Information processing device, control method, program and storage medium

Abstract

To provide an information processing device capable of estimating an individual facility visited by a user in a complex facility.SOLUTION: A server device 1 includes individual facility list acquisition means, facility visit history acquisition means, score calculation means, and estimation means. The individual facility list acquisition means acquires an individual facility list of facilities corresponding to a parking position of a vehicle. The facility visit history acquisition means acquires a facility visit history of a user of the vehicle. The score calculation means calculates, for each individual facility included in the individual facility list, a score indicating a degree of certainty that the user will visit the individual facility, based on the individual facility list and the facility visit history of the user. The estimation means estimates the individual facility visited this time by the user based on a comparison result of the score for each individual facility.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a system for analyzing destinations in a complex. [Background technology]

[0002] There are known technologies that analyze user behavior and provide advertisements and the like that are appropriate for the user. For example, Patent Document 1 discloses a technology that analyzes the tendency of facilities used by users based on the usage history of parking lots, and displays information about facilities that is useful to the user on an in-vehicle device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2012-068041 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the method of Patent Document 1, when a user uses a parking lot of a complex, it is not possible to identify which stores in the complex the user visited. Therefore, in the method of Patent Document 1, the accuracy of analysis of visiting trends decreases as the user uses the complex more frequently.

[0005] In view of the above-mentioned problems, an object of the present invention is to provide an information processing device capable of estimating individual facilities visited by a user in a complex. [Means for solving the problem]

[0006] The present invention relates to an information processing device, an individual facility list acquiring means for acquiring an individual facility list of individual facilities present in a facility corresponding to a parking position of the vehicle; a facility visit history acquisition means for acquiring a facility visit history of a user of the vehicle; a score calculation means for calculating, for each individual facility included in the individual facility list, a score indicating a likelihood that the user will visit the individual facility, based on the individual facility list and the user's facility visit history; an estimation means for estimating an individual facility currently visited by the user based on a comparison result of the scores for each individual facility; The present invention is characterized in that the information processing device comprises:

[0007] The invention described in the claims is a control method executed by an information processing device, an individual facility list acquisition step of acquiring an individual facility list of individual facilities present in a facility corresponding to a parking position of the vehicle; a facility visit history acquisition step of acquiring a facility visit history of a user of the vehicle; a score calculation step of calculating, for each individual facility included in the individual facility list, a score indicating a likelihood that the user will visit the individual facility based on the individual facility list and the facility visit history of the user; an estimation step of estimating an individual facility currently visited by the user based on a comparison result of the scores for each individual facility; The control method is characterized by having the following features.

[0008] The claimed invention is a program executed by a computer, an individual facility list acquiring means for acquiring an individual facility list of individual facilities present in a facility corresponding to a parking position of the vehicle; a facility visit history acquisition means for acquiring a facility visit history of a user of the vehicle; a score calculation means for calculating, for each individual facility included in the individual facility list, a score indicating a likelihood that the user will visit the individual facility, based on the individual facility list and the user's facility visit history; The program causes a computer to function as an estimation means for estimating the individual facility that the user has currently visited, based on the comparison result of the scores for each individual facility. [Brief description of the drawings]

[0009] [Figure 1] 1 illustrates an example of the configuration of a destination analysis system according to an embodiment. [Diagram 2] 2 illustrates an example of a schematic configuration of a server device. [Diagram 3] 2 shows an example of a schematic configuration of an in-vehicle device. [Figure 4] An example of a visit history is shown below. [Diagram 5] An example of a layout plan of individual facilities within a complex is shown below. [Figure 6] 1 is a flowchart showing a processing procedure according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] In one preferred embodiment of the present invention, an information processing device includes an individual facility list acquisition means for acquiring an individual facility list of individual facilities present in a facility corresponding to the parking position of a vehicle, a facility visit history acquisition means for acquiring a facility visit history of a user of the vehicle, a score calculation means for calculating, for each individual facility included in the individual facility list based on the individual facility list and the facility visit history of the user, a score indicating the likelihood that the user will visit the individual facility, and an estimation means for estimating the individual facility currently visited by the user based on a comparison result of the scores for each individual facility.

[0011] The information processing device described above can estimate individual facilities visited by a user in a complex. This makes it possible to accumulate the facility visit history of the user and to improve the accuracy of user analysis using the facility visit history.

