Vehicle management facility information providing method and program

Abstract

To provide a management facility information providing method and program that effectively eliminate uneven distribution of vehicles at management facilities that manage vehicles.SOLUTION: In a vehicle sharing system 100 in which a vehicle management server 10, multiple vehicle devices 60, and multiple user terminals 70 are connected to a network 80 such as the Internet, the vehicle management server executes processing for: identifying, as a reference facility, one of management facilities that manage unrented vehicles based on input by a user; extracting, as unevenly distributed facilities, management facilities that exist within a predetermined range from the reference facility and that should reduce the number of unrented vehicles they manage; identify, from among the unevenly distributed facilities, an unevenly distributed facility where a benefit of the user renting a vehicle from the unevenly distributed facility matches a benefit that the user values; and presenting information on the identified unevenly distributed facility to the user.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a method and a program for providing management facility information for a vehicle. [Background technology]

[0002] In recent years, services have emerged that allow multiple users to share vehicles such as cars, bicycles, and e-scooters. There are two types of service provision: the "station-based" type and the "free-float" type. In the station-based type, users rent a vehicle from a dedicated station (management facility) installed around town and return it to the same or a different station after use. On the other hand, the free-float type allows users to freely return (drop off) the vehicle anywhere, including on the street.

[0003] In the case of the station-based system, the return station is set according to the user's wishes, so there is a risk of uneven distribution of vehicles, such as one station having many vehicles and another station having almost no vehicles.

[0004] In response to this, techniques for resolving uneven vehicle distribution are known, such as those disclosed in Patent Documents 1 and 2. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2016-95750 A [Patent Document 2] Patent Publication No. 2021-60921 Summary of the Invention [Problem to be solved by the invention]

[0006] Patent Document 1 discloses a method for lowering the usage fee for users who use a shared vehicle in a manner that reduces uneven distribution, and for raising the usage fee for users who use a shared vehicle in a manner that increases uneven distribution. Patent Document 2 discloses a method for presenting users with recommended routes that eliminate uneven distribution of vehicles, and giving incentives to users who follow the recommended routes.

[0007] However, Patent Documents 1 and 2 only disclose providing a specific incentive to users who resolve vehicle uneven distribution. Therefore, users who are not attracted to the specific incentive may not take any action to resolve vehicle uneven distribution.

[0008] According to one aspect, the present invention aims to provide a method and a program for providing vehicle management facility information, which can effectively eliminate uneven distribution of vehicles in a management facility that manages vehicles. [Means for solving the problem]

[0009] In one aspect, a method for providing information on management facilities for vehicles is a method for providing information on management facilities for vehicles, in which a computer executes processing to identify one of the management facilities that manages unrented vehicles as a reference facility based on user input, extract management facilities that are located within a predetermined range of the reference facility and that should reduce the number of unrented vehicles they manage as unevenly distributed facilities, identify among the unevenly distributed facilities a facility where the benefit of the user renting a vehicle from that unevenly distributed facility matches the benefit that the user values, and present information on the identified unevenly distributed facility to the user.

[0010] In another aspect, a method for providing information on management facilities for vehicles is a method for providing information on management facilities for vehicles, in which a computer executes processing to identify one of the management facilities that manages unrented vehicles as a reference facility based on user input, extract management facilities that are located within a predetermined range of the reference facility and that should increase the number of unrented vehicles they manage as unevenly distributed facilities, identify among the unevenly distributed facilities a facility where the benefit to the user of returning a vehicle at that unevenly distributed facility matches the benefit that the user values, and present information on the identified unevenly distributed facility to the user. Effect of the Invention

[0011] This effectively alleviates the uneven distribution of vehicles in management facilities that manage vehicles. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating a schematic configuration of a vehicle sharing system according to an embodiment. [Diagram 2] FIG. 2(a) is a diagram showing the hardware configuration of a vehicle management server, and FIG. 2(b) is a diagram showing the hardware configuration of a vehicle device. [Diagram 3] FIG. 3 is a functional block diagram of the vehicle management server and the vehicle device. [Figure 4] Figure 4 is a map showing the stations scattered across the map. [Diagram 5] FIG. 5(a) is a diagram showing the data structure of a user DB, FIG. 5(b) is a diagram showing the data structure of a station DB, and FIG. 5(c) is a diagram showing the data structure of a maintenance base DB. [Figure 6] FIG. 6 is a flowchart (part 1) showing the process of the vehicle management server. [Figure 7] FIG. 7 is a flowchart (part 2) showing the process of the vehicle management server. [Figure 8]FIG. 8(a) is a diagram showing a state in which departure and destination stations (reference stations) have been selected, and FIG. 8(b) is a diagram showing a state in which a standard route has been searched for. [Figure 9] FIG. 9 is a diagram showing predetermined ranges As and Ag centered on stations S and G. [Figure 10] FIG. 10 is a diagram for explaining a first modification of the method for extracting unevenly distributed stations. [Figure 11] FIG. 11 is a diagram for explaining the second modification of the method for extracting unevenly distributed stations. [Figure 12] FIG. 12 is a diagram showing unevenly distributed stations S1, S2, G1, G2, and maintenance base M1. [Figure 13] Figure 13(a) is a diagram showing a recommended route between stations S and G, including a route between candidate stations S1 and G1, and Figure 13(b) is a diagram showing a recommended route between stations S and G, including a route between candidate stations S2 and G2. [Figure 14] FIG. 14 is a diagram showing a recommended route between stations S and G including a route between candidate stations S2 and M1. [Figure 15] FIG. 15(a) is a diagram (part 1) showing an example of a screen presented to a user, and FIG. 15(b) is a diagram (part 2) showing an example of a screen presented to a user. [Figure 16] FIG. 16 is a diagram (part 3) showing an example of a screen presented to the user. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] An embodiment will be described in detail below with reference to Figs. 1 to 16. Fig. 1 shows a schematic configuration of a vehicle sharing system 100 according to an embodiment. The vehicle sharing system 100 of this embodiment is a system that provides a service (vehicle sharing service) that allows a plurality of users to share a vehicle. The vehicle may be an automobile, a bicycle, an e-scooter, or the like, but in this embodiment, the vehicle is a bicycle or an e-scooter equipped with a battery. There are two types of vehicle sharing service provision: a "station-based type" and a "free-floating type," and this embodiment is the "station-based type." In the case of the "station-based type," many stations (management facilities) are installed in the city, and a user borrows a vehicle from one of the stations. After using the vehicle, the user returns the vehicle to one of the stations.

