Information Processing Apparatus, Information Processing Method, and Non-Transitory Storage Medium

Abstract

The present disclosure provides an information processing apparatus, an information processing method, and a non-transitory storage medium for improving the working efficiency of a vehicle in a system that autonomously dispatches a vehicle to a user's location. The information processing apparatus performs the following processing: selecting, from among a plurality of first users who have a possibility of receiving a predetermined service, a plurality of second users who are the objects of offering the predetermined service; and sending a message offering the predetermined service to devices respectively associated with the plurality of second users. In addition, an upper limit number of the selected second users is determined based on a promise probability that is the probability of the second users promising the offer.

Description

Technical Field

[0001] The present disclosure relates to a technology for supporting the movement of users. Background Art

[0002] There is a service for appropriately performing vehicle dispatching of a vehicle according to a user's commission. For example, in Patent Document 1, an application system capable of requesting vehicle dispatching of a taxi with a simple operation is disclosed.

[0003] On the other hand, it is conceivable that a system for supporting the movement of users by an autonomous driving vehicle operating on a demand basis will be realized in the near future. In addition, a technology for inferring a situation where a user needs a moving unit before the user makes a meaning display and autonomously making a proposal for vehicle dispatching is expected to be put into practical use.

[0004] Prior Art Documents

[0005] Patent Documents

[0006] Patent Document 1: Japanese Patent Application Laid-Open No. 2014-029580 Summary of the Invention

[0007] Problems to be Solved by the Invention

[0008] In such a system, the working efficiency of the vehicle becomes a problem. For example, in the case of performing vehicle dispatching for a vehicle based on a request sent from a user, it is necessary to know in advance the number of vehicles to perform the work. On the other hand, in the case of autonomously proposing vehicle dispatching, whether to accept this proposal depends on the user, and thus vehicles that do not work may be generated according to the situation.

[0009] An object of the present disclosure is to improve the working efficiency of vehicles in a system for autonomously dispatching vehicles to a user's location.

[0010] Means for Solving the Problems

[0011] A first aspect of the present disclosure is an information processing apparatus having a control unit that performs the following processing: selecting a plurality of second users as objects for proposing the provision of a predetermined service from a plurality of first users having a possibility of receiving a predetermined service; and sending a message for proposing the provision of the predetermined service to devices respectively associated with the plurality of second users, and the control unit determines an upper limit number of the selected second users based on a promise probability that is a probability of the second users accepting the proposal.

[0012] In addition, a second aspect of the present disclosure is an information processing method, including the following steps: a step of selecting, from among a plurality of first users who have a possibility of receiving a predetermined service, a plurality of second users who are targets for proposing the provision of the predetermined service; a step of sending a message proposing the provision of the predetermined service to devices respectively associated with the plurality of second users; and a step of determining an upper limit number of the selected second users based on a promise probability that is a probability of the second users promising the proposal.

[0013] In addition, as another aspect, a program that causes a computer to execute the above-described information processing method and a computer-readable storage medium that non-temporarily stores the above-described program can be cited.

[0014] Advantageous Effects of the Invention

[0015] According to the present disclosure, it is possible to improve the working efficiency of vehicles in a system for autonomously dispatching vehicles to the locations of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A diagram for explaining the outline of a vehicle allocation system.

[0017] Figure 2 A diagram for more specifically showing the structural elements of a vehicle allocation system.

[0018] Figure 3A An example of terminal location data stored in a storage unit.

[0019] Figure 3B An example of an action model stored in a storage unit.

[0020] Figure 3C An example of probability data stored in a storage unit.

[0021] Figure 3D An example of vehicle data stored in a storage unit.

[0022] Figure 4 A data flow diagram between functional modules included in a control unit.

[0023] Figure 5 A diagram for explaining a query queue.

[0024] Figure 6 A flowchart of processing performed by a control unit in a first embodiment.

[0025] Figure 7 A flowchart of processing performed by a control unit in a first embodiment.

[0026] Figure 8Flowchart of the process implemented by the control unit in the first embodiment. Detailed implementation

[0027] It is expected that in the near future, technologies that autonomously propose the provision of mobility services implemented by autonomous vehicles to users will be put into practical use.

[0028] In such a system, the working efficiency of the vehicles becomes a problem. Considering business viability, it is preferable to have all the vehicles under the system's management work simultaneously. However, since not all users will necessarily respond to the proposal, there may sometimes be vehicles that do not work. On the other hand, through this situation, it can be foreseen that if more users than the number of available vehicles respond to the proposal, overcrowding problems may occur.

[0029] To solve this problem, it is necessary to appropriately determine the upper limit of the number of users to whom the provision of the proposed mobility service is offered. The information processing device according to this embodiment will solve this problem.