[0012] In one aspect of the information processing device, the facility is a complex facility that combines a plurality of individual facilities. With this aspect, the information processing device can estimate individual facilities that the user has visited in the complex facility.

[0013] In another aspect of the information processing device, the information processing device includes a scenery image acquisition means for acquiring a scenery image of an external scenery including the user from the vehicle, and an entrance estimation means for estimating an entrance of a complex facility to which the user headed from the scenery image, and the score calculation means assigns a predetermined weight to the score of each individual facility located within a predetermined range from the entrance. With this aspect, the information processing device can more accurately estimate the individual facilities visited by the user.

[0014] In another aspect of the information processing device, the information processing device includes a visit date and time acquisition means for acquiring a date and time of a current visit of the user to the facility, the facility visit history of the user includes a date and time of visit to the visited facility, and the score calculation means selects a history of a visit date and time that matches or is similar to the date and time of the current visit from the facility visit history of the user, and assigns a predetermined weight to the visit score of each individual facility based on the selected history. With this aspect, the information processing device can more accurately estimate the individual facilities visited by the user.

[0015] In another aspect of the information processing device, the information processing device includes an interior image acquisition means for acquiring an interior image of the vehicle, and a passenger estimation means for estimating a passenger of the vehicle from the interior image, wherein the facility visit history of the user includes the passenger, and the score calculation means selects a history having the same passenger as the current passenger from the facility visit history of the user, and assigns a predetermined weight to the visit score of each individual facility based on the selected history. With this aspect, the information processing device can more accurately estimate the individual facilities visited by the user.

[0016] In another aspect of the information processing device, the information processing device includes a stay time acquisition means for acquiring a stay time of the vehicle at the parking position, the facility visit history of the user includes a stay time at each individual facility, and the estimation means estimates one or more individual facilities as the individual facility visited this time by the user based on the score and the stay time for each individual facility. With this aspect, the information processing device can estimate the individual facility even if the user has visited multiple individual facilities.

[0017] In another aspect of the information processing device, the device includes an output means for outputting the individual facility estimated by the estimation means, and a correct / incorrect acquisition means for acquiring from the user whether the estimated individual facility is correct, and if the estimated individual facility is not correct, the estimation means further estimates a next candidate individual facility, and if the estimated individual facility is correct, the estimation means determines the estimated individual facility as the individual facility visited this time by the user. With this aspect, the information processing device can confirm whether the estimated individual facility is correct.

[0018] In another preferred embodiment of the present invention, a control method executed by an information processing device includes an individual facility list acquisition step of acquiring an individual facility list of individual facilities present in a facility corresponding to a parking position of a vehicle, a facility visit history acquisition step of acquiring a facility visit history of a user of the vehicle, a score calculation step of calculating, for each individual facility included in the individual facility list based on the individual facility list and the facility visit history of the user, a score indicating a likelihood that the user will visit the individual facility, and an estimation step of estimating an individual facility currently visited by the user based on a comparison result of the scores for each individual facility. By executing this control method, the information processing device can estimate the individual facilities visited by the user in a complex facility.

[0019] In yet another embodiment of the present invention, a program executed by a computer causes the computer to function as an individual facility list acquisition means for acquiring an individual facility list of individual facilities present in a facility corresponding to the parking position of a vehicle, a facility visit history acquisition means for acquiring a facility visit history of a user of the vehicle, a score calculation means for calculating, for each individual facility included in the individual facility list based on the individual facility list and the facility visit history of the user, a score indicating the likelihood that the user will visit the individual facility, and an estimation means for estimating an individual facility currently visited by the user based on a comparison result of the scores for each individual facility. By executing this program, the computer of the information processing device can estimate the individual facilities visited by the user in a complex facility. Preferably, the program is stored in a storage medium. EXAMPLES

[0020] Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings.

[0021] <System configuration> [Overall configuration] 1 shows an example of the configuration of a destination analysis system according to an embodiment. The destination analysis system includes a server device 1 and an on-board device 2 installed in a vehicle. The server device 1 and the on-board device 2 communicate data with each other via a communication network 3 such as the Internet or a dedicated communication network. The server device 1 is an example of an "information processing device."

[0022] The vehicle-mounted device 2 is a terminal device that moves with the vehicle. Hereinafter, the vehicle on which the vehicle-mounted device 2 is mounted is also referred to as a "target vehicle." In response to a request from the server device 1, the vehicle-mounted device 2 transmits to the server device 1 a driving history, scenery images (moving images) taken of the outside of the target vehicle, and interior images (moving images) taken of the interior of the target vehicle. The driving history includes date and time, and position information of the target vehicle at that date and time.