[0014] 1, the vehicle sharing system 100 includes a vehicle management server 10, a vehicle device 60, and a user terminal 70. The vehicle management server 10, the vehicle device 60, and the user terminal 70 are connected to a network 80 such as the Internet. The user terminal 70 is an information processing terminal such as a smartphone, and is a terminal that is held and used by a user who uses the service (rents a vehicle).

[0015] The vehicle management server 10 collects information from the vehicle equipment 60 and the user terminal 70, and based on the information entered into the user terminal 70 and the collected information, provides the user terminal 70 with information on stations that manage unrented vehicles and information on routes between stations.

[0016] FIG. 2(a) shows the hardware configuration of the vehicle management server 10. As shown in FIG. 2(a), the vehicle management server 10 includes a CPU (Central Processing Unit) 90, a ROM (Read Only Memory) 92, a RAM (Random Access Memory) 94, a storage (e.g., an SSD (Solid State Drive) or an HDD (Hard Disk Drive)) 96, a network interface 97, and a portable storage medium drive 99. These components of the vehicle management server 10 are connected to a bus 98. In the vehicle management server 10, the CPU 90 executes a program (including a vehicle management facility information providing program) stored in the ROM 92 or the storage 96, or a program read from the portable storage medium 91 by the portable storage medium drive 99, thereby realizing the functions of the components shown in FIG. 3. The functions of FIG. 3 may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). Details of the components of FIG. 3 will be described later.

[0017] The vehicle device 60 is a device mounted on each vehicle shared by multiple users, and acquires vehicle information and transmits the acquired information to the vehicle management server 10. FIG. 2(b) shows the hardware configuration of the vehicle device 60. As shown in FIG. 2(b), the vehicle device 60 includes a CPU 190, a ROM 192, a RAM 194, a storage 196, a network interface 197, a display unit 193, an input unit 195, a position detection device 187, a battery remaining amount detection device 189, and the like. These components of the vehicle device 60 are connected to a bus 198. The display unit 193 is a liquid crystal display or the like, and displays vehicle information (battery remaining amount, etc.). The position detection device 187 is a GNSS (Global Navigation Satellite System) sensor or the like, and is a device that detects the position information (latitude, longitude, etc.) of the vehicle. The battery remaining amount detection device 189 is a device that detects the remaining amount of the battery mounted on the vehicle.

[0018] 3 shows a functional block diagram of the vehicle management server 10 and the vehicle device 60. The functions of the vehicle management server 10 and the vehicle device 60 will be described below.

[0019] (Functions of the vehicle management server 10) The vehicle management server 10 functions as an input receiving unit 12, a data management unit 14, a standard route search unit 16, a distributed station extraction unit 18, a candidate station identification unit 20, a recommended route search unit 22, and a presentation unit 24 by the CPU 90 executing a program. Note that Fig. 3 also illustrates a user DB 30, a station DB 32, a maintenance base DB 34, and a learning model / learning data storage unit 36 ​​stored in the storage 96 or the like.

[0020] The input reception unit 12 receives information (such as route search conditions) input from the user terminal 70, and transfers it to the standard route search unit 16. In this embodiment, as shown in the map in FIG. 4, stations that manage vehicles are scattered at the locations indicated by black circles (●). Also, facilities (maintenance bases) that perform vehicle maintenance are located at the locations indicated by black triangles (▲). At the maintenance bases, maintenance such as vehicle servicing and battery charging / replacement is performed. The source of the maps in FIG. 4 and other drawings is the website of the Geospatial Information Authority of Japan (https: / / maps.gsi.go.jp / ).

[0021] 4 on the screen of the user terminal 70, selects a station to be set as the starting point, and selects a station to be set as the destination, and sets these as conditions for route search. Note that the station that the user sets as the starting point is the station that is closest to the user's current location, but is not limited to this.

[0022] The data management unit 14 acquires information transmitted from the vehicle device 60, and updates the station DB 32 with the acquired information. The data management unit 14 also acquires information input by the user to the user terminal 70, usage history information of related services and apps by the user, and the like, and updates the user DB 30 and stores the information in the learning model and learning data storage unit 36. The data management unit 14 also generates a learning model (described in detail later) for each user using the data (learning data) of each user stored in the learning model and learning data storage unit 36, and stores the model in the learning model and learning data storage unit 36.

[0023] Here, the user DB30 is a database that manages information of users who use the service, and has a data structure as shown in FIG. 5(a). Specifically, the user DB30 stores information on "user ID", "number of uses", "learning model storage destination", "learning data storage destination", and "related application ID". The "user ID" is identification information assigned to a user who uses the service. The "number of uses" is the number of times each user has used the service, and the value is increased by one each time the user inputs from the user terminal 70 that the user will use the vehicle. The "learning model storage destination" is an address indicating the storage destination of the learning model generated for each user. Note that, if a learning model has not been generated, "N / A" is stored. The "learning data storage destination" is an address indicating the storage destination of the learning data of each user. The "related application ID" is the ID of an application (e.g., a health application) used by the user (installed in the user terminal 70) or the ID of a related service.

