Information processing device

Abstract

To suppress excessive overlapping of presentation routes to a plurality of users in a route guidance for the plurality of users.SOLUTION: An information processing device includes a control unit 110 that executes: acquiring each preference of a plurality of users relating to a moving route; using each preference of each user to calculate a first moving route for each of the users; when the first moving routes are overlapped beyond a predetermined reference, correcting the preferences among the plurality of users to use the corrected preference to calculate a second moving route; and presenting the plurality of calculated second moving routes to the plurality of users.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to route guidance. [Background technology]

[0002] There are many known techniques related to route guidance. For example, Patent Document 1 discloses a route search device that searches for a recommended route using a cost value that is determined based on a representative value of the travel time of links and a value that indicates the statistical variation of the travel time. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-165665 A Summary of the Invention [Problem to be solved by the invention]

[0004] The present disclosure aims to prevent excessive overlap of suggested routes to multiple users in route guidance for the users. [Means for solving the problem]

[0005] One aspect of the present disclosure is to The information processing device has a control unit that executes the following operations: acquiring preferences of each of a plurality of users regarding travel routes; calculating a first travel route for each of the users using the preferences of each of the users; if the first travel routes overlap beyond a predetermined standard, correcting the preferences between the plurality of users and calculating a second travel route using the corrected preferences; and presenting the calculated second travel routes to each of the plurality of users.

[0006] Other aspects include a method executed by the above-mentioned device, a program for causing a computer to execute the method, or a computer-readable storage medium non-transitoryly storing the program. Effect of the Invention

[0007] According to the present disclosure, in route guidance for multiple users, it is possible to prevent routes suggested to each user from overlapping excessively. [Brief description of the drawings]

[0008] [Figure 1] FIG. 4 is a diagram showing an overview of a process executed by a server device according to the embodiment. [Diagram 2] FIG. 2 is a diagram for explaining components of a server device according to the embodiment. [Diagram 3] 5 is a flowchart of a process executed by a control unit of the server device according to the embodiment. [Figure 4] 11 is a flowchart of a process of correcting weights so as to emphasize differences, which is executed by a control unit of the server device according to the embodiment. [Diagram 5] 11 is a flowchart of a process for calculating a value indicating a preference, which is executed by a control unit of the server device according to the embodiment. [Figure 6] 11 is a flowchart of a process for correcting a weight of an item with a relatively low cost, which is executed by a control unit of the server device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] 2. Description of the Related Art Devices that provide route guidance are known.

[0010] For example, consider a device that provides route guidance to multiple users heading in the same direction. First, the device obtains information on the starting point and destination of each of the multiple users. Then, the device presents the optimal route from each starting point to the destination to each user.

[0011] However, even if the optimal route is calculated for each of the multiple users, the same route may be proposed to most of the multiple users heading in the same direction. In this way, the device may guide many vehicles to a specific road by proposing the same route to many users, which may cause problems such as traffic congestion. In order to address this issue, it is preferable that the system calculates a different route for each user, even when multiple users are heading in the same direction, thereby reducing overlapping of routes proposed to each user. The information processing device in this embodiment solves this problem.

[0012] An information processing device according to an embodiment of the present disclosure includes: The system has a control unit that executes the following operations: acquiring preferences of each of a plurality of users regarding travel routes; calculating a first travel route for each of the users using the preferences of each of the users; if the first travel routes overlap beyond a predetermined standard, correcting the preferences between the plurality of users and calculating a second travel route using the corrected preferences; and presenting the calculated second travel routes to each of the plurality of users.

[0013] A user's preference for a travel route indicates the tendency of each user to place importance on characteristics of the travel route, such as minimum fuel consumption, minimum travel time, wide roads, or the presence of a specific store along the travel route.

[0014] The first moving route is a moving route from a starting point to a destination point of the user, which is calculated by the control unit using the user's preferences. Here, the case where the first moving routes overlap beyond a predetermined criterion means that the first moving routes proposed to each user are the same or partially the same among a predetermined number or more of multiple users.

[0015] The second movement route is a movement route from the starting point to the destination point of the user that is recalculated by the control unit by correcting the acquired preferences between the users and using the corrected preferences.

[0016] The control unit calculates a first moving route using the preferences of each user, and when the first moving routes proposed to each user overlap each other beyond a predetermined standard, the control unit corrects the preferences of each user and calculates a second moving route using the corrected preferences of each user. Thus, the control unit can calculate a second moving route different from the overlapping first moving route.

[0017] As a result, the information processing device according to the present disclosure can prevent excessive overlap of suggested routes to each user in route guidance to multiple users.