[0030] The information processing device according to one aspect of the present disclosure includes a control unit that performs the following processing: selects a plurality of second users from among a plurality of first users who have the possibility of receiving a predetermined service as the objects to whom the provision of the predetermined service is proposed; and sends a message proposing the provision of the predetermined service to devices respectively associated with the plurality of second users. The control unit determines the upper limit of the number of the selected second users based on the acceptance probability, which is the probability that the second users will respond to the proposal.

[0031] The first user is a user who has the possibility of receiving a predetermined service. For example, when the predetermined service is a transportation service implemented by a vehicle, the first user can be set as a user who has the possibility of wanting to make a move implemented by the vehicle.

[0032] The second user is a user who is the object of inquiring about the provision of the service. The control unit included in the information processing device determines the upper limit of the number of second users based on the probability (acceptance probability) that the second user will respond to the provision of the service. Additionally, the acceptance probability can also be the average value of a plurality of second users. By using the acceptance probability, the working efficiency can be maximized.

[0033] Furthermore, it can also be characterized in that the control unit determines the upper limit of the number of second users based on a value indicating the ability to simultaneously provide the predetermined service and the acceptance probability.

[0034] For example, the upper limit number of the second users can also be calculated by multiplying the value representing the ability to provide services simultaneously by the reciprocal of the promised probability. For example, when the probability that a user who is inquired about the provision of a transportation service promises this inquiry is 80%, and there are 100 vehicles that can work simultaneously, the provision of transportation services can be inquired about to a maximum of 125 people. According to the above method, the working efficiency of the service can be maximized.

[0035] In addition, the following can also be set as a feature, that is, the control unit further performs the following processing: obtaining action data that is data related to human actions; and specifying, based on the action data, the users who are inferred to start moving within a predetermined period as the first users.

[0036] Based on the action data, it is possible to judge the situation where a certain user shows signs of moving. Thus, for example, it becomes possible to inquire about the provision of transportation services to users who are inferred to start moving within a predetermined time.

[0037] In addition, the following can also be set as a feature, that is, the control unit obtains environmental data that is data related to the moving environment of the second user, and determines the promised probability based on the environmental data.

[0038] The probability that a user promises a proposal may change according to the environment in which the user is located (for example, the current location, climate, day of the week, traffic conditions, or time period, etc.). Therefore, by determining the promised probability based on data related to the moving environment, more accurate inference can be implemented.

[0039] It is also possible to adopt the following method, that is, the information processing device further has a storage unit that stores data associating the moving environment with the promised probability.

[0040] In addition, the following can also be set as a feature, that is, the control unit performs the selection in such a way that users who meet a predetermined condition are given priority.

[0041] In addition, the following can also be set as a feature, that is, the control unit determines the priority of being selected as the second user for each of the multiple first users.

[0042] In addition, the following can also be set as a feature, that is, the control unit selects the first users whose priority is higher than a predetermined value as the second users.

[0043] Alternatively, the following method may be adopted, i.e., which user among the first users is to be set as the second user is determined by a predetermined condition. For example, the more beneficial a user is to the utilization of the transportation service, the more preferentially the provision of the service is inquired of the user.

[0044] In addition, the following may also be set as a feature, i.e., the control unit determines the priority based on the utilization history of the vehicle achieved by each user.

[0045] For example, since the more a user has utilized the vehicle in the past, the higher the utilization rate can be predicted, the priority can be improved.

[0046] In addition, the following may also be set as a feature, i.e., the control unit also determines the priority based on the amount of luggage associated with each user.

[0047] For example, when the amount of luggage transported by a user is large, it is preferable to dispatch a vehicle to the user. The amount of luggage transported by the user can be determined based on an image obtained by photographing the user or based on the settlement history completed by the user, etc.

[0048] Hereinafter, embodiments of the present disclosure will be described based on the drawings. The structures of the following embodiments are examples, and the present disclosure is not limited to the structures of the embodiments.

[0049] (First Embodiment)

[0050] Regarding the outline of the vehicle allocation system according to the first embodiment, it will be described while referring to Figure 1 The vehicle allocation system according to the present embodiment is configured to include: a user terminal 200 which is a terminal held by a user, an autonomous driving vehicle (hereinafter, vehicle 300) that provides a transportation service, and a server device 100 that controls the vehicle 300.

[0051] The user terminal 200 is a portable terminal held by a user. The user terminal 200 periodically sends data related to the user's actions to the server device 100. In the present embodiment, the user terminal 200 sends data indicating the position of the present terminal as data related to the user's actions.

[0052] The vehicle 300 is an autonomous vehicle that can carry a user and travel. The vehicle 300 can perform driverless driving in accordance with an instruction sent from the server device 100. In addition, the vehicle 300 can let a user get on and off at a midway point of the route. There may be multiple vehicles 300 included in the system.