[0024] The station DB 32 is a database that manages information about each station, and has a data structure as shown in FIG. 5(b). Specifically, the station DB 32 stores information about "station ID," "location," "accommodable number of vehicles," "current number of vehicles," "duration (minutes) of the current number of vehicles," "vehicle ID to be maintained," and "periphery information." The "station ID" is identification information assigned to each station. The "location" is the location information (latitude, longitude) of each station. The "accommodable number of vehicles" is the number of vehicles that can be accommodated at the same time in each station. The "current number of vehicles" is the number of vehicles currently accommodated in each station. The "duration (minutes) of the current number of vehicles" is the time that has elapsed since each station became in the current state (since the current number of vehicles was accommodated). The "vehicle ID to be maintained" is identification information of a vehicle that needs to have its battery replaced. The "periphery information" is information about the vicinity of each station (such as information about what tourist resources are available in the vicinity).

[0025] The maintenance base DB 34 is a database that manages information about each maintenance base, and has a data structure as shown in FIG. 5(c). Specifically, the maintenance base DB 34 stores the following information: "Base ID," "Location," and "Eligible for discount?". "Base ID" is identification information assigned to each maintenance base. "Location" is location information (latitude, longitude) of each maintenance base. The "Eligible for discount?" column stores information indicating whether or not the vehicle usage fee will be discounted (true or false) when the vehicle is returned to each base.

[0026] 3, the learning model / learning data storage unit 36 ​​stores the learning model generated for each user, and also stores the learning data of each user used when generating the learning model. The addresses of the "storage destination of the learning model" and "storage destination of the learning data" in the user DB 30 described above are addresses within the learning model / learning data storage unit 36.

[0027] The standard route search unit 16 executes a route search based on the information received by the input reception unit 12. Specifically, the standard route search unit 16 searches for a route between the departure station and the destination station input by the user, and sets the route as a standard route.

[0028] The unevenly distributed station extraction unit 18 extracts, from among stations existing near the station of the departure point input by the user, stations that accommodate a larger number of vehicles (are unevenly distributed) than other stations as unevenly distributed stations. Also, from among stations existing near the station of the destination input by the user, the unevenly distributed station extraction unit 18 extracts, from among stations existing near the station of the destination input by the user, stations that accommodate a smaller number of vehicles (are unevenly distributed) than other stations as unevenly distributed stations.

[0029] The candidate station identifying unit 20 identifies stations (candidate stations) to be presented to the user from among the unevenly distributed stations extracted by the unevenly distributed station extraction unit 18. When identifying the candidate stations, the candidate station identifying unit 20 uses a learning model for the user if one exists. In this case, a station that is likely to be used by the user is identified as a candidate station. The candidate station identifying unit 20 may identify any maintenance base as a candidate station.

[0030] The recommended route search unit 22 searches for a recommended route including a route between the candidate stations identified by the candidate station identification unit 20. The recommended route is a route connecting a departure station and a destination station input by the user, in which the route between the candidate stations is traveled by vehicle and the other routes are traveled on foot.

[0031] The presentation unit 24 generates a screen displaying the standard route searched by the standard route search unit 16 and the recommended route searched by the recommended route search unit 22, and transmits the screen to the user terminal 70. At this time, the presentation unit 24 also displays information on the screen indicating what kind of merit the user will get by selecting the recommended route.

[0032] (Functions of the vehicle device 60) As shown in FIG. 3, the vehicle device 60 functions as a rental status management unit 61, a current position acquisition unit 62, a remaining battery level acquisition unit 64, and a communication unit 66 by the CPU 190 executing a program.

[0033] The rental status management unit 61 manages information on whether or not a user is using a vehicle (rental status information). When the rental status management unit 61 detects that a user has started or ended use of a vehicle, it transmits the detected information to the data management unit 14 of the vehicle management server 10 via the communication unit 66.

[0034] The current position acquisition unit 62 acquires the current position of the vehicle from the position detection device 187 (see FIG. 2(b)) and transmits it to the data management unit 14 of the vehicle management server 10 via the communication unit 66. The data management unit 14 of the vehicle management server 10 checks which station each vehicle is accommodated at based on information on whether each vehicle is rented or not and information on each vehicle's current position. The data management unit 14 then updates the "current number of vehicles accommodated" and "duration of current number of vehicles accommodated" in the station DB 32 as needed.

[0035] The battery remaining amount acquisition unit 64 acquires information on the remaining amount of the battery mounted on the vehicle from the battery remaining amount detection device 189 (see FIG. 2(b)), and transmits the information to the data management unit 14 of the vehicle management server 10 via the communication unit 66. When a vehicle has a low remaining battery amount, the data management unit 14 stores the vehicle ID of the vehicle in the "maintenance target vehicle ID" field of the station (station that houses the vehicle) corresponding to the current location of the vehicle in the station DB 32.

[0036] The communication unit 66 transmits the information acquired by the rental status management unit 61, the current position acquisition unit 62, and the battery remaining capacity acquisition unit 64 to the data management unit 14 of the vehicle management server 10.

[0037] (Regarding the processing of the vehicle management server 10) The processing of the vehicle management server 10 will be described in detail below with reference to the flowcharts of Figures 6 and 7 and other drawings as appropriate. Note that the data management unit 14 of the vehicle management server 10 updates the user DB 30 and station DB 32 every time information is transmitted from the user terminal 70 and the vehicle device 60.