[0023] The server device 1 receives the driving history of the target vehicle from the vehicle-mounted device 2, and estimates individual facilities (hereinafter, also referred to as "stores") visited by the user who is the driver of the target vehicle. In particular, the server device 1 of this embodiment is characterized in that, when the user's destination is a complex facility, it can estimate which stores in the complex facility the user visited.

[0024] [Server device] 2 shows an example of a schematic configuration of the server device 1. The server device 1 mainly includes a communication unit 11, a storage unit 12, and a control unit 13. The elements in the server device 1 are connected to each other via a bus line 10.

[0025] The communication unit 11 performs data communication with an external device such as the vehicle-mounted device 2 under the control of the control unit 13. For example, the communication unit 11 may receive map data for updating a map DB (DataBase) 12b from a map management server (not shown).

[0026] The storage unit 12 is configured with various types of memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), and a non-volatile memory (including a hard disk drive, a flash memory, etc.). The storage unit 12 stores a program 12a for the server device 1 to execute a predetermined process. The storage unit 12 is also used as a working memory for the control unit 13. The program executed by the server device 1 may be stored in a storage medium other than the storage unit 12.

[0027] The storage unit 12 also stores a map DB 12b, a walking history 12c, and a facility visit history 12d. The map DB 12b stores various data necessary for route guidance. The map DB 12b is data necessary for map display based on a predetermined position such as the current position of the target vehicle. The map DB 12b is a database including, for example, road data that represents a road network by a combination of nodes and links, and facility data that indicates facilities that are candidates for destinations, stopovers, or landmarks. The map DB 12b may be updated based on information received by the communication unit 11 from a map management server under the control of the control unit 13. The walking history 12c stores a walking history received from a user terminal such as a smartphone. The walking history includes date and time and the user's location information at the date and time. Therefore, in a situation where location information can be obtained from a smartphone or the like, it is possible to obtain the facility visit history of the user even if the store is in a complex. The server device 1 can also obtain the visit history of a single store that does not belong to a complex based on the location information of the target vehicle and the map DB 12b. The facility visit history 12d records the facility visit history of the user based on these.

[0028] The control unit 13 includes a central processing unit (CPU), a graphics processing unit (GPU), etc., and controls the entire server device 1. In addition, the control unit 13 executes a program stored in the storage unit 12 to perform an estimation process of a visited store.

[0029] Note that the configuration of the server device 1 shown in Fig. 2 is an example, and various changes may be made to the configuration shown in Fig. 2. For example, instead of the map DB 12b, the walking history 12c, and the facility visit history 12d being stored in the memory unit 12, the control unit 13 may receive information from an external device (not shown) via the communication unit 11.

[0030] [In-vehicle device] 3 shows an example of a schematic configuration of the vehicle-mounted device 2. The vehicle-mounted device 2 mainly includes a communication unit 21, a storage unit 22, an input unit 23, a control unit 24, a sensor group 25, a display unit 26, and a sound output unit 27. The elements in the vehicle-mounted device 2 are connected to each other via a bus line 20.

[0031] The communication unit 21 performs data communication with an external device such as the server device 1 under the control of the control unit 24.

[0032] The storage unit 22 is configured with various types of memory such as RAM, ROM, and non-volatile memory (including a hard disk drive, a flash memory, etc.). The storage unit 22 stores programs for the vehicle-mounted device 2 to execute predetermined processes. The above-mentioned programs may include application programs for making calls. The storage unit 22 is also used as a working memory for the control unit 24. The programs executed by the vehicle-mounted device 2 may be stored in a storage medium other than the storage unit 22.

[0033] The input unit 23 is a button, a touch panel, a remote controller, a voice input device, etc. that the user operates. The display unit 26 is a display or the like that displays information based on the control of the control unit 24. The sound output unit 27 is a speaker or the like that outputs sound based on the control of the control unit 24.

[0034] The control unit 24 includes a CPU, a GPU, and the like, and controls the entire in-vehicle device 2. The processing executed by the control unit 24 is not limited to being realized by software using a program, but may be realized by any combination of hardware, firmware, and software. The processing executed by the control unit 24 may be realized by using an integrated circuit programmable by a user, such as an FPGA (Field-Programmable Gate Array) or a microcomputer. In this case, the program executed by the control unit 24 in this embodiment may be realized by using this integrated circuit.