[0053] The server device 100 is a device that controls the vehicle 300. In addition, based on the location information received from the user terminal 200, the server device 100 infers (in other words, detects the omen of movement) the situation where the user starts to move within a predetermined period, and based on the result of this inference, probes the user for the provision of a transportation service implemented by the vehicle 300. If the user responds to this probe, the server device 100 dispatches the vehicle 300 to the user's location. Thus, it is possible to autonomously provide a means of transportation to users who need a means of movement.

[0054] Here, when there are multiple users who show the omen of movement, the problem becomes to which of them to probe for the provision of a transportation service. For example, when there is a certain number of users who decline the probe, if probes are made to more users than the number of available vehicles, the working efficiency of the vehicles will increase. On the other hand, if the number of users to whom the probe is made increases too much, the problem of overcrowding may occur. That is, a situation may be triggered where users hope for the provision of a transportation service but the vehicles cannot be allocated to them.

[0055] To address this situation, in the present embodiment, the server device 100 determines in real time the upper limit number of users to whom the probe for the provision of a transportation service is made according to the situation.

[0056] In addition, in the present embodiment, the following method is exemplified, that is, the server device 100 detects the omen of a user located in a predetermined commercial facility to go home, and dispatches the vehicle 300 to the user in accordance with the predicted departure time (the time to start going home).

[0057] Figure 2 A diagram showing in more detail the structural elements of the vehicle allocation system according to the present embodiment.

[0058] First, the user terminal 200 will be described.

[0059] The user terminal 200 is a small computer such as, for example, a smartphone, a mobile phone, a tablet computer, a personal information terminal, a laptop computer, or a wearable computer (such as a smartwatch). The user terminal 200 is configured to include a control unit 201, a storage unit 202, a communication unit 203, an input / output unit 204, and a short-range communication unit 205.

[0060] The control unit 201 is an arithmetic device responsible for the control implemented by the user terminal 200. The control unit 201 can be implemented by an arithmetic processing device such as a CPU (Central Processing Unit).

[0061] The control unit 201 is configured to have two functional modules, namely a position data acquisition unit 2011 and a position data transmission unit 2012. These functional modules can also be implemented by the CPU executing a program stored in the storage unit 202 described later.

[0062] The position data acquisition unit 2011 acquires data related to the position of the present terminal (hereinafter referred to as position data). The position data can be represented by, for example, latitude and longitude, but in the present embodiment, it is set to be data representing the position within the commercial facility that is the object.

[0063] When, for example, a plurality of beacons are provided within a commercial facility, the position data acquisition unit 2011 can communicate with the beacon via the short-range communication unit 205 described later to acquire its identifier. In this case, the identifier of the beacon becomes data related to the position of the present terminal. Thereby, the system can grasp in which place (for example, which store) within the facility the user is located.

[0064] The position data transmission unit 2012 periodically transmits the position data acquired by the position data acquisition unit 2011 to the server device 100.

[0065] The storage unit 202 is configured to include a main storage device and an auxiliary storage device. The main storage device is a memory in which a program executed by the control unit 201 and data used by the control program are expanded. The auxiliary storage device is a device that stores a program executed in the control unit 201 and data used by the control program. In the auxiliary storage device, the content obtained by packaging the program to be executed in the control unit 201 as an application may also be stored. In addition, an operating system for executing these applications may be stored. By loading the program stored in the auxiliary storage device into the main storage device and executing it by the control unit 201, the processing described below is implemented.

[0066] The main storage device may also include a RAM (Random Access Memory) or a ROM (Read Only Memory). In addition, the auxiliary storage device may also include an EPROM (Erasable Programmable ROM) or a hard disk drive (HDD, Hard Disk Drive). Moreover, the auxiliary storage device may also include a removable medium, that is, a portable recording medium. The removable medium is, for example, a USB (Universal Serial Bus) memory, or an optical disc recording medium such as a CD (Compact Disc) or a DVD (Digital Versatile Disc).

[0067] The communication unit 203 is a wireless communication interface for connecting the user terminal 200 to a network. The communication unit 203 is configured to be able to communicate with the server device 100 via, for example, a wireless LAN or mobile communication services such as 3G, LTE, and 5G.

[0068] The input / output unit 204 is a unit that receives input operations performed by a user and presents information to the user. In the present embodiment, the input / output unit 204 is constituted by a single touch panel display. That is, the input / output unit 204 is constituted by a liquid crystal display and its control unit, and a touch panel and its control unit.

[0069] The short-range communication unit 205 is an interface for performing short-range wireless communication with a beacon provided in a facility. The short-range communication unit 205 performs communication at a short range (about several meters) using a predetermined wireless communication standard.

[0070] In the present embodiment, the short-range communication unit 205 performs data communication based on the Bluetooth (registered trademark) Low Energy standard (hereinafter, BLE). In addition, although BLE is exemplified in the present embodiment, other wireless communication standards may also be used. For example, NFC (Near Field Communication), UWB (Ultra Wideband), Wi-Fi (registered trademark), etc. can also be used.