[0038] When the processing of Fig. 6 and Fig. 7 is started, first, in step S10, the input receiving unit 12 waits until the start and destination stations are selected. For example, assume that the user selects stations S and G indicated by white circles (◯) on the map shown in Fig. 8(a) as the start (Start) and destination (Goal) stations. In this case, the determination in step S10 is affirmative, and the process proceeds to step S12. The input receiving unit 12 specifies the selected station as the reference station.

[0039] In step S12, the standard route search unit 16 searches for a route having the reference stations S and G as the starting point and destination, and sets the route as the standard route. In Fig. 8(b), the searched standard route is shown by a thick line.

[0040] Next, in step S14, the unevenly distributed station extraction unit 18 sets a predetermined range centered on the selected station (reference station S, G). Here, as shown in FIG. 9, ranges As and Ag indicated by circles of a predetermined radius centered on stations S and G, respectively, are set. The predetermined radius may be common to all users, or may be determined for each user based on the user's attributes (age, usual number of steps, etc.). For example, when the user is older or the usual number of steps is smaller, the predetermined radius can be made smaller. The user's age may be identified from the date of birth, age, etc. input by the user when registering for use of the service. The usual number of steps may be identified from the number of steps measured by a specific app such as a health app installed in the user terminal 70.

[0041] Next, in step S16, the unevenly distributed station extraction unit 18 extracts unevenly distributed stations within the set ranges As and Ag. The unevenly distributed stations within the range As refer to stations that accommodate a large number of vehicles and should reduce the number of vehicles, while the unevenly distributed stations within the range Ag refer to stations that accommodate a small number of vehicles and should increase the number of vehicles. For example, the unevenly distributed station extraction unit 18 refers to the station DB 32 to obtain the average number of vehicles accommodated in all stations. The unevenly distributed station extraction unit 18 also identifies the number of vehicles accommodated in each station within the range As, and extracts stations with the identified number of vehicles accommodated being greater than the average value as unevenly distributed stations. The unevenly distributed station extraction unit 18 also identifies the number of vehicles accommodated in each station within the range Ag, and extracts stations with the identified number of vehicles accommodated being less than the average value as unevenly distributed stations.

[0042] However, the present invention is not limited to this, and the unevenly distributed station extracting unit 18 may extract unevenly distributed stations in the following manner.

[0043] (Variation 1 of the method for extracting unevenly distributed stations) For example, suppose that there are stations with station IDs S001 to S003 within the range As, and the number of vehicles that can be accommodated and the current number of vehicles that can be accommodated at each station are as shown in FIG. 10. In this case, the unevenly distributed station extraction unit 18 obtains the ratio of the current number of vehicles to the number of vehicles that can be accommodated for each station. As a result, the ratio of station S001 is 80.0%, the ratio of station S002 is 33.3%, and the ratio of station S003 is 28.6%. Note that the average value of the ratios of all stations is 47.3%. Then, the unevenly distributed station extraction unit 18 obtains the difference (deviation) between the obtained ratio and the average value. As a result, as shown in FIG. 10, the deviation of station S001 is 32.7%, the deviation of station S002 is -14.0%, and the deviation of station S003 is -18.7%.

[0044] The unevenly distributed station extraction unit 18 assumes that a station with a positive deviation is a station with a large number of vehicles, and extracts, as an unevenly distributed station, a station with a positive deviation within the range As. Note that the unevenly distributed station extraction unit 18 may extract, as an unevenly distributed station, a station with a positive deviation and an absolute value equal to or greater than a predetermined value.

[0045] 10 are within the range Ag, the unevenly distributed station extraction unit 18 extracts stations within the range Ag whose deviation is a negative value (stations with a small number of vehicles accommodated) as unevenly distributed stations. Note that the unevenly distributed station extraction unit 18 may extract only stations whose deviation is a negative value and whose absolute value is a predetermined value or more as unevenly distributed stations.

[0046] (Variation 2 of the method for extracting unevenly distributed stations) The unevenly distributed station extraction unit 18 may weight the deviation calculated in the above-mentioned modified example 1 by the "duration of the current number of vehicles accommodated" and identify the unevenly distributed station based on the weighted value. For example, the duration of the current number of vehicles accommodated / a reference value (e.g., 750) may be used as a weighting coefficient. The rightmost column of the table in FIG. 11 shows the result of weighting the deviation by the duration. For example, within the range As, the unevenly distributed station extraction unit 18 determines a station whose weighted deviation is a positive value and whose absolute value is equal to or greater than a predetermined value as an unevenly distributed station. Also, for example, within the range Ag, the unevenly distributed station extraction unit 18 determines a station whose weighted deviation is a negative value and whose absolute value is equal to or greater than a predetermined value as an unevenly distributed station.

[0047] (Variation 3 of the method for extracting unevenly distributed stations) The unevenly distributed station extraction unit 18 may extract unevenly distributed stations using the degree of uneven distribution K(h) as disclosed in, for example, JP 2016-95750 A.

[0048] The method of extracting unevenly distributed stations is not limited to the above-mentioned example, and unevenly distributed stations may be extracted by other methods (calculation methods).

[0049] In addition, even if a station is extracted as a station with a large (or small) number of vehicles accommodated using the above-mentioned method for extracting stations with uneven distribution, it may be possible to predict that the uneven distribution will be resolved in the near future based on past trends, reservation information, etc. In this way, stations where the uneven distribution is predicted to be resolved in the near future may be excluded from the stations with uneven distribution.