[0035] The sensor group 25 includes various sensors that perform sensing related to the state of the target vehicle or the environment outside the vehicle. The sensor group 25 includes an exterior camera 51, an interior camera 52, and a vehicle behavior detector 53.

[0036] The exterior camera 51 is one or more cameras that capture images of the outside of the target vehicle, such as the area in front of the target vehicle, and generates images (also called "landscape images") captured at predetermined time intervals. The interior camera 52 is a camera that captures images of the interior of the target vehicle, and generates images (also called "interior images") captured at predetermined time intervals. The vehicle behavior detector 53 generates detection signals that indicate the behavior of the target vehicle, such as the current position, vehicle speed, acceleration, steering angle, etc. The vehicle behavior detector 53 includes, for example, a Global Navigation Satellite System (GNSS) receiver, a gyro sensor, an Inertial Measurement Unit (IMU), a vehicle speed sensor, an acceleration sensor, a steering angle sensor, etc.

[0037] In addition, the sensor group 25 may include various external sensors (including cameras, lidars, radars, ultrasonic sensors, infrared sensors, sonar, etc.) and internal sensors in addition to the exterior camera 51, the interior camera 52, and the vehicle behavior detector 53.

[0038] The configuration of the vehicle-mounted device 2 shown in Fig. 3 is an example, and various modifications may be made to the configuration shown in Fig. 3. For example, at least one of the input unit 23, the display unit 26, and the sound output unit 27 may be provided in the target vehicle as an external device of the vehicle-mounted device 2, and may supply the generated signal to the vehicle-mounted device 2. Furthermore, at least some of the sensors in the sensor group 25 may be sensors provided in the target vehicle. In this case, the vehicle-mounted device 2 may acquire information output by the sensors provided in the target vehicle from the target vehicle based on a communication protocol such as CAN (Controller Area Network).

[0039] In the above configuration, the control unit 13 is an example of an individual facility list obtaining means, a facility visit history obtaining means, a score calculating means, and an estimating means.

[0040] [Method of estimating visited stores] Next, a method for estimating the visited stores in a complex will be described. With this estimation method, even in a situation where location information cannot be acquired from a user terminal such as a smartphone, it is possible to estimate the stores visited by the user in the complex when the user visits the complex by vehicle.

[0041] (Visiting a complex facility) First, the server device 1 judges whether or not the user has visited the complex facility based on the driving history of the target vehicle and the position information of the parking lot of the complex facility. Specifically, when the server device 1 detects that the target vehicle has been parked in the parking lot of the complex facility for a predetermined time TH1 or more, it judges that the user has visited the complex facility. The server device 1 can acquire the driving history of the target vehicle from the vehicle-mounted device 2. The server device 1 can also acquire the position information of the parking lot of the complex facility from the map DB 12b.

[0042] (Getting a list of individual facilities) Next, when the server device 1 determines that the user has visited the complex facility, it acquires an individual facility list of the complex facility. The individual facility list is, for example, a list that links store names with store types. The server device 1 may store the individual facility list of the complex facility in advance in the storage unit 12, and acquire the individual facility list of the complex facility from the storage unit 12. The server device 1 may also acquire the individual facility list of the complex facility by performing data communication with an external device via the communication unit 11.

[0043] (Acquisition of facility visit history) Furthermore, when the server device 1 determines that the user has visited a complex, it extracts the facility visit history of the user from the facility visit history 12d. Fig. 4 shows an example of the facility visit history of a specific user. The facility visit history in Fig. 4 stores the user name, passengers, visit date and time, facility type, facility name, store name, and store type in association with the user ID assigned to each user.

[0044] "User name" indicates the name of the user who is the driver of the target vehicle. "Passenger" indicates the name of a passenger other than the user. The server device 1 can detect passengers from the in-vehicle image of the in-vehicle device 2. For example, the server device 1 detects passengers from the in-vehicle image using a pre-prepared image recognition model. This image recognition model is a machine learning model constructed by performing machine learning using human images as learning data.

[0045] "Facility type" indicates whether the facility visited is a complex or not. In Figure 4, "complex" indicates a complex that combines multiple facilities. "Standalone" indicates a standalone store that does not belong to a complex.