[0071] Next, the server device 100 will be described.

[0072] The server device 100 stores a model (hereinafter referred to as an action model) representing typical actions that a user can take, and determines whether the user holding the user terminal 200 can be seen as showing signs of going home based on the location data received from the user terminal 200.

[0073] Furthermore, the server device 100 conducts a query regarding whether to provide a transportation service implemented by the vehicle 300 for users who show signs of going home. At this time, the server device 100 appropriately determines the maximum number of users for whom the query is to be conducted in order to maximize the operational efficiency of the vehicle.

[0074] The specific method will be described later.

[0075] The server device 100 can be constituted by a general-purpose computer. That is, the server device 100 can be constituted as a computer having a processor such as a CPU or GPU, a main storage device such as a RAM or ROM, and an auxiliary storage device such as an EPROM, a hard disk drive, and a removable medium. Additionally, the removable medium can also be, for example, a USB memory or an optical disc recording medium such as a CD or DVD. In the auxiliary storage device, an operating system (OS), various programs, various tables, etc. are stored. By loading the programs stored herein into the work area of the main storage device and executing them, and by controlling each structural part, etc. through the execution of the programs, various functions consistent with the predetermined purpose as described later can be realized. However, part or all of the functions can also be realized by a hardware circuit such as an ASIC or FPGA.

[0076] The control unit 101 is an arithmetic device responsible for the control implemented by the server device 100. The control unit 101 can be realized by an arithmetic processing device such as a CPU.

[0077] The control unit 101 is constituted in such a way as to have four functional modules: an inference unit 1011, a queue size determination unit 1012, a proposal unit 1013, and an operation instruction unit 1014. Each functional module can also be realized by the CPU executing the stored programs.

[0078] The inference unit 1011 acquires location data from the user terminal 200, and based on the acquired location data, determines a situation in which the user can perceive a sign of going home. This determination can be implemented using the location data stored in the storage unit 102 described later, and the action models corresponding to each user (both described later). When there is a user for whom a sign of going home has been detected, the inference unit 1011 stores information related to the movement of this user (hereinafter, movement data) in a queue (hereinafter, the query queue). The server device 100 queries (polls) the user as to whether to provide a transportation service based on the movement data stored in the query queue.

[0079] The queue size determination unit 1012 adjusts the size of the query queue based on the probability that the user will respond to the poll for providing the transportation service (hereinafter, the response probability). The size of the query queue indicates the number of users who are simultaneously queried as to whether to provide the transportation service. That is, when the response probability is low, the queue size determination unit 1012 increases the size of the query queue to query more users. Conversely, when the response probability is high, the queue size determination unit 1012 reduces the size of the query queue to reduce the number of users for whom the query is implemented.

[0080] The proposal unit 1013 queries the user as to whether to provide the transportation service implemented by the vehicle 300 based on the movement data stored in the query queue. When the user shows a meaning indicating that they want to take the vehicle 300, the movement data corresponding to this user is sent to the operation instruction unit 1014 described later.

[0081] The operation instruction unit 1014 generates an instruction for transporting the user (operation instruction) based on the received movement data, and sends it to the target vehicle. The operation instruction includes information related to the driving route, the locations where the user gets on and off, and the identifier of the user getting on and off.

[0082] Furthermore, the operation instruction unit 1014 has a function of managing the vehicles 300 included in the system. The operation instruction unit 1014 periodically communicates with the multiple vehicles 300 included in the system to acquire the current location and status of each vehicle, the tasks currently being executed, the occupancy time, etc., and stores these data as vehicle data. By referring to the stored vehicle data, it is possible to determine the vehicle to be dispatched for a specific user.

[0083] The storage unit 102 is configured to include a main storage device and an auxiliary storage device. The main storage device is a memory in which programs executed by the control unit 101 and data used by the control programs are expanded. The auxiliary storage device is a device that stores programs executed by the control unit 101 and data used by the control programs.

[0084] The storage unit 102 stores the position data periodically collected from the user terminal 200 as terminal position data 102A. Figure 3A This is an example of terminal position data. As shown in the figure, the terminal position data includes information such as the identifier of the user (user ID), position information (store ID), date, day of the week, and time.

[0085] In addition, the storage unit 102 stores an action model for each user (action model 102B). The action model in this embodiment refers to a model that defines the actions that a user can take before starting to go home through the transfer of positions.

[0086] For example, Figure 3B As shown, the typical actions within a commercial facility from the time of entry to the time of exit can vary for each user. For example, in the case of a user with an action pattern as shown in Pattern A and who has moved to the food counter, it can be inferred that the user will soon go home. In addition, in the case of a user with an action pattern as shown in Pattern B and who has moved to the daily necessities counter, it can be inferred that the user will soon go home. In this embodiment, the action model stores information for inferring the timing when a user starts to go home in this way. The action model corresponding to the user is stored in the storage unit 102 in advance. The action model 102B can be generated, for example, based on the history of the position data obtained from the user terminal 200 held by the user.