[0018] In addition, the control unit may calculate values ​​indicating the preferences for multiple items for each of the multiple users, and if the first movement routes overlap beyond a predetermined standard, correct weights for at least some of the items so as to emphasize differences in preferences between the multiple users, and calculate a second movement route using the corrected weights.

[0019] To correct the weights so as to emphasize the differences in preferences means to The weight for each item of each user is adjusted so as to further increase the difference between users.

[0020] As a result, the information processing device according to the present disclosure can prevent the proposed routes to each user from overlapping excessively without deviating from the preference trends of each user for travel routes.

[0021] In addition, the control unit may calculate values ​​indicating the preferences for multiple items for each of the multiple users, and when the first movement route overlaps beyond a predetermined standard, extract a cost corresponding to the multiple items on a third movement route, which is an alternative route to the first movement route, that is relatively lower than the first movement route, correct the weight for the item corresponding to the extracted cost for each of the multiple users so that it is relatively larger than the weights for the other items, and calculate a second movement route using the corrected weight.

[0022] The third movement route is a route from the starting point of the user to the destination, and can be an alternative to the first movement route.

[0023] The cost of a travel route is the degree to which the characteristics of the travel route are realized on the travel route. For example, the cost of a travel route may be the fuel consumption value, the travel time value, the road width value, or the number of specific stores, or the normalized value of each of the above-mentioned characteristics of the travel route.

[0024] The control unit compares the cost of a plurality of items representing the characteristics of the third moving route with the cost of the corresponding items of the first moving route, and extracts an item having a lower cost than the cost of the corresponding items of the first moving route from among the plurality of items representing the characteristics of the third moving route. Then, the control unit corrects the weight of the user's preference item corresponding to the extracted item so that it is relatively larger than the weight of other items from among the plurality of items of the user's preference, thereby calculating the second moving route.

[0025] An information processing device according to the present disclosure can appropriately distribute suggested routes to a user when there are multiple travel routes that match the user's preferences but only a specific travel route is calculated as a suggested route.

[0026] In addition, the control unit may extract multiple users who depart from the same starting point and pass through the same destination point via different travel routes, and compare the costs of the travel routes between the extracted multiple users to relatively calculate a value indicating the preference that indicates the degree of the preference of the user between the multiple users. In this way, the information processing device according to the present disclosure can determine a value indicating the preference of each user by reflecting the difference in characteristics of the routes selected by each user in the past. Therefore, the information processing device according to the present disclosure can calculate a value indicating the preference that can propose a travel route that meets the needs of the user.

[0027] The control unit may also calculate, for each of the multiple users, a preference value indicating a degree of the preference of the user, based on a survey result for each of the multiple users.

[0028] In this way, the information processing device according to the present disclosure can calculate a value indicating a user's preference based on feedback from the user. Therefore, the information processing device according to the present disclosure can calculate a value indicating a user's preference through simpler processing.

[0029] Specific embodiments of the present disclosure will be described below with reference to the drawings. Unless otherwise specified, the hardware configuration, module configuration, functional configuration, and the like described in each embodiment are not intended to limit the technical scope of the disclosure to only those.

[0030] First Embodiment An overview of the processing performed by the server device according to the embodiment will be described with reference to FIG. 1. FIG. 1 is a diagram showing an overview of the processing performed by the server device 100 according to the embodiment. Here, the server device 100 is an example of an information processing device according to the present disclosure. The server device 100 is a device that calculates a travel route from a departure point to a destination of a plurality of users and proposes the route to each user. The server device 100 is configured to be able to communicate with a vehicle 10.

[0031] First, the server device 100 acquires preferences for a travel route from a plurality of users. The preference of a user for a travel route is, for example, a preference for fuel consumption on the travel route (preferring low fuel consumption, etc.). In addition, for example, the preference of a user for a travel route may be a preference for travel time on the travel route (preferring short travel time, etc.), a preference for road width on the travel route (preferring wide road width, etc.), etc. The preferences of each user may be expressed by scores for a plurality of items. For example, as shown in FIG. 1, the preferences of user 1 may be expressed as values ​​indicating the preferences, such as (preference for low fuel consumption, preference for short travel time, preference for wide road width)=(10, 7, 2). The higher the score of the value indicating the preference, the higher the degree of preference for that item (for example, the higher the degree of preference for low fuel consumption).

[0032] Each user has different preferences. For example, the values ​​indicating the preferences of user 2 are (preference for low fuel consumption, preference for short travel time, preference for wide roads) = (9, 8, 3), which is different from the preferences of user 1.