[0050] In this embodiment, it is assumed that within the range As, stations S1 and S2 shown in FIG. 12 are extracted as unevenly distributed stations, and within the range Ag, stations G1 and G2 shown in FIG. 12 are extracted as unevenly distributed stations.

[0051] Next, in step S17, if a maintenance base satisfies a predetermined condition, the unevenly distributed station extraction unit 18 extracts the maintenance base as an unevenly distributed station. For example, the unevenly distributed station extraction unit 18 refers to the maintenance base DB 34, and if there is a maintenance base that is located within the range Ag and is eligible for a discount, extracts the maintenance base as an unevenly distributed station. Note that the condition for extracting a maintenance base as an unevenly distributed station can be changed as appropriate. For example, a maintenance base extracted as an unevenly distributed station may be outside the range Ag. Note that in this embodiment, it is assumed that the maintenance base M1 in FIG. 12 is extracted as an unevenly distributed station.

[0052] Returning to FIG. 6, in the next step S18, the candidate station identification unit 20 judges whether or not an unevenly distributed station has been extracted in step S16. If an unevenly distributed station has been extracted in at least one of the ranges As and Ag, the judgment in this step S18 is deemed to be positive. If the judgment in this step S18 is negative (if no unevenly distributed station has been extracted), the process proceeds to step S22. When the process proceeds to step S22, the presentation unit 24 transmits a screen (FIG. 8(b)) displaying the standard route searched by the standard route search unit 16 to the user terminal 70, and displays it on the screen to present it to the user. After that, all the processes in FIG. 6 and FIG. 7 are terminated.

[0053] On the other hand, if the determination in step S18 is positive (if at least one unevenly distributed station is extracted), the process proceeds to step S20. In step S20, the candidate station identification unit 20 refers to the user DB 30 and acquires the learning model of the user from the learning model / learning data storage unit 36.

[0054] Next, when the process proceeds to step S30 in Fig. 7, the candidate station identification unit 20 judges whether or not the learning model of the user has been acquired. That is, it judges whether or not the learning model of the user has already been generated. If the judgment of this step S30 is positive, the process proceeds to step S32.

[0055] When proceeding to step S32, the candidate station identification unit 20 uses the learning model acquired in step S20 to identify, as a candidate station, from among the extracted unevenly distributed stations, the unevenly distributed station that is most likely to be selected by the user.

[0056] Here, the learning model is a model that is generated for each user and is used to specify, as a candidate station, the unevenly distributed station that is most likely to be used by the user among the unevenly distributed stations extracted by the unevenly distributed station extraction unit 18. The learning model is configured to output candidate stations by inputting information about each of the extracted unevenly distributed stations (information on whether or not the station has surrounding information, location information, distance from a reference station, etc.).

[0057] The learning model is generated by the data management unit 14 using the learning data (feature amounts) such as the following (1) to (4) including questionnaires and profile information for users, usage history of related services and apps, and behavioral history. Note that a validity period may be set appropriately for the learning data to be used. For example, the learning model may be generated using only the learning data collected within the past month. (1) Data on exercise habits and health awareness For example, data on the number of steps taken, amount of exercise, and usage of health apps. (2) Data on reactions to new spots and event information For example, this data includes store usage history for related services, response rates to advertisements, and frequency of use in the same area. (3) Data on responses to economic incentives For example, data such as the usage status of coupons and points for related services. (4) Data regarding past route choices For example, this data may be a selection history that indicates what benefits routes have been selected in the past.

[0058] The data management unit 14 uses the above-mentioned learning data to generate a learning model for determining what kind of merit station each user will select by a general-purpose machine learning method such as a neural network. An output example of the learning model (an example of identifying candidate stations) will be described below. (Example 1) For example, if the user is highly interested in new spots or events or is a tourist, the station DB 32 identifies the station as a candidate station that is associated with peripheral information. For example, if peripheral information is associated with the stations S1 and G1 in FIG. 12, the stations S1 and G1 are identified as candidate stations. (Example 2) For example, if a user lacks exercise or is interested in exercise, unevenly distributed stations on or near the standard route (unevenly distributed stations that force the user to travel on foot) are identified as candidate stations. For example, unevenly distributed stations S2 and G2 in Fig. 12 are stations on or near the standard route, so these stations S2 and G2 are identified as candidate stations. Note that unevenly distributed stations that force the user to travel on foot may also be identified as candidate stations even if they are not on or near the standard route. (Example 3) For example, if the user is a user who tends to be frugal, then the station (e.g., S2) that houses vehicles that need maintenance (vehicles with low battery power) and the station (e.g., M1) that can offer a discount on the usage fee are identified as candidate stations.

[0059] Returning to FIG. 7, when the process proceeds to step S34, the recommended route search unit 22 searches for a route between the identified candidate stations, and sets the route between stations S and G including the searched route as the recommended route. For example, when unevenly distributed stations S1 and G1 are identified as candidate stations as in the above (Example 1), a recommended route as shown in FIG. 13(a) is searched. Note that, in the recommended route, the portion indicated by the dashed line is a walking section, and the portion indicated by the solid line is a section using a vehicle. Also, for example, when unevenly distributed stations S2 and G2 are identified as candidate stations as in the above (Example 2), a recommended route as shown in FIG. 13(b) is searched. Furthermore, for example, when unevenly distributed stations S2 and M1 are identified as candidate stations as in the above (Example 3), a recommended route as shown in FIG. 14 is searched.