[0087] In addition, the storage unit 102 stores data (probability data 102C) for calculating the probability (promise probability) that a user who is inquired about the provision of a transportation service will promise this inquiry.

[0088] The probability data 102C can be set, for example, as a table that describes the promise probability for each environment in which the user is located (hereinafter, the moving environment). Figure 3C This is an example of the probability data 102C. In this example, the promise probability is associated with the facility ID (identifier of the target commercial facility), climate, and time period respectively. In the case of adopting this example, by using the target commercial facility, climate, and time period as keywords, the promise probability can be obtained.

[0089] In addition, although in this example, the place, climate, and time period are exemplified as elements representing the mobile environment, other elements may also be used.

[0090] Furthermore, the probability data 102C may also be a machine learning model or the like that takes data related to the user's mobile environment as input and outputs the promise probability.

[0091] The method of using the promise probability will be described later.

[0092] In addition, the storage unit 102 stores data for managing multiple vehicles 300 (vehicle data 102D). Figure 3D This is an example of vehicle data. The vehicle data is data that describes the identifier of the vehicle 300 managed by the system, its location information, operating status, occupancy time period, etc. In addition, the vehicle data may include other information. For example, it may include the use or type of the vehicle 300, information related to the standby location (garage or business office), body size, loading capacity (seating capacity), travelable distance when fully charged, travelable distance at the current time point, passing places, travel routes, or information related to the destination, etc.

[0093] The vehicle data 102D is periodically updated based on information transmitted from the vehicle 300 (hereinafter, vehicle information).

[0094] The communication unit 103 is a communication interface for connecting the server device 100 to the network. The communication unit 103 is configured, for example, to include a network interface board or a wireless communication circuit for performing wireless communication.

[0095] In addition, Figure 2 The structure shown is an example, and all or part of the illustrated functions may also be executed using a specially designed circuit. In addition, the storage or execution of the program may also be implemented by a combination of a main storage device and an auxiliary storage device other than the illustrated structure.

[0096] Next, regarding the processing performed by the control unit 101, it will be described while referring to the figure showing the data transmitted and received between the modules, that is, Figure 4 while referring to the figure.

[0097] The inference unit 1011 receives position data from multiple user terminals 200 and accumulates the received position data as terminal position data 102A in the storage unit 102. In addition, the inference unit 1011 determines whether the user can be seen as showing signs of going home by comparing the action model stored in the storage unit 102 with the accumulated position data. For example, when the change in position matches the pattern specified in the action model, it can be inferred that the user will start going home in the near future.

[0098] When the inference unit 1011 determines that the user will start going home in the near future, it generates movement data. The movement data includes data such as the identifier of the user to be picked up by the vehicle 300, the location and time of picking up the user, and the location where the user will get off.

[0099] For example, when the inference unit 1011 determines that the user will start going home in 30 minutes, it generates movement data indicating that the user will be picked up at the entrance of the commercial facility in 30 minutes. The generated movement data is appended to Figure 5 the query queue as shown.

[0100] Alternatively, the following method can also be adopted, that is, when the inference unit 1011 can determine the accuracy (hereinafter, movement accuracy) of the user starting to move (going home) as inferred, and when the movement accuracy exceeds a predetermined value, it generates movement data.

[0101] On the other hand, the queue size determination unit 1012 changes the size of the query queue in real time in a manner independent of the processing of the inference unit 1011. The size of the query queue can be determined based on the promised probability described above. For example, when there are 100 currently available vehicles and the promised probability is 50%, vehicle allocation can be inquired for up to 200 users.

[0102] The promised probability depends greatly on the movement environment described above. For example, in the case of poor weather, the promised probability increases compared to the case of good weather.

[0103] The queue size determination unit 1012 calculates the promised probability p based on data related to the user's movement environment (environment data) and the stored probability data. In addition, the environment data can be obtained from outside the device.

[0104] When the probability data is a table or a database, the queue size determination unit 1012 can also use multiple items included in the environment data as keywords to retrieve the promised probability.

[0105] In addition, when the probability data is a machine learning model, the queue size determination unit 1012 can also convert multiple items included in the environment data into feature quantities and input them into the model, and obtain the output promised probability.

[0106] Further, the queue size determination unit 1012 obtains the number v of currently available vehicles 300 with reference to the vehicle data 102D. Moreover, the queue size determination unit 1012 calculates the value obtained by multiplying the number of vehicles 300 by the reciprocal of the promise probability, and sets it as the maximum number n of queries that can be sent. n becomes the size of the query queue.

[0107] n = v × (1 / p) … Equation (1)

[0108] For example, when the number of available vehicles 300 is 100 and the promise probability calculated based on the mobile environment is 67%, n = 150. In this case, 150 copies of mobile data can be stored in the query queue (in other words, queries can be sent to 150 people simultaneously).