[0033] Then, the server device 100 calculates a travel route that satisfies the preferences of each user. For example, as shown in FIG. 1, route 1 is calculated for user 1 and user 3, route 2 for user 2, and route 3 for user 4 and user 5. In this manner, the same travel route may be calculated in a duplicated manner for a plurality of users. Here, the same travel route calculated in a duplicated manner may be an exact same travel route, or may be a partially identical travel route.

[0034] As described above, the preferences of each user typically show different tendencies. However, even if users have different tendencies, the same travel route may be assigned depending on the calculation method. If many users are guided to the same travel route, it may cause problems such as traffic congestion, so it is desirable to avoid overlapping travel routes proposed to each user beyond a certain standard.

[0035] Therefore, when the same travel route is calculated for multiple users more than a predetermined standard, the server device 100 changes the weighting for the value indicating the preference and calculates a travel route that satisfies the preference of each user again. For example, the weighting for each item of the value indicating the preference of each user is corrected so that the difference between the values ​​indicating the preference of each user is emphasized. Then, for example, route 1 for user 1, route 2 for user 2, route 4 for user 3, route 3 for user 4, and route 5 for user 5 are calculated this time as shown in FIG. 1.

[0036] In this way, compared to the initial calculation, the travel route calculated for user 3 is changed from route 1 to route 4, and the travel route calculated for user 5 is changed from route 3 to route 5. This prevents the same travel route from being calculated multiple times for multiple users. Then, the server device 100 presents the recalculated travel route to each user.

[0037] As described above, when the initially calculated travel routes for each user overlap among the users beyond a predetermined criterion, the server device 100 corrects the preferences of the multiple users and recalculates the travel route using the corrected preferences. This allows the server device 100 to avoid proposing a specific travel route to an excessive number of users.

[0038] According to this configuration, the server device 100 can prevent routes proposed to a plurality of users from overlapping excessively when providing route guidance to the users.

[0039] Next, a detailed description will be given of each element constituting the server device 100. Fig. 2 is a diagram for explaining the components of the server device 100 according to the embodiment.

[0040] The server device 100 according to this embodiment includes a control unit 110, a storage unit 120, and a communication unit .

[0041] The control unit 110 is realized by a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit) and a memory. The control unit 110 includes, as functional modules, an acquisition unit 111, a calculation unit 112, a correction unit 113, and a presentation unit 114. These functional modules may be realized by the control unit 110 executing a program.

[0042] The acquisition unit 111 acquires information representing the preferences of each user. That is, the acquisition unit 111 acquires information representing the tendency of each user to place importance on characteristics of a travel route. The acquisition unit 111 may acquire information representing the preferences of each user by communicating with an information terminal associated with each user, or may acquire information representing the preferences of each user by communicating with a vehicle 10 associated with each user.

[0043] The calculation unit 112 calculates the first movement route using the preference of each user. For example, the calculation unit 112 may calculate a movement route that satisfies the preference of each user as the first movement route.

[0044] The calculation unit 112 also determines whether the same travel route is calculated for a plurality of users in a manner that exceeds a predetermined criterion. If the same travel route is calculated for a plurality of users in a manner that exceeds a predetermined criterion, the calculation unit 112 calculates a second travel route using the corrected preference.

[0045] Furthermore, the calculation unit 112 may calculate, for each user, values ​​indicating preferences for multiple items among the characteristics of the travel route based on the information indicating the preferences of each user. Here, the value indicating the preference may be a numerical value indicating the tendency of each user to place importance on the characteristics of the travel route.

[0046] In addition, when the same movement route is calculated for multiple users in a manner that exceeds a predetermined standard, the calculation unit 112 may calculate a second movement route based on a value indicating preference using the weight corrected by the correction unit 113.

[0047] The calculation unit 112 may also extract a plurality of users who travel from the same starting point to the same destination point via different travel routes, and compare the costs of the travel routes between the extracted plurality of users. Then, the calculation unit 112 may calculate a value indicating the preference of each user relatively between the plurality of users, based on the costs of each of the compared travel routes. Alternatively, the calculation unit 112 may calculate a value indicating the preference of each user based on the results of a questionnaire given to each user.

[0048] When the same travel route is calculated more than once beyond a predetermined standard, the correction unit 113 may correct the weighting for at least some of the items among the values ​​indicating the user preferences so as to emphasize the differences in preferences among multiple users.