[0046] "Facility name" indicates the name of a complex. "Store name" indicates the name of a store. For example, record 41 in FIG. 4 indicates that the user visited "XX Shop" in "XX SC (shopping center)."

[0047] "Store type" indicates the type of business of the store. In FIG. 4, store types are shown as fashion, miscellaneous goods, food and drink, etc. Store types may be further classified. For example, fashion may be further classified into men's fashion and women's fashion, and food and drink may be further classified into Japanese food, Western food, cafe, ramen, etc.

[0048] (Visit score settings) Next, the server device 1 sets a visit score indicating the probability of a user's visit for each store in the complex.

[0049] The server device 1 determines whether the user has visited the same complex in the past based on the walking history of the user. Note that the server device 1 can acquire the walking history of the user from the walking history 12c.

[0050] If the user has visited the same complex facility in the past, the server device 1 sets a visit score for each store based on the user's visit history to the complex facility. Specifically, the server device 1 refers to the user's facility visit history and extracts records that include the complex facility. The server device 1 then calculates the visit frequency for each store type based on the extracted records. For example, if the server device 1 extracts 50 records, of which 10 are records of the store type "food and drink", the visit frequency for restaurants is 0.2. The server device 1 then sets a visit score for each store based on the visit frequency for each store type. For example, the server device 1 sets the visit score for a store of the store type "food and drink" to 0.2.

[0051] On the other hand, if the user has not visited the same complex facility in the past, the server device 1 sets the visit score of each store based on the user's visit history to the single store. Specifically, the server device 1 refers to the user's facility visit history and extracts records whose facility type is "single" and whose store type matches the store type included in the individual facility list of the complex facility. For example, in FIG. 4, when the user visits a new complex facility and the store types included in the individual facility list of the complex facility are fashion and food and drink, the server device 1 extracts records 42 and 46 from the user's facility visit history. Then, the server device 1 calculates the visit frequency for each store type based on the extracted records. Then, the server device 1 sets the visit score for each store based on the visit frequency for each store type. Note that, if the user's facility visit history includes a visit history to a complex facility other than the complex facility visited this time, the server device 1 may also use that visit history to set the visit score for each store.

[0052] In addition, when the user has visited the same complex facility in the past, the server device 1 may set the visit score using the user's visit history to individual stores in addition to the facility visit history of the user to the complex facility. Specifically, the server device 1 calculates the visit frequency for each store type from the visit history to the complex facility, and calculates the visit frequency for each store type from the visit history to the individual stores. Then, the server device 1 sets the visit score for each store based on the visit frequency for each store type. At this time, the server device 1 assigns a predetermined weight W1 to the visit frequency calculated from the visit history of the complex facility. The predetermined weight W1 is a numerical value exceeding 1. For example, the server device 1 calculates the visit score (S1) of a store whose store type is a restaurant based on the visit frequency (F1) of the store type "restaurant" calculated from the visit history to the complex facility and the visit frequency (F2) of the store type "restaurant" calculated from the visit history to the individual stores. The visit score (S1) is calculated, for example, by the following formula. (S1) = (F1 × W1) + F2 (1)

[0053] (Decision on visiting stores) The server device 1 compares the visit scores of each store and estimates the store visited by the current user. For example, the server device 1 estimates that the store with the highest visit score is the store visited by the current user.

[0054] Furthermore, the server device 1 may reset the visit score of each store by assigning weights as follows to the visit score of each store, and estimate the stores visited by the user.

[0055] (1) Weight W2 according to the entrance If there is layout data of stores in a complex, the server device 1 may assign a predetermined weight W2 to stores close to the entrance the user headed for. FIG. 5 shows a layout map of individual facilities (stores) in the complex. The complex in FIG. 5 has two entrances (entrance A and entrance B), and the user is heading for entrance A. At this time, the server device 1 assigns a predetermined weight W2 to stores within a predetermined range from entrance A. The predetermined weight W2 is a numerical value of 1 or more. For example, the server device 1 multiplies the visit score of store B close to entrance A by the predetermined weight W2, and resets the visit score of store B.

[0056] The server device 1 can estimate the entrance to which the user headed from the scenery image (video) of the vehicle-mounted device 2. For example, the server device 1 acquires a scenery image immediately after the user gets off the vehicle-mounted device 2. Then, the server device 1 detects the user and his / her position from each frame of the scenery image using a previously prepared object detection model. Then, the server device 1 estimates the user's moving direction by tracking the detected user between frames. The above-mentioned object detection model is a machine learning model constructed by performing machine learning using images including objects and object position information as learning data.