[0109] The proposal unit 1013 obtains the mobile data stored in the query queue at each predetermined cycle, and sends a query to the corresponding user terminal 200. When there is a response from the user or the query times out, the mobile data corresponding to the user is deleted from the query queue. When there is a user who responds to the inquiry, the corresponding mobile data is sent to the operation instruction unit 1014.

[0110] The operation instruction unit 1014 determines the vehicle 300 to be assigned to the user based on the obtained mobile data. The vehicle assigned to the user can be determined by referring to the vehicle data 102D. Moreover, the operation instruction is sent to the determined vehicle.

[0111] The operation instruction includes information for identifying the user, the time to pick up the user (vehicle allocation time), the location to pick up the user (vehicle allocation location), the location to drop off the user (for example, the user's own residence), etc.

[0112] The vehicle 300 that receives the operation instruction travels according to the operation instruction to transport the user.

[0113] Moreover, the operation instruction unit 1014 performs a process of managing multiple vehicles 300. That is, it periodically communicates with multiple vehicles 300 to collect information related to the status of each vehicle (vehicle information), and updates the vehicle data 102D.

[0114] Figures 6 - 8 It is a flowchart showing the process implemented by the server device 100.

[0115] In addition, the process of the operation instruction unit 1014 collecting vehicle information and updating the vehicle data 102D is executed in parallel in a manner independent of the illustrated process.

[0116] Figure 6 The flowchart shown represents the process in which the inference unit 1011 receives location data from the user terminal 200 and accumulates it.

[0117] First, in step S11, location data is received from the user terminal 200, and this data is accumulated as terminal location data 102A in the storage unit 102.

[0118] Next, in step S12, the set of accumulated location data is compared with the action model corresponding to the user, and it is determined whether there is a user showing signs of going home. For example, when the degree of consistency between the movement of the location and the action pattern defined by the action model is higher than a threshold, it can be determined that signs of going home can be seen. When the patterns are consistent (step S13 - Yes), the process proceeds to step S14. When the patterns are not consistent (step S13 - No), the process returns to step S11.

[0119] In step S14, the inference unit 1011 generates movement data corresponding to the user who matches, and adds this movement data to the query queue.

[0120] Here, when there is no empty space in the query queue and the movement data cannot be added, this movement data can be processed by any of the following methods.

[0121] (Method A) Do not add the movement data of the object to the queue

[0122] (Method B) Delete the other movement data with the earliest addition time to the queue from the queue

[0123] (Method C) Determine the priority for the movement data, and delete the other movement data with a lower priority from the queue

[0124] The priority for the movement data can be determined based on the following criteria, for example.

[0125] (1) Determine the priority based on the value representing the number of times or the frequency of use of the transportation service previously implemented by the user

[0126] For example, the storage unit 102 stores information representing the usage history of the transportation service, and sets the value representing the number of times or the frequency of use in a predetermined past period as the priority.

[0127] (2) The value representing the number of times or the frequency of the user's response to the transportation service offer inquiry

[0128] For example, the storage unit 102 stores information indicating the number of times a user who has been queried about the provision of a transportation service in a past predetermined period replied to the query, the number of times the query was accepted, the round-trip time until the reply, etc., and sets the values representing this information as priorities.

[0129] (3) The value indicating the movement accuracy of the user

[0130] For example, when the inference unit 1011 can determine the movement accuracy corresponding to the user, it sets the value representing the movement accuracy as the priority.

[0131] Since the probability stored in the query queue increases when the priority is high, the user is more likely to be selected as the object for providing the transportation service.

[0132] In addition, values other than these can also be used as priorities.

[0133] Moreover, the priority can also be corrected according to the user's status. For example, the higher the number of pieces of luggage carried by the user, the higher the priority, or the higher the number of people (such as family members) traveling with the user, the higher the priority. The amount of luggage carried by the user can be judged either based on the result of sensing and detecting the user or based on the settlement information associated with the user. In addition, the number of people traveling with the user can also be obtained via the transportation unit during the outbound journey. For example, when the user uses the transportation service during the outbound journey, the number of people traveling with the user can be judged based on the number of passengers at that time.

[0134] Figure 7 The flowchart shown represents the process in which the queue size determination unit 1012 adjusts the size of the query queue. As described above, Figure 7 The process shown is Figure 6 executed independently of the process shown at a predetermined cycle (for example, every 15 minutes).

[0135] First, in step S21, the probability data 102C and the vehicle data 102D stored in the storage unit 102 are acquired.

[0136] Next, in step S22, environmental data is acquired, and the acceptance probability is determined based on the environmental data and the probability data 102C. For example, in the case of Figure 3C the example shown, the acceptance probability can be obtained based on the target commercial facility, the climate, and the time period. When the probability data 102C is a machine learning model, the movement conditions are converted into feature quantities as inputs, and the output acceptance probability is acquired.