[0060] Next, in step S36, the presentation unit 24 presents the standard route and the recommended route (and merits) to the user. For example, when a recommended route as shown in FIG. 13(a) is searched, the presentation unit 24 generates a screen that displays the standard route and the recommended route as well as merits (information around stations S1 and G1) when the recommended route is selected as shown in FIG. 15(a). Also, for example, when a recommended route as shown in FIG. 13(b) is searched, the presentation unit 24 generates a screen that displays the standard route and the recommended route as well as merits (information that the lack of exercise will be resolved) when the recommended route is selected as shown in FIG. 15(b). Also, for example, when a recommended route as shown in FIG. 14 is searched, the presentation unit 24 generates a screen that displays the standard route, the recommended route, and merits that a discount on the usage fee will be provided when the vehicle to be maintained is used and returned to the maintenance base as shown in FIG. 16. Then, the presentation unit 24 transmits the generated screen to the user terminal 70. Note that, in each screen of FIG. 15(a) to FIG. 16, the user can select either the standard route or the recommended route.

[0061] Next, in step S38, the data management unit 14 waits until a route is selected by the user. When either the standard route or the recommended route is selected by the user, the process proceeds to step S40, and the data management unit 14 stores the selection result in the learning model and learning data storage unit 36 ​​as learning data.

[0062] Next, in step S42, the data management unit 14 updates the learning model by using the learning data stored in the learning model / learning data storage unit 36. After the processing up to step S42 is performed, all the processing in Figs. 6 and 7 is terminated.

[0063] On the other hand, if the determination in step S30 is negative, that is, if the learning model of the user cannot be acquired in step S20 in FIG. 6 (the learning model has not yet been generated), the process proceeds to step S52.

[0064] In step S52, the candidate station identifying unit 20 randomly selects the extracted unevenly distributed stations as candidate stations. In this case, the candidate station identifying unit 20 randomly selects, for example, one of the unevenly distributed stations S1 and S2, and one of the unevenly distributed stations G1, G2, and M1 as candidate stations.

[0065] Next, in step S54, the recommended route search unit 22 searches for a route between the candidate stations and sets it as a recommended route.

[0066] Next, in step S56, the presentation unit 24 presents the standard route and the recommended route (and their merits) to the user.

[0067] Next, in step S58, the data management unit 14 waits until a route is selected by the user. When either the standard route or the recommended route is selected by the user, the process proceeds to step S60, and the data management unit 14 stores the selection result in the learning model and learning data storage unit 36 ​​as learning data.

[0068] Next, in step S61, the data management unit 14 judges whether or not a learning model can be generated using the user's learning data stored in the learning model / learning data storage unit 36. That is, the data management unit 14 judges whether or not learning data has been collected to the extent that a learning model can be generated. If the judgment in step S61 is positive, the process proceeds to step S62, and the data management unit 14 generates a learning model using the learning data stored in the learning model / learning data storage unit 36. After that, all the processes in Figs. 6 and 7 are terminated. Also, if the judgment in step S61 is negative, all the processes in Figs. 6 and 7 are terminated without going through step S62.

[0069] In steps S52, S54, and S56, routes of all combinations of unevenly distributed stations S1 and S2 and unevenly distributed stations G1, G2, and M1 may be presented as recommended routes to a user who does not have a learning model.

[0070] As described above in detail, according to this embodiment, the input receiving unit 12 sets one of the stations that manages unrented vehicles based on the user's input as the reference station (S). The unevenly distributed station extracting unit 18 extracts, as the unevenly distributed station, a station that exists within a predetermined range As from the reference station and has a large number of vehicles and should reduce the number of vehicles. The candidate station identifying unit 20 identifies, as the candidate station, an unevenly distributed station whose merit of renting a vehicle at the unevenly distributed station matches the merit emphasized by the user. Then, the presenting unit 24 presents information about the identified candidate station (recommended route via the candidate station) to the user. In this embodiment, information about unevenly distributed stations that have merits emphasized by the user (merits that match the user's preferences), that is, information about unevenly distributed stations that are likely to be used by the user, can be presented to the user. This promotes the use of vehicles accommodated in the unevenly distributed stations, and makes it possible to alleviate the uneven distribution of vehicles between stations.

[0071] According to the present embodiment, the input receiving unit 12 sets one of the stations that manages unrented vehicles based on the user's input as the reference station (G). The uneven distribution station extraction unit 18 extracts, as the uneven distribution station, a station that exists within a predetermined range Ag from the reference station, has a small number of vehicles, and should increase the number of vehicles. The candidate station identification unit 20 identifies, as the candidate station, an uneven distribution station whose merit of returning the vehicle at the uneven distribution station matches the merit emphasized by the user. Then, the presentation unit 24 presents information about the identified candidate station (recommended route via the candidate station) to the user. In the present embodiment, information about uneven distribution stations that have merits emphasized by the user (merits that match the user's preferences), that is, information about uneven distribution stations that are likely to be used by the user, can be presented to the user. This promotes the return of vehicles to uneven distribution stations, and makes it possible to alleviate uneven distribution of vehicles between stations.

[0072] In addition, in this embodiment, the data management unit 14 generates a learning model using learning data such as information on whether the user has used the unevenly distributed stations presented to the user in the past, survey results for the user, profile information, and usage history of related services and apps. Then, the candidate station identification unit 20 uses the learning model to identify unevenly distributed stations that the user is likely to use, and presents information on the identified unevenly distributed stations to the user. This makes it possible to accurately identify unevenly distributed stations that the user is likely to use. In addition, by presenting unevenly distributed stations that the user is likely to use to the user, it is possible to effectively alleviate the uneven distribution of vehicles between stations.