[0049] In addition, when the same moving route is calculated more than once beyond a predetermined standard, the correction unit 113 may extract a relatively lower cost in the third moving route compared to the first moving route among the costs corresponding to a plurality of items of the value indicating the user's preference. Here, the third moving route may be a route that is an alternative to the first moving route.

[0050] Then, the correction unit 113 may correct the weighting for at least some of the items among the values ​​indicating the user's preferences so that, for each user, the weighting for the item corresponding to the extracted cost is relatively larger than the weighting for the other items.

[0051] The presentation unit 114 presents to each user each of the multiple second movement routes calculated by the calculation unit 112. For example, the presentation unit 114 may display information content such as a map showing the second movement route on a display unit of an information terminal associated with the user or a display unit of an in-vehicle terminal provided in the vehicle 10 associated with the user.

[0052] The storage unit 120 is a main storage device such as a RAM or a ROM, an EPROM, a hard disk drive, and an auxiliary storage device such as a removable medium. An operating system (OS), various programs, various tables, and the like are stored in the auxiliary storage device, and by executing the programs stored therein, each function that matches the predetermined purpose of each part of the control unit 110 can be realized. However, some or all of the functions may be realized by a hardware circuit such as an ASIC or an FPGA.

[0053] The storage unit 120 stores data and the like used or generated in the processing performed by the control unit 110. The storage unit 120 may also temporarily store information indicating the preferences of each user acquired from an external device, such as an information terminal, associated with the user, or from the vehicle 10, etc., associated with the user.

[0054] The communication unit 130 is configured with a communication circuit that performs wireless communication. The communication unit 130 may be, for example, a communication circuit that performs wireless communication using 4G (4th Generation) or a communication circuit that performs wireless communication using 5G (5th Generation). The communication unit 130 may also be a communication circuit that performs wireless communication using LTE (Long Term Evolution) or a communication circuit that performs wireless communication using LPWA (Low Power Wide Area). The communication unit 130 may be a communication circuit that performs communication using a standard wireless communication area (Wi-Fi).

[0055] Next, a specific description will be given of the processing performed by the server device 100. Fig. 3 is a flowchart of the processing executed by the control unit 110 of the server device 100 according to the embodiment.

[0056] For example, the server device 100 may start the process shown in FIG. 3 when a trigger is received from an information terminal associated with a user or from the vehicle 10 associated with a user.

[0057] First, in step S10, the acquisition unit 111 acquires information on the departure point and destination of each user, and information indicating a preference for a travel route. The acquisition unit 111 may acquire the above information by communicating with an information terminal associated with the user or a vehicle 10 associated with the user via the communication unit 130. Alternatively, the server device 100 may acquire the above information input from an input terminal connected to the server device 100.

[0058] At the same time, the acquisition unit 111 may generate road network information from existing map data. For example, the acquisition unit 111 may estimate information on the travel time and fuel consumption cost corresponding to a point for each link on the road network from past driving information of a plurality of vehicles 10 and road gradient information, etc., and associate the information with each link. In addition, for example, the acquisition unit 111 may calculate information on the road width and the number of facilities on the road in the road network based on information acquired from an external device.

[0059] The acquisition unit 111 may generate road network information for each day of the week or each time period, or may individually generate a road network when a traffic regulation is issued. The acquisition unit 111 may generate a road network using machine learning. For example, the acquisition unit 111 acquires driving information of the vehicle 10 when the latest traffic regulation is issued, and calculates a first feature amount for the number of vehicles passing for each time period or each link. Then, the acquisition unit 111 calculates a second feature amount that is a feature amount when a similar traffic regulation is issued in the past. The acquisition unit 111 trains a clustering model using the second feature amount as an input, and inputs the first feature amount to the clustering model. Then, the acquisition unit 111 calculates a cluster corresponding to the first feature amount, and obtains driving information when a similar traffic regulation is issued in the past, which corresponds to the feature amount belonging to the corresponding cluster. Then, the acquisition unit 111 may estimate a travel time or a cost of fuel consumption in each link from the driving information when a similar traffic regulation is issued in the past.

[0060] Next, in step S11, the calculation unit 112 calculates a first movement route using the preferences of each user. For example, the calculation unit 112 may calculate a first movement route for each user that satisfies the preferences of each user. The first movement route is calculated for each user. The first movement route may be calculated as a solution to a multi-objective optimization problem in which the sum of the costs of each item of the preferences of each user is set as an objective function, and the positions of the departure point, intermediate points, and destination are set as constraint functions.