[0137] Next, in step S23, based on the determined commitment probability and the number of available vehicles, the size of the query queue is changed using Equation (1). The number of available vehicles can be obtained by referring to the vehicle data 102D.

[0138] Here, when the data volume exceeds the limit due to the change in the size of the query queue (step S24 - Yes), the process transfers to step S25, and the mobile data of the deletion target is determined. For the user who becomes the deletion target, the provision of the transportation service will not be solicited. The deletion target can be determined by any one of the aforementioned (Method A) to (Method C), for example. When the data volume does not exceed the limit even after the change in the size of the query queue (step S24 - No), the process ends.

[0139] Figure 8 FIG. is a flowchart of the process in which the proposal unit 1013 solicits the provision of the transportation service for the users included in the query queue. Figure 8 The process shown is executed at a predetermined cycle.

[0140] First, in step S31, all the mobile data included in the query queue is processed, and a message soliciting the provision of the transportation service is sent to the user terminal 200 held by the corresponding user.

[0141] Next, in step S32, the mobile data corresponding to the users who have not replied within a certain time (e.g., 5 minutes) is deleted from the queue.

[0142] Next, in step S33, it is judged whether there is a reply from any user. If there is a reply, in step S34, the vehicle allocation policy (whether to implement vehicle allocation or not) for that user is determined. If there is no reply, the process transfers to step S35.

[0143] In step S35, it is judged whether the vehicle allocation policy has been determined for all the users who have been queried. When the judgment in this step is negative, the process returns to step S32.

[0144] When the vehicle allocation policy has been determined for all the users who have been queried, the process transfers to step S36, and the mobile data corresponding to the users who wish to have vehicle allocation is transferred to the operation instruction unit 1014.

[0145] The operation instruction unit 1014 allocates the vehicle 300 based on the obtained mobile data and generates operation instructions for each vehicle. The operation instructions are sent to the corresponding vehicle 300 respectively to start the operation.

[0146] As described above, the server device 100 according to the first embodiment detects a sign that a user starts to move (go home) based on the information received from the user terminal 200, and autonomously inquires about the provision of a mobility service. In addition, the number of users for whom the inquiry is made is dynamically adjusted based on the commitment probability. Thereby, the working efficiency of the vehicle can be maximized.

[0147] (Second Embodiment)

[0148] Although in the first embodiment, the mobility data corresponding to all users who show signs of movement is added to the query queue, it is also possible to add only the mobility data corresponding to users who meet a predetermined condition to the query queue. As the predetermined condition, for example, the actual utilization results of the transportation service, the number of fellow passengers, or the amount of luggage carried by the user can be used.

[0149] In addition, as shown in (Method C) of the first embodiment, the priority can be determined for each user, and only the mobility data corresponding to users whose priority meets the threshold is added to the query queue. The priority can be determined, for example, based on the actual utilization results of the transportation service, or based on the number of fellow passengers, the amount of luggage carried by the user, or the mobility accuracy.

[0150] Moreover, the threshold of the priority can also be dynamically changed based on the operating conditions of the vehicle, etc.

[0151] For example, when there are few users showing signs of movement and the working efficiency of the vehicle has not improved, by lowering the threshold of the priority, more users can be included in the queue. On the contrary, when there are many users showing signs of movement and the working efficiency of the vehicle is continuously approaching 100%, by raising the threshold of the priority, the vehicle can be preferentially allocated to users who are more beneficial for the utilization of the transportation service.

[0152] (Modification Example)

[0153] The above-described embodiments are merely examples, and the present disclosure can be appropriately modified and implemented without departing from its gist.

[0154] For example, in the present disclosure, the processes or units described can be freely combined and implemented as long as there is no technical contradiction.

[0155] In addition, although the signs that a user staying in a commercial facility is about to go home are detected in the description of the embodiment, as long as it is possible to infer the situation where the user starts to move, the place where the user stays is not limited to a commercial facility. Moreover, the actions of the subject are not limited to going home. For example, it is also possible to detect the signs that a user staying in his / her own house is about to go out based on the actions of the user in his / her own house.

[0156] Also, although an example where the server device 100 has jurisdiction over a predetermined commercial facility is listed in the description of the embodiment, the server device 100 does not have to be at the facility level. For example, it is also possible to make the server device 100 manage vehicles that can be dispatched to a predetermined area, and determine the signs of movement for users located within that area. In this case, it is also possible to judge the situation where the corresponding user will start to move (for example, start going home) in the near future based on the information sent from the user terminal 200 located within the area.

[0157] The predetermined area can be either an area divided by a grid or an area defined according to administrative divisions, etc.

[0158] In addition, the area under the jurisdiction of the server device 100 can also be multiple. In this case, it is also possible to obtain the number of available vehicles and the upper limit number of users for whom inquiries are to be implemented for each area, and implement inquiries for vehicle allocation using the method described above. Additionally, it is also possible to define the probability data 102C for each area.