[0073] In addition, in this embodiment, when a learning model of a user has not been generated, a maldistribution station is randomly selected and information on the selected maldistribution station is presented to the user. In this way, when a learning model of a user has not been generated, information on maldistribution stations that provide various benefits can be presented to the user evenly. In this case, by using information on whether or not the user has used the presented maldistribution station, a highly accurate learning model can be generated.

[0074] In this embodiment, the unevenly distributed station extraction unit 18 determines whether each station is an unevenly distributed station based on the number of unrented vehicles (current capacity) currently managed by each station. This makes it possible to determine whether a station is an unevenly distributed station in an appropriate manner. Also, by determining whether a station is an unevenly distributed station based on the predicted change in the capacity of each station, it is possible to avoid presenting information about stations that are expected to cease to be unevenly distributed stations in the near future to the user.

[0075] In this embodiment, the vehicle maintenance base may be an unevenly located station. This allows the user to be given an incentive, such as a discount on the usage fee, to transport the vehicle (vehicle that needs maintenance) to the maintenance base after use. This reduces the labor required for maintenance by the service provider, etc.

[0076] In addition, in this embodiment, when the recommended route is presented to the user, the advantages of selecting the recommended route are also presented, allowing the user to determine whether to select the reference route or the recommended route while referring to the advantages of the recommended route.

[0077] In the above embodiment, the case where the user selects the station (S) as the starting point and the station (G) as the destination has been described, but the present invention is not limited to this. When the user inputs the current location and the destination, the input receiving unit 12 may search for the station closest to the current location and the station closest to the destination, and specify the searched station as the reference station (reference facility).

[0078] In the above embodiment, the case where the user searches for a route has been described, but the present invention is not limited to this. When the user searches for the station located closest to the current location, information on the station located closest to the current location may be presented to the user, and information on a station that is not located closest but is advantageous to use may be presented to the user.

[0079] In the above embodiment, a learning model is used to identify candidate stations from among unevenly distributed stations, but the present invention is not limited to this. If it is known from a prior questionnaire or the like what kind of merit a user will select from a station, information on unevenly distributed stations that have the same merit may be presented.

[0080] In the above embodiment, a case where a vehicle with a low remaining battery power is brought to a maintenance base has been described. However, this is not limited to this, and other vehicles (for example, vehicles with low air pressure, vehicles with a long battery life, vehicles for which a predetermined period of time has passed since the last maintenance, etc.) may be brought to a maintenance base.

[0081] The above processing functions can be realized by a computer. In that case, a program is provided that describes the processing contents of the functions that the processing device should have. The above processing functions are realized on the computer by executing the program on the computer. The program that describes the processing contents can be recorded on a computer-readable recording medium (excluding carrier waves).

[0082] When a program is distributed, it is sold in the form of a portable recording medium on which the program is recorded, such as a DVD (Digital Versatile Disc), a CD-ROM (Compact Disc Read Only Memory), etc. The program can also be stored in a storage device of a server computer and transferred from the server computer to other computers via a network.

[0083] A computer that executes a program stores, for example, a program recorded on a portable recording medium or a program transferred from a server computer in its own storage device. The computer then reads the program from its own storage device and executes processing in accordance with the program. The computer can also read the program directly from a portable recording medium and execute processing in accordance with that program. The computer can also execute processing in accordance with the received program each time a program is transferred from the server computer.

[0084] The above-described embodiment is a preferred example of the present invention, but the present invention is not limited to this embodiment and can be modified in various ways without departing from the scope of the present invention.

[0085] In addition, the following supplementary notes are disclosed in relation to the above-described embodiment. (Appendix 1) Identify one of the management facilities that manages unrented vehicles as a reference facility based on user input; extracting, as an unevenly distributed facility, a management facility that is present within a predetermined range from the reference facility and that is in a position where the number of unrented vehicles under management should be reduced; identifying a facility among the unevenly distributed facilities in which the benefit of the user renting a vehicle at the unevenly distributed facility coincides with the benefit that the user values, and presenting information on the identified unevenly distributed facility to the user; A method for providing vehicle management facility information, the processing of which is executed by a computer. (Appendix 2) Identify one of the management facilities that manages unrented vehicles as a reference facility based on user input; extracting, as an unevenly distributed facility, a management facility that is present within a predetermined range from the reference facility and that should increase the number of unrented vehicles under its management; identifying a facility among the unevenly distributed facilities in which the benefit of returning the vehicle to the facility coincides with the benefit that the user values, and presenting information on the identified unevenly distributed facility to the user; A method for providing vehicle management facility information, the processing of which is executed by a computer. (Appendix 3) A method for providing facility management information to a vehicle as described in appendix 1 or 2, characterized in that a learning model is used to identify, among the unevenly distributed facilities, those unevenly distributed facilities for which the benefits of the user using the facility match the benefits that the user values, using the facility, based on at least one of information on whether the user has used the unevenly distributed facility presented in the past, information on the user input by the user, and information on the user's behavioral history. (Appendix 4) A method for providing facility information for vehicle management as described in Appendix 3, characterized in that, when the learning model has not been generated, information on at least one of the unevenly distributed facilities is presented to the user. (Appendix 5) A method for providing vehicle management facility information as described in any one of Appendices 1 to 4, characterized in that the management facilities to be extracted as the unevenly distributed facilities are determined based on the number of unrented vehicles managed by each of the management facilities. (Appendix 6) A method for providing vehicle management facility information as described in Appendix 5, characterized in that the management facilities to be extracted as the unevenly distributed facilities are determined based on the results of predicting changes in the number of unrented vehicles managed at each of the management facilities. (Supplementary Note 7) The method for providing facility information for a vehicle according to any one of Supplementary Notes 1 to 6, characterized in that, as the unevenly located facilities, maintenance facilities that perform maintenance of the vehicle and that satisfy a predetermined condition are extracted. (Appendix 8) A method for providing management facility information for a vehicle as described in any one of Appendices 1 to 7, characterized in that in the process of identifying the reference facility, one of the management facilities is identified as the reference facility based on route search conditions input by the user. (Appendix 9) A method for providing facility management information to a vehicle as described in any one of Appendices 1 to 8, characterized in that in the process of presenting to the user, the extracted information on the unevenly located facility is presented along with benefits of using the unevenly located facility. (Appendix 10) Identifying one of the management facilities that manages unrented vehicles as a reference facility based on user input; extracting, as an unevenly distributed facility, a management facility that is present within a predetermined range from the reference facility and that is in a position where the number of unrented vehicles under management should be reduced; identifying a facility among the unevenly distributed facilities in which the benefit of the user renting a vehicle at the unevenly distributed facility coincides with the benefit that the user values, and presenting information on the identified unevenly distributed facility to the user; A vehicle management facility information providing program that causes a computer to execute a process. (Appendix 11) Identify one of the management facilities that manages unrented vehicles as a reference facility based on user input; extracting, as an unevenly distributed facility, a management facility that is present within a predetermined range from the reference facility and that should increase the number of unrented vehicles under its management; identifying a facility among the unevenly distributed facilities in which the benefit of returning the vehicle to the facility coincides with the benefit that the user values, and presenting information on the identified unevenly distributed facility to the user; A vehicle management facility information providing program that causes a computer to execute a process. [Explanation of symbols]