[0061] The following may be adopted as the cost of each item of each user's preference: (i) a weight for fuel consumption multiplied by the sum of the fuel consumption of each link on the travel route to be calculated, (ii) a weight for travel time multiplied by the sum of the travel time of each link on the travel route to be calculated, (iii) a weight for the number of facilities on the travel route to be calculated multiplied by the sum of the number of facilities on each link on the travel route, and (iv) a weight for road width multiplied by the average road width of each link on the travel route to be calculated.

[0062] The calculation unit 112 may calculate, as the first travel route, a travel route that minimizes the sum of the costs of each item based on a predetermined weight for each item of the user's preferences.

[0063] Next, in step S12, the calculation unit 112 determines whether or not the same travel route is calculated for multiple users in a manner that exceeds a predetermined criterion. The calculation of the same travel route in a manner that exceeds a predetermined criterion may mean that a predetermined number or more of the same travel routes, in which both the starting point and the destination match, are calculated for multiple users. Alternatively, the calculation of the same travel route in a manner that exceeds a predetermined criterion may mean that a predetermined number or more of travel routes, in which at least one of the starting point and the destination does not match, are calculated for multiple users, and at least one of the travel routes is at least partially overlapping. The above-mentioned predetermined number may be determined based on the capacity of the road, for example.

[0064] In this step, a positive determination is made when the calculation unit 112 determines that the same movement route has been calculated for a plurality of users in a manner that exceeds a predetermined criterion.

[0065] If the determination in this step is positive, the process proceeds to step S13.

[0066] If the determination in this step is negative, the process proceeds to step S15.

[0067] When the process proceeds to step S13, the correction unit 113 corrects the preferences of each user. The process of correcting the preferences of each user by the correction unit 113 will be described in detail later.

[0068] Next, in step S14, the calculation unit 112 calculates a second movement route using the corrected preference. The second movement route is a movement route that has a common starting point and destination with the first movement route. The second movement route is calculated for each user. The second movement route may be calculated as a solution to a multi-objective optimization problem, similar to the first movement route.

[0069] For example, the calculation unit 112 may calculate, as the second travel route, a travel route that minimizes the sum of the costs of each item based on the corrected weight for each item of the user's preferences. Also, for example, the calculation unit 112 may calculate, as the second travel route, a travel route that maximizes the reduction in the cost of each item with respect to the reference travel route. Specifically, the calculation unit 112 may calculate, as the second travel route, a travel route that maximizes the reduction in the cost related to the fuel consumption and travel time included in the items of the preferences that each user individually values. At this time, the preferences of each user may be reflected as to whether the reduction in the fuel consumption or the reduction in the travel time is to be emphasized.

[0070] Next, in step S15, the presentation unit 114 presents the second movement route calculated by the calculation unit 112 to each user. For example, the presentation unit 114 displays information indicating the second movement route on an information terminal associated with the user, or an in-vehicle terminal of the vehicle 10 associated with the user. Alternatively, the presentation unit 114 may output information indicating the second movement route by voice from an information terminal associated with the user, or an in-vehicle terminal of the vehicle 10 associated with the user. Note that, if a positive determination is made in step S12 and the process transitions to step S15, the presentation unit 114 presents the first movement route to each user.

[0071] The presentation unit 114 may receive feedback on the second movement route from the user after step S15. For example, the presentation unit 114 may receive feedback from the user that the second movement route requires a lower fuel consumption or a shorter travel time.

[0072] As a result, when the travel routes calculated for each user overlap among the users beyond a predetermined criterion, the server device 100 can correct the preferences of the multiple users and recalculate the travel routes using the corrected preferences. In other words, the server device 100 can distribute the travel routes calculated for each user. Therefore, the server device 100 can suppress excessive overlap of proposed routes to each user in route guidance for multiple users.

[0073] Next, the process of correcting preferences performed by the correction unit 113 of the control unit 110 of the server device 100 will be described. Specifically, the correction unit 113 corrects weights for at least some items among values ​​indicating user preferences so as to emphasize differences in preferences among a plurality of users. FIG. 4 is a flowchart of the process of correcting weights so as to emphasize differences, which is executed by the control unit 110 of the server device 100 according to the embodiment. The process described in FIG. 4 is a detailed description of the process of step S13 described in FIG. 3.

[0074] First, in step S20, the correction unit 113 compares the values ​​indicating the preferences of each user between the users. The correction unit 113 may calculate tendencies between items included in the values ​​indicating the preferences of each user, and compare the tendencies between the users.

