit, 300 ... transaction information management device, 400 ... network

Claims (6)

An information acquisition unit that acquires a plurality of position information indicating the position of the terminal device and transaction information indicating the content of the transaction performed by the owner of the terminal device.
Based on the location information and the transaction information, the actual number of people who are estimated to have actually visited the predetermined facility where the transaction was performed and actually visited the facility shown in the transaction information and made the transaction. It relates to the number of people who visited the predetermined facility based on the calculated number of visitors who are estimated to have visited the predetermined facility with the terminal device based on the location information and the actual number of transactions. generates statistics, the number of terminal identifier indicating the number of terminal identifiers used in trade at the predetermined facility on the basis of the transaction information, the based on the actual transaction number, the terminal device at the predetermined facility A calculation unit that generates comprehensive information showing the percentage of transactions that were actually made using
The number of position information located facility within the region of interest of estimation processing of the plurality of position information including those not used for processing in the calculator, and the statistical information, and the coverage information, the based on an estimation unit that estimates a real transaction number which definitive facility to be the estimation process,
Equipped with an estimation system. The estimator is further based on the number of facilities near the predetermined facility region or the predetermined facility shown, to estimate the actual transaction number which definitive said predetermined property,
The estimation system according to claim 1. The estimator is further based on the number of the positional information per owner one of the terminal devices, to estimate the actual transaction number which definitive said predetermined property,
The estimation system according to claim 2. An information acquisition unit that acquires a plurality of position information indicating the position of the terminal device and transaction information indicating the content of the transaction performed by the owner of the terminal device.
Based on the location information and the transaction information, the actual number of people who are estimated to have actually visited the predetermined facility where the transaction was performed and actually visited the facility shown in the transaction information and made the transaction. It relates to the number of people who visited the predetermined facility based on the calculated number of visitors who are estimated to have visited the predetermined facility with the terminal device based on the location information and the actual number of transactions. generates statistics, the number of terminal identifier indicating the number of terminal identifiers used in trade at the predetermined facility on the basis of the transaction information, the based on the actual transaction number, the terminal device at the predetermined facility A calculation unit that generates comprehensive information showing the percentage of transactions that were actually made using
The number of position information located facility within the region of interest of estimation processing of the plurality of position information including those not used for processing in the calculator, and the statistical information, and the coverage information, the based on an estimation unit that estimates a real transaction number which definitive facility to be the estimation process,
An estimation device. An information acquisition step in which the estimation device acquires a plurality of position information indicating the position of the terminal device and transaction information indicating the content of the transaction performed by the owner of the terminal device.
Based on the location information and the transaction information, it is presumed that the estimation device actually visited the predetermined facility where the transaction was performed shown in the transaction information and actually visited the facility to perform the transaction. The actual number of people traded was calculated, and the number of visitors estimated to have visited the predetermined facility with the terminal device based on the location information and the number of people actually traded were used to visit the predetermined facility. generates statistics on the number of people, the number of terminal identifier indicating the number of terminal identifiers used in trade at the predetermined facility on the basis of the transaction information, based the on the actual transaction number, the predetermined facility A calculation step that generates comprehensive information indicating the percentage of transactions actually made using the terminal device in
Estimating apparatus, the number of position information located facility within the region of interest of estimation processing of the plurality of position information including those not used for processing in the calculation step, and the statistical information, the cover information, based on an estimation step of estimating the actual transaction number which definitive facility to be the estimation process,
An estimation method. A computer program for operating a computer as the estimation system according to any one of claims 1 to 3.

Images