[0057] (2) Weighting according to time period W3 The server device 1 may assign a predetermined weight W3 based on the day of the week and the time period (e.g., morning, afternoon, night). For example, the server device 1 refers to the user's facility visit history and extracts records having the same day of the week and time period as the day of the week and time period when the user visited the complex facility this time. The server device 1 then determines the store type that appears most frequently among the store types included in the extracted records as the store type with a high probability of being visited by the user. The server device 1 multiplies the visit score of the store of that store type by the predetermined weight W3 to reset the visit score.

[0058] (3) Weighting according to passengers W4 The server device 1 may assign a predetermined weight W4 based on the passenger of the target vehicle. For example, the server device 1 refers to the user's facility visit history and extracts records having the same passenger as the current passenger. Then, the server device 1 determines the store type that appears most frequently among the store types included in the extracted records as the store type with a high probability of being visited by the user. The server device 1 multiplies the visit score of the store of that store type by the predetermined weight W4 to reset the visit score.

[0059] (4) Weighting according to stay time W5 The server device 1 may assign a predetermined weight W5 based on the parking time in the parking lot of the complex. For example, the server device 1 acquires the parking time from when parking in the parking lot of the complex to when the vehicle leaves the parking lot based on the position information of the target vehicle as the current stay time in the complex. The server device 1 then refers to the facility visit history of the user, identifies a store type whose average stay time falls within a predetermined time range based on the current stay time, and resets the visit score by multiplying the visit score of the identified store type by the predetermined weight W5.

[0060] The above-described methods for setting the visit score and the method for setting the weight are merely examples, and the present invention is not limited to these.

[0061] The server device 1 may generate a record including the currently estimated visited store and register it in the facility visit history 12d. This allows the server device 1 to accumulate the facility visit history of the user even when the walking history cannot be acquired from the user terminal. The accumulated facility visit history can be used for user analysis, etc.

[0062] [Processing flow] Fig. 6 is an example of a flowchart showing the procedure of a process executed by the server device 1. The server device 1 executes the process of the flowchart shown in Fig. 6 at every predetermined time TH2. This process is realized by the control unit 13 shown in Fig. 2 executing a program prepared in advance.

[0063] First, the server device 1 acquires the driving history of the target vehicle from the vehicle-mounted device 2 at every predetermined time TH2. Then, the server device 1 determines whether or not the user has visited the complex facility based on the driving history of the target vehicle and the position information of the parking lot of the complex facility (step S101). If the server device 1 determines that the user has visited the complex facility (step S101: Yes), the server device 1 proceeds to the process of step S102. On the other hand, if the server device 1 determines that the user has not visited the complex facility (step S101: No), the process of the flowchart ends.

[0064] Next, the server device 1 acquires an individual facility list of the complex facility visited by the user and the user's facility visit history (step S102). Next, the server device 1 determines whether the user has visited the same complex facility in the past from the user's walking history (step S103). If the user has visited the same complex facility in the past (step S103: Yes), the server device 1 acquires a record including the complex facility (visit history of the complex facility) from the facility visit history (step S104). On the other hand, if the user has not visited the same complex facility in the past (step S103: No), the server device 1 proceeds to the process of step S105.

[0065] Next, the server device 1 refers to the facility visit history and acquires records whose store type matches the store type included in the individual facility list of the complex facility (visit history of the same store type as the individual facility list) (step S105). Next, the server device 1 sets a visit score for each store in the complex facility based on the individual facility list and the acquired visit history (step S106). Specifically, the server device 1 calculates the visit frequency for each store type based on the acquired visit history. Then, the server device 1 sets a visit score for each store included in the individual facility list based on the visit frequency for each store type.

[0066] Next, the server device 1 assigns a predetermined weight to the visit score of each store (step S107). For example, the server device 1 may assign a predetermined weight W2 to a store that is close to the entrance the user headed for. The server device 1 may also set a predetermined weight W3 based on the day of the week or time period when the user visited. The server device 1 may also set a predetermined weight W4 based on the passengers in the target vehicle. The server device 1 may also set a predetermined weight W5 based on the parking time of the target vehicle.