[0075] Next, in step S21, the correction unit 113 corrects the weighting for each item of the value indicating preference so as to emphasize the difference between the values ​​indicating preference among the users. Here, the weighting for each item of the value indicating preference is the weighting used in the calculation when the calculation unit 112 calculates the first movement route and the second movement route. The correction unit 113 corrects the weighting for each item of the value indicating preference used when the calculation unit 112 calculates the first movement route, and sets it as the weighting for each item of the value indicating preference used when the calculation unit 112 calculates the second movement route.

[0076] For example, the correction unit 113 evaluates the magnitude of difference between users for each item of the values ​​indicating preferences. The evaluation of the difference may be performed based on, for example, standard deviation, variance, or the difference between the maximum value and the minimum value. Then, the correction unit 113 corrects the weight for each item in order so that the weight for the item with the largest difference is the largest for each user.

[0077] Consider a case where user 1's (preference for low fuel consumption, preference for short travel time, preference for wide road width)=(10,7,2) and user 2's corresponding preferences are (9,8,3). Specifically, the correction unit 113 may correct the original user 1's (weight for low fuel consumption, weight for short travel time, weight for wide road width)=(100,70,20) to (150,35,20). And the correction unit 113 may correct the original user 2's (weight for low fuel consumption, weight for short travel time, weight for wide road width)=(90,80,30) to (80,60,30).

[0078] Also, for example, consider a case where user 1 and user 2 have the same level of preference for fuel consumption, route 2 has the same level of cost for fuel consumption as route 1, and has a lower cost for travel time than route 1. In this case, the correction unit 113 may correct the weights for the preference values ​​of a user with a weak preference for travel time so that the weight for travel time becomes relatively smaller.

[0079] At this time, the correction unit 113 may use grid search or reinforcement learning based on past driving information or a history of travel route proposals, etc. to calculate a range of weight values ​​that will output reasonable results in advance, and change the weights within that range.

[0080] Moreover, the correction unit 113 may determine the weight for each item of the value indicating the preference by using a method of contrastive learning or heuristic analysis.

[0081] In this way, the server device 100 can correct the weights for the values ​​indicating the preferences so that the differences in the preferences of each user for the travel route become more prominent. Therefore, the server device 100 can prevent the proposed routes for each user from overlapping excessively without deviating from the preferences of each user for the travel route.

[0082] Next, a process of calculating a value indicating a user's preference by the calculation unit 112 of the control unit 110 of the server device 100 will be described. Fig. 5 is a flowchart of the process of calculating a value indicating a preference executed by the control unit 110 of the server device 100 according to the embodiment. The process described here may be executed instead of the process of acquiring the user's preference, which is executed in step S10 described in Fig. 3.

[0083] First, in step S30, the calculation unit 112 extracts a plurality of users who have passed through the same starting point and destination. The calculation unit 112 may extract the users based on travel information acquired from a plurality of vehicles.

[0084] Next, in step S31, the calculation unit 112 calculates the number of users extracted in step S40. The calculation unit 112 calculates the costs of each of the travel routes selected by the multiple users, with respect to multiple items of the characteristics of the travel route, and compares the costs between the users for each item.

[0085] Next, in step S32, the calculation unit 112 calculates a value indicating the preference of each user relatively among the multiple users. The calculation unit 112 determines a value indicating the preference of each user for each item so as to reflect the result of the comparison of the costs related to the multiple items among the users in step S31.

[0086] In this way, the server device 100 can determine a value indicating the preference of each user by reflecting the difference in the characteristics of the routes selected by each user in the past. Therefore, the server device 100 can calculate a value indicating the preference that can propose a travel route that meets the needs of the user.

[0087] In FIG. 5, a process for calculating a value indicating each user's preference based on the user's past travel route has been described. In contrast, when requests are received directly from each user, it is possible to calculate a value indicating each user's preference by a simpler process. Therefore, a process for calculating a value indicating each user's preference based on the results of a questionnaire given to the users will be described. The process described here may be executed instead of the process of acquiring the user's preference, which is performed in step S10 described in FIG. 3. Also, the process described below may be executed instead of the process described in FIG. 6.

[0088] First, the acquisition unit 111 acquires the results of a questionnaire regarding preferences for travel routes from each user. The acquisition unit 111 may conduct a questionnaire regarding preferences for travel routes via an information terminal associated with the user or an in-vehicle terminal provided in a vehicle associated with the user, and acquire the input answers. For example, the answers may be input as numerical values ​​for each item of preferences for travel routes.

[0089] Next, the calculation unit 112 calculates a value indicating the preference of each user based on the survey results acquired by the acquisition unit 111. The calculation unit 112 may determine the value indicating the preference of each user by reflecting the distribution of the numerical values ​​of the answers.