[0159] Also, although the situation where the corresponding user starts to move is inferred based on the location information in the description of the embodiment, other data can also be used. For example, it is also possible to judge the situation where the user will start to move in the near future based on information other than the location information sent from the user terminal 200 held by the user (for example, information related to electronic settlement, messages, email, etc.), or data obtained by sensing and detecting the user.

[0160] In addition, the processing described as being implemented by one device can also be executed by multiple devices sharing the work. Or, the processing described as being implemented by different devices can also be executed by one device. In a computer system, it is possible to flexibly change the hardware structure (server structure) for implementing each function.

[0161] The present disclosure can also provide a computer program installed with the functions described in the above embodiments to a computer, and cause one or more processors included in the computer to read and execute the program to implement. Such a computer program can be provided to the computer either through a non-transitory computer-readable storage medium capable of being connected to the system bus of the computer or via a network. The non-transitory computer-readable storage medium includes, for example, any type of disk such as a floppy disk (Floopy, registered trademark), a hard disk drive (HDD), etc., an optical disc (CD-ROM, DVD disc, Blu-ray disc, etc.), a read-only memory (ROM), a random access memory (RAM), an EPROM, an EEPROM, a magnetic card, a flash memory, an optical card, and any type of medium suitable for storing electronic instructions.

[0162] Symbol Explanation

[0163] 100… Server device;

[0164] 101, 201… Control unit;

[0165] 102, 202… Storage unit;

[0166] 103, 203… Communication unit;

[0167] 200… User terminal;

[0168] 204… Input / output unit;

[0169] 205… Short-range communication unit;

[0170] 300… Vehicle.

Claims

1. An information processing apparatus, wherein, it has a control unit, and the control unit performs the following processing: acquire action data which is data related to human actions; based on the action data, determine, as first users, users who are inferred to start moving within a predetermined period and wish to utilize a transportation service provided by a vehicle; select, from among the multiple first users, multiple second users who are the targets for proposing the provision of the transportation service; send a message proposing the provision of the transportation service to devices respectively associated with the multiple second users; the control unit determines the upper limit number of the selected second users based on the acceptance probability which is the probability of the second users accepting the proposal.

2. The information processing apparatus according to claim 1, wherein, the control unit determines the upper limit number of the second users based on a value indicating the ability to simultaneously provide the transportation service and the acceptance probability.

3. The information processing apparatus according to claim 1, wherein, the control unit acquires environment data which is data related to the moving environment of the second users, and determines the acceptance probability based on the environment data.

4. The information processing apparatus according to claim 3, wherein, it further has a storage unit, and the storage unit stores data associating the moving environment with the acceptance probability.

5. The information processing apparatus according to any one of claims 1 to 4, wherein, the control unit preferentially selects, as the second users, the first users among the multiple first users who satisfy a predetermined condition.

6. The information processing apparatus according to any one of claims 1 to 4, wherein, the control unit determines, for each of the multiple first users, the priority of being selected as the second user.

7. The information processing apparatus according to claim 6, wherein, the control unit determines the priority based on the utilization history of the vehicle achieved by each of the multiple first users.

8. The information processing apparatus according to claim 7, wherein, the control unit further determines the priority based on the amount of luggage associated with each of the multiple first users.

9. The information processing apparatus according to claim 6, wherein, the control unit selects, as the second users, the first users whose priority is higher than a predetermined value.

10. An information processing method, including the following steps: a step of acquiring action data which is data related to human actions; a step of determining, based on the action data, as first users, users who are inferred to start moving within a predetermined period and wish to utilize a transportation service provided by a vehicle; a step of selecting, from among the multiple first users, multiple second users who are the targets for proposing the provision of the transportation service; a step of sending a message proposing the provision of the transportation service to devices respectively associated with the multiple second users; a step of determining the upper limit number of the selected second users based on the acceptance probability which is the probability of the second users accepting the proposal.

11. The information processing method according to claim 10, wherein, the upper limit number of the second users is determined based on a value indicating the ability to provide the transportation service simultaneously and the promised probability.

12. The information processing method according to claim 10, wherein, it further includes the following steps, that is: obtain environmental data as data related to the moving environment of the second users, and determine the promised probability based on the environmental data.

13. The information processing method according to claim 12, wherein, it further includes the following steps, that is: obtain data associating the moving environment with the promised probability.

14. The information processing method according to any one of claims 10 to 13, wherein, it further includes the following steps, that is: determine the priority of being selected as the second user for each of the plurality of first users.

15. The information processing method according to claim 14, wherein, select the first users with the priority higher than a predetermined value as the second users.

16. A non-transitory storage medium storing a program for causing a computer to execute the information processing method according to any one of claims 10 to 15.

Images