[0067] Next, the server device 1 compares the visit scores of each store and estimates the store visited by the current user. For example, the server device 1 estimates the store with the highest visit score as the store visited by the current user (step S106). Then, the process ends.

[0068] [Variations] Next, preferred modifications of the above-mentioned embodiment will be described. The following modifications may be combined and applied to the above-mentioned embodiment.

[0069] (Variation 1) The server device 1 may estimate a plurality of visited stores according to the user's stay time in the complex facility. For example, the server device 1 analyzes the average stay time for each store type as the stay time trend for each store type from the user's facility visit history. Then, the server device 1 compares the average stay time, which is the stay time trend for the store type of the store with the highest visit score in the current visit to the complex facility (hereinafter also referred to as the "first store"), with the parking time in the parking lot of the current complex facility (hereinafter also referred to as the "current stay time"). If the server device 1 determines that the current stay time is longer than a predetermined time range based on the average stay time for the store type of the first store, the server device 1 determines whether the current stay time is within a predetermined time range based on the total average stay time, which is the sum of the average stay times for the store types of the first store and the store with the second highest visit score (hereinafter also referred to as the "second store"), and if it is determined that the current stay time is within the predetermined time range based on the total average stay time, which is the sum of the average stay times for the store types of the first store and the store with the second highest visit score (hereinafter also referred to as the "second store"), the server device 1 estimates that the user visited the second store in addition to the first store.

[0070] Furthermore, when the server device 1 determines that the stay time in the current complex is longer than the total average stay time in the first store and the second store, the server device 1 may perform the same determination for the store with the third highest visit score (hereinafter, also referred to as the "third store"). Alternatively, the server device 1 may estimate the currently visited store by identifying a combination of the first store, the second store, and the third store that does not cause a contradiction between the total average stay time and the stay time in the current complex. Note that the server device 1 may use the longest stay time or the most frequent stay time for comparison instead of the average stay time as the stay time trend by store type. In this way, the server device 1 can estimate multiple visited stores according to the user's stay time in the complex.

[0071] (Variation 2) The server device 1 may confirm with the user whether the estimated visited store is correct. For example, when the vehicle-mounted device 2 notifies the server device 1 that the target vehicle has departed from the parking lot of the complex, the server device 1 transmits the estimated visited store to the vehicle-mounted device 2. The vehicle-mounted device 2 then outputs a message to the user confirming whether the received visited store is correct. For example, the vehicle-mounted device 2 outputs a voice message to the user asking, "Did you go to the bakery?" If there is a response from the user, the vehicle-mounted device 2 transmits the response from the user to the server device 1.

[0072] The server device 1 judges whether the estimated visited store is correct based on the answer from the user. For example, if the user answers "Yes", the server device 1 judges that the estimated visited store is correct. Then, the server device 1 generates a record including the estimated visited store and registers it in the facility visit history 12d. On the other hand, if the user answers "No", the server device 1 transmits the next candidate to the vehicle-mounted device 2. Then, the vehicle-mounted device 2 outputs a message to the user confirming whether the next candidate is correct. For example, the vehicle-mounted device 2 outputs a message to the user saying, "So, you went to a udon restaurant, right?" In this way, by confirming with the user whether the estimated visited store is correct, an accurate facility visit history can be accumulated.

[0073] (Variation 3) The facility visit history 12d is updated based on the user's walking history or the estimation result of the visited store by the server device 1. The server device 1 may estimate the visited store by using only the stores identified from the user's walking history among the facility visit history 12d. Alternatively, the server device 1 may estimate the visited store after giving a predetermined weight W6 to the stores identified from the user's walking history. By preferentially using the facility visit history with high reliability, the server device 1 can more accurately estimate the stores visited by the user.

[0074] As described above, the server device 1 includes an individual facility list acquisition means, a facility visit history acquisition means, a score calculation means, and an estimation means. The individual facility list acquisition means acquires an individual facility list of facilities corresponding to the parking position of a vehicle. The facility visit history acquisition means acquires the facility visit history of the user of the vehicle. The score calculation means calculates, based on the individual facility list and the facility visit history of the user, a score indicating the likelihood that the user will visit each individual facility included in the individual facility list. The estimation means estimates the individual facility visited this time by the user based on a comparison result of the scores for each individual facility. This enables the server device 1 to estimate the individual facilities visited by the user in a complex facility.