[0090] This allows the server device 100 to calculate a value indicating a preference that directly reflects the user's desires.

[0091] In the above description, the process of calculating a value indicating the preference of each user based on the user's past movement route and the process of calculating a value indicating the preference of each user based on the result of a questionnaire to the user have been described. In contrast to this, it is possible to estimate the preference of each user not only from the user's past movement history but also from the user's overall past behavior history. Therefore, the process of calculating a value indicating the preference of each user based on the user's past behavior history will be described. Here, the process described may be executed instead of the process of acquiring the user's preferences, which is performed in step S10 described in FIG. 3. In addition, the process described below may be executed instead of the process described in FIG. 6 and the process of calculating a value indicating the preference of each user based on the result of a questionnaire to the user.

[0092] First, the acquisition unit 111 acquires a past behavior history from each user. The acquisition unit 111 may acquire the past behavior history of each user from an information terminal associated with the user or a vehicle 10 associated with the user. Typically, the past behavior history may be acquired from past driving information of each user.

[0093] Next, the calculation unit 112 clusters the information on the past behavior history. Then, the calculation unit 112 calculates each index, such as the average value and variance value of the fuel consumption or travel time per unit time in one trip, or the average value and variance value of the number of facility stops in one trip, in each cluster. Then, the calculation unit 112 may assign a score to each item of the value indicating the preference for each cluster based on the calculated index. The value indicating the preference of each user is the value indicating the preference assigned to the cluster to which each user belongs. Here, a neural network may be used for the clustering.

[0094] This allows the server device 100 to calculate a value indicating a preference inferred from the user's behavior history.

[0095] Second Embodiment In the first embodiment, an example was described in which the correction unit 113 corrects the weighting of the value indicating the user's preference so as to emphasize the difference in preference between a plurality of users. In contrast, a case is assumed in which only a specific travel route is calculated even though there is a travel route that can be an alternative. In order to deal with such a case, in the second embodiment, the correction unit 113 corrects the weighting of the value indicating the user's preference according to the characteristics of the alternative route. In this way, when there are a plurality of candidate travel routes, the server device 100 can disperse the travel routes to be proposed. FIG. 6 is a flowchart of a process of correcting the weighting of an item with a relatively low cost, which is executed by the control unit 110 of the server device 100 according to the embodiment. The process described in FIG. 6 is a detailed description of the process of step S13 described in FIG. 3, and is a process that replaces step S21 and step S22 in FIG. 4.

[0096] First, in step S40, the correction unit 113 extracts a cost that is relatively lower than that of the first moving route among the costs corresponding to a plurality of items of the values ​​indicating the user's preferences in the third moving route. Here, the third moving route is a route that is an alternative to the first moving route. For example, the third moving route may be a moving route in which the cost for the item having the highest value indicating the user's preferences is at the same level as that of the first moving route, and the costs for the other items are different from those of the first moving route. For example, in the third moving route, if the cost related to fuel consumption is at the same level as that of the first moving route, the cost related to travel time is lower than that of the first moving route, and the cost related to road width is higher than that of the first moving route, the cost related to travel time is extracted.

[0097] Next, in step S41, the correction unit 113 corrects the weights for at least some items in the values ​​indicating the user's preferences so that the weights for the items corresponding to the costs extracted in step S40 are relatively larger than the weights for the other items for each user. For example, when a cost related to travel time is extracted for the third travel route, the weight for the travel time is corrected to be larger than the weights for the other items in the values ​​indicating the user's preferences.

[0098] Consider a case where user 1's (preference for low fuel consumption, preference for short travel time, preference for wide road width)=(10,7,2) and user 2's corresponding preferences are (9,8,3). Specifically, the correction unit 113 may correct the original user 1's (weight for low fuel consumption, weight for short travel time, weight for wide road width)=(100,70,20) to (95,90,20). And the correction unit 113 may correct the original user 2's (weight for low fuel consumption, weight for short travel time, weight for wide road width)=(90,80,30) to (87,85,30).

[0099] At this time, the correction unit 113 uses grid search or reinforcement learning based on the past travel information or the history of travel route proposals to determine in advance a range of weight values ​​that will output a valid result. may be calculated and the weight may be changed within that range.

[0100] In addition, when there are a predetermined number or more of candidate travel routes for the third travel route, the correction unit 113 may also perform a process of correcting weights for values ​​indicating user preferences so as to emphasize differences in preferences between a plurality of users, as described in Fig. 4. The same applies when there are a predetermined number or more of items of values ​​indicating user preferences.