[0086] 10 Vehicle management server 12 Input reception section 14 Data Management Department 16 Standard Route Search Section 18 Uneven Station Extraction Unit 20 Candidate Station Identification Division 22 Recommended route search section 24 Presentation section 30 User DB 32 Station DB 34 Maintenance base DB 36 Learning model and learning data storage section 60 Vehicle equipment 61 Loan Availability Management Department 62 Current position acquisition unit 64 Battery remaining capacity acquisition unit 66 Communications Department 100 Vehicle sharing system

Claims

1. Identifying one of the management facilities that manages unrented vehicles as a reference facility based on user input; extracting, as an unevenly distributed facility, a management facility that is present within a predetermined range from the reference facility and that is in a position where the number of unrented vehicles under management should be reduced; identifying a facility among the unevenly distributed facilities in which the benefit of the user renting a vehicle at the facility coincides with the benefit emphasized by the user, and presenting information on the identified unevenly distributed facility to the user; A method for providing vehicle management facility information, the processing of which is executed by a computer.

2. Identifying one of the management facilities that manages unrented vehicles as a reference facility based on user input; extracting, as an unevenly distributed facility, a management facility that is present within a predetermined range from the reference facility and that should increase the number of unrented vehicles under its management; identifying a facility among the unevenly distributed facilities in which the benefit of returning the vehicle to the facility coincides with the benefit emphasized by the user, and presenting information on the identified unevenly distributed facility to the user; A method for providing vehicle management facility information, the processing of which is executed by a computer.

3. The method for providing facility information for vehicle management as described in claim 1 or 2, characterized in that a learning model is used to generate information based on at least one of information on whether the user has used the unevenly distributed facility presented in the past, information on the user input by the user, and information on the user's behavioral history, to identify among the unevenly distributed facilities those where the benefits of the user using a vehicle at the unevenly distributed facility match the benefits that the user values.

4. 4. The method for providing facility information for a vehicle according to claim 3, further comprising the step of: presenting information on at least one of the unevenly distributed facilities to the user when the learning model has not been generated.

5. 3. The method for providing facility information on vehicles according to claim 1, further comprising the step of determining which management facilities to extract as the unevenly distributed facilities based on the number of unrented vehicles managed by each of the management facilities.

6. The vehicle management facility information providing method according to claim 5, characterized in that the management facilities to be extracted as the unevenly distributed facilities are determined based on the results of predicting changes in the number of unrented vehicles managed at each of the management facilities.

7. 3. The method for providing facility information for a vehicle according to claim 1, further comprising extracting, as the unevenly located facilities, maintenance facilities that satisfy a predetermined condition from among maintenance facilities that perform maintenance of the vehicle.

8. 3. The method for providing management facility information for a vehicle according to claim 1, wherein in the process of identifying the reference facility, one of the management facilities is identified as the reference facility based on route search conditions input by the user.

9. 3. The vehicle management facility information providing method according to claim 1, wherein in the process of presenting to the user, benefits of using the unevenly located facility are presented together with the extracted information on the unevenly located facility.

10. Identifying one of the management facilities that manages unrented vehicles as a reference facility based on user input; extracting, as an unevenly distributed facility, a management facility that is present within a predetermined range from the reference facility and that is in a position where the number of unrented vehicles under management should be reduced; identifying a facility among the unevenly distributed facilities in which the benefit of the user renting a vehicle at the facility coincides with the benefit emphasized by the user, and presenting information on the identified unevenly distributed facility to the user; A vehicle management facility information providing program that causes a computer to execute a process.

11. Identifying one of the management facilities that manages unrented vehicles as a reference facility based on user input; extracting, as an unevenly distributed facility, a management facility that is present within a predetermined range from the reference facility and that should increase the number of unrented vehicles under its management; identifying a facility among the unevenly distributed facilities in which the benefit of returning the vehicle to the facility coincides with the benefit emphasized by the user, and presenting information on the identified unevenly distributed facility to the user; A vehicle management facility information providing program that causes a computer to execute a process.

Images