[0075] In each of the above-mentioned embodiments, the program can be stored using various types of non-transitory computer readable media and supplied to a control unit, which is a computer. The non-transitory computer readable media includes various types of tangible storage media. Examples of the non-transitory computer readable media include magnetic storage media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical storage media (e.g., magneto-optical disks), CD-ROM (Read Only Memory), CD-R, CD-R / W, and semiconductor memory (e.g., mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, and RAM (Random Access Memory).

[0076] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above-mentioned embodiments. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. In other words, the present invention naturally includes various modifications and corrections that a person skilled in the art could make in accordance with the entire disclosure, including the claims, and the technical ideas. In addition, the disclosures of the above cited patent documents and the like are incorporated herein by reference. [Explanation of symbols]

[0077] 1. Server device 2 On-vehicle device 3. Communication Network 11, 21 Communications Department 12, 22 Storage section 13, 24 Control section 23 Input section 25 Sensors 26 Display section 27 Sound output section

Claims

1. an individual facility list acquiring means for acquiring an individual facility list of individual facilities present in a facility corresponding to a parking position of the vehicle; a facility visit history acquisition means for acquiring a facility visit history of a user of the vehicle; a score calculation means for calculating, for each individual facility included in the individual facility list, a score indicating a likelihood that the user will visit the individual facility based on the individual facility list and the user's facility visit history; an estimation means for estimating an individual facility currently visited by the user based on a comparison result of the scores for each individual facility; An information processing device comprising:

2. The information processing apparatus according to claim 1 , wherein the facility is a complex facility that combines a plurality of individual facilities.

3. a scenery image acquisition means for acquiring a scenery image obtained by capturing an external scenery including the user from the vehicle; an entrance estimation means for estimating an entrance of the complex facility to which the user is heading from the scenery image, The information processing apparatus according to claim 2 , wherein the score calculation means assigns a predetermined weight to the score of each individual facility located within a predetermined range from the entrance.

4. a visit date and time acquisition means for acquiring a date and time of the user's current visit to the facility, The facility visit history of the user includes a visit date and time to the facility, The information processing device according to claim 2 , wherein the score calculation means selects a visit date and time from the user's facility visit history that matches or is similar to the current visit date and time, and assigns a predetermined weight to the visit score of each individual facility based on the selected history.

5. An interior image acquisition means for acquiring an interior image of the vehicle; a passenger estimation means for estimating a passenger of the vehicle from the vehicle interior image, The facility visit history of the user includes passengers, The information processing device according to claim 2 , wherein the score calculation means selects from the user's facility visit history a history having the same passenger as the current passenger, and assigns a predetermined weight to the visit score of each individual facility based on the selected history.

6. a stay time acquisition means for acquiring a stay time of the vehicle at the parking position, The facility visit history of the user includes a stay time at each individual facility, The information processing apparatus according to claim 2 , wherein the estimation means estimates one or more individual facilities as the individual facilities currently visited by the user based on the score for each individual facility and the duration of stay.

7. an output means for outputting the individual facilities estimated by the estimation means; a correct / incorrect acquisition means for acquiring correct / incorrect information about the individual facilities from the user, 3. The information processing device according to claim 2, wherein the estimation means, when the estimated individual facility is not correct, further estimates a next candidate individual facility, and, when the estimated individual facility is correct, determines the estimated individual facility as the individual facility currently visited by the user.

8. A control method executed by an information processing device, comprising: an individual facility list acquisition step of acquiring an individual facility list of individual facilities present in a facility corresponding to a parking position of the vehicle; a facility visit history acquisition step of acquiring a facility visit history of a user of the vehicle; a score calculation step of calculating, for each individual facility included in the individual facility list, a score indicating a likelihood that the user will visit the individual facility based on the individual facility list and the facility visit history of the user; an estimation step of estimating an individual facility currently visited by the user based on a comparison result of the scores for each individual facility; The control method includes:

9. A program executed by a computer, an individual facility list acquiring means for acquiring an individual facility list of individual facilities present in a facility corresponding to a parking position of the vehicle; a facility visit history acquisition means for acquiring a facility visit history of a user of the vehicle; a score calculation means for calculating, for each individual facility included in the individual facility list, a score indicating a likelihood that the user will visit the individual facility based on the individual facility list and the user's facility visit history; A program that causes a computer to function as an estimation means for estimating the individual facility that the user has currently visited based on the comparison result of the scores for each individual facility.

10. A storage medium storing the program according to claim 9.

Images