[0101] This allows the server device 100 to correct the weighting of the value indicating the user's preference according to the characteristics of the actual alternative route. Therefore, when there are multiple travel routes that match the user's preference but only a specific travel route is calculated as the suggested route, the server device 100 can appropriately distribute the suggested routes to the user. Instead of the above process, the correction unit 113 may extract a relatively low cost from among the costs corresponding to the items of the values ​​indicating the user's preferences in the first movement route, compared to the other movement routes. Then, the correction unit 113 may weight the extracted item higher than the weights for the other items.

[0102] Third embodiment In the first embodiment, an example was described in which the correction unit 113 corrects the weighting of the value indicating the user's preference so as to emphasize the difference in preference between a plurality of users. Then, in the second embodiment, an example was described in which the correction unit 113 corrects the weighting of the value indicating the user's preference in accordance with the characteristics of an alternative route. In contrast, in the third embodiment, an example is described in which a travel route in which the travel time cost or the fuel consumption cost is optimized is guided to all users. In the third embodiment, the correction unit 113 corrects the weighting of the value indicating the user's preference so as to emphasize the preference for fuel consumption and the preference for travel time.

[0103] The correction unit 113 corrects the weights for the values ​​indicating the preferences so that the weights for fuel consumption, travel time, and the preference items that each user individually values ​​are greater than the weights for the other items. The correction unit 113 may change the magnification of the correction of the weights for each item of the values ​​indicating the preferences for each item.

[0104] (Modification) The above-described embodiment is merely an example, and the present disclosure can be modified and implemented as appropriate without departing from the spirit and scope of the present disclosure.

[0105] For example, the processes and means described in this disclosure can be freely combined and implemented as long as no technical contradiction occurs.

[0106] Furthermore, a process described as being performed by one device may be shared and executed by multiple devices. Alternatively, a process described as being performed by different devices may be executed by one device. In a computer system, the hardware configuration (server configuration) by which each function is realized can be flexibly changed.

[0107] The present disclosure can also be realized by supplying a computer program implementing the functions described in the above embodiments to a computer, and having one or more processors of the computer read and execute the program. Such a computer program may be provided to the computer by a non-transitory computer-readable storage medium connectable to the system bus of the computer, or may be provided to the computer via a network. The non-transitory computer-readable storage medium may be, for example, any type of disk, such as a magnetic disk (floppy disk, hard disk drive (HDD), etc.), an optical disk (CD-ROM, DVD disk, Blu-ray disk, etc.), a read-only medium, etc. This includes read only memory (ROM), random access memory (RAM), electronic programmable read only memory (EPROM), electronic data read only memory (EEPROM), magnetic cards, flash memory, optical cards, and any type of medium suitable for storing electronic instructions. [Explanation of symbols]

[0108] 10. Vehicle 100 Server device 110... Control unit 111...Acquisition part 112... Calculation section 113... Correction section 114...Presentation part 120...Storage section 130 Communications Department

Claims

1. Acquiring preferences of each of a plurality of users regarding a travel route; calculating, for each of the users, a first movement route using the preferences of each of the users; When the first movement route overlaps with the first movement route beyond a predetermined criterion, the preferences among the plurality of users are corrected, and a second movement route is calculated using the corrected preferences; and presenting the calculated second movement routes to each of the users. Information processing device.

2. The control unit is calculating values ​​indicating the preferences for a plurality of items for each of the plurality of users; If the first movement path overlaps beyond a predetermined criterion, The weights for at least some of the items are corrected so as to emphasize differences in preferences among the plurality of users, and a second movement route is calculated using the corrected weights. The information processing device according to claim 1 .

3. The control unit is calculating values ​​indicating the preferences for a plurality of items for each of the plurality of users; If the first movement path overlaps beyond a predetermined criterion, extracting a cost that is relatively lower than the first moving path among the costs corresponding to the plurality of items in a third moving path that is an alternative to the first moving path; correcting weights for at least some of the items so that the weights for the items corresponding to the extracted costs are relatively larger than the weights for the other items for each of the plurality of users, and calculating a second movement route using the corrected weights. The information processing device according to claim 1 .

4. The control unit is Extracting a plurality of users who have taken different travel routes, departed from the same departure point, and passed through the same destination point; By comparing the costs of the travel routes between the extracted users, a value indicating the preference indicating the degree of the preference of the user is calculated relatively between the multiple users.

4. The information processing device according to claim 1.

5. The control unit is calculating, for each of the plurality of users, a value indicating the degree of the preference of the user based on a survey result for each of the plurality of users; 4. The information processing device according to claim 1.

Images