JP7502968B2 - Recommendation device - Google Patents

Description

This disclosure relates to a recommendation device.

Technology is known that presents a user with travel routes between multiple points specified by the user. Patent Document 1 discloses a notification system that searches for multiple travel methods from a starting point to a destination specified by the user, determines a notification priority for each of the multiple travel methods found, and notifies the user of the travel methods according to the priority determined for each of the multiple travel methods.

JP 2016-211915 A

For example, when a user travels to multiple destinations during a trip, the user may want to know a route that will give the user high satisfaction. There is a need for a method that presents routes that will give the user high satisfaction.

This disclosure describes a recommendation device that can present travel routes that provide high satisfaction to users.

A recommendation device according to one aspect of the present disclosure is a device that presents an optimal combination from among multiple combinations of multiple travel orders that can be used to travel between multiple destinations and multiple means of transportation that can be used between two destinations. This recommendation device includes an acquisition unit that acquires weather information that indicates the weather at the multiple destinations, a determination unit that determines the optimal combination based on the weather information, and a presentation unit that presents recommendation information that indicates the optimal combination.

In this recommendation device, weather information indicating the weather at multiple destinations is acquired, an optimal combination is determined based on the weather information, and recommendation information indicating the optimal combination is presented. It can be said that a user's satisfaction with a combination of a tour order for visiting multiple destinations and a means of transportation between each two destinations varies depending on the weather at the destinations the user visits. According to the above configuration, the weather at the multiple destinations the user visits is taken into consideration and an optimal combination is determined from among the tour order and combinations of means of transportation between each two destinations, so that a combination that provides high user satisfaction can be determined as an optimal combination (route). Therefore, a route that provides high satisfaction to the user can be presented.

This disclosure makes it possible to present a route that will provide high satisfaction to the user.

FIG. 1 is a schematic configuration diagram of a recommendation system including a recommendation server according to an embodiment. FIG. 2 is a diagram showing an example of behavioral information stored in the behavioral information DB shown in FIG. FIG. 3 is a diagram showing an example of node information stored in the node information DB shown in FIG. FIG. 4 is a diagram showing an example of edge information stored in the edge information DB shown in FIG. FIG. 5 is a block diagram showing a functional configuration of the recommendation server shown in FIG. FIG. 6 is a flowchart showing a series of processes of the recommendation method performed by the recommendation server shown in FIG. FIG. 7 is a diagram showing an example of multiple destinations. FIG. 8 is a diagram showing examples of multiple order candidates. FIG. 9 is a flowchart showing the calculation process of FIG. 6 in detail. FIG. 10 is a diagram showing an example of a screen displayed on the terminal device shown in FIG. FIG. 11 is a diagram illustrating a hardware configuration of the recommendation server illustrated in FIG.

Embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements will be designated by the same reference numerals, and duplicate descriptions will be omitted.

The configuration of a recommendation system 1 according to one embodiment will be described with reference to Figures 1 to 4. Figure 1 is a schematic diagram of a recommendation system 1 including a recommendation device 80 according to one embodiment. Figure 2 is a diagram showing an example of behavior information stored in the behavior information DB 20 shown in Figure 1. Figure 3 is a diagram showing an example of node information stored in the node information DB 30 shown in Figure 1. Figure 4 is a diagram showing an example of edge information stored in the edge information DB 40 shown in Figure 1.

The recommendation system 1 shown in FIG. 1 is a system that presents an optimal combination from among multiple combinations of multiple tour orders and multiple means of transportation available between two destinations. The tour order is the order in which a user U visits multiple destinations. The means of transportation are means that can be used to travel between two destinations that are adjacent to each other in the tour order. The multiple destinations are located within a range in which the user U can visit each destination. Each destination is, for example, a tourist spot that the user U stops at when traveling. Examples of destinations include art galleries, parks, museums, and shrines. Examples of means of transportation include walking, rental bicycles, trains, taxis, and buses. Hereinafter, the section between two destinations that are adjacent to each other in the tour order may simply be referred to as a "section." The recommendation system 1 presents, for example, a combination of a tour order when a user U visits multiple tourist spots while traveling and a means of transportation for each section.

When touring multiple destinations, for example, in the case of three destinations A to C, multiple candidates for the tour order (hereinafter referred to as "multiple candidate orders") can be considered, such as "Destination A → Destination B → Destination C", "Destination A → Destination C → Destination B", etc. When moving between each section, multiple candidates for transportation means can be considered, such as walking, bus, and taxi. Therefore, the recommendation system 1 uses a method described later to present an optimal combination as a tour route from multiple combinations of multiple candidate orders and multiple candidate transportation means. The candidate orders are candidates for the tour order. The candidate transportation means are transportation means that can be taken (used) in the section. The candidate transportation means differ depending on the section. Specifically, the candidate transportation means between destinations A and B are walking, rental bicycles, and taxis, and the candidate transportation means between destinations B and C are walking, buses, trains, and taxis, and the transportation means that can be taken for each section are the candidate transportation means.

In the recommendation system 1, a graph from graph theory and the concept of utility are used to determine a tour route. A graph is composed of a set of nodes and a set of edges. The nodes correspond to the starting point, destination, and return point. Each order candidate is represented by the order in which the nodes are arranged. Between the nodes are edges. There are multiple edges (i.e., multiple candidate means of transportation) between each node.

In the recommendation system 1, a first utility is calculated for each node, and a second utility is calculated for each edge. The first utility indicates the user U's satisfaction with the destination (node). The second utility indicates the user U's satisfaction with the means of transportation (edge). Then, in the recommendation system 1, an optimal combination is determined based on the first utility and the second utility. Details of the method for determining the optimal combination will be described later.

The recommendation system 1 includes one or more terminal devices 10, a behavioral information DB 20, a node information DB 30, an edge information DB 40, a tourist destination information DB 50, a weather information DB 60, a traffic information DB 70, and a recommendation device 80. The recommendation device 80 is configured to be able to communicate with one or more terminal devices 10, the behavioral information DB 20, the node information DB 30, the edge information DB 40, the tourist destination information DB 50, the weather information DB 60, and the traffic information DB 70 via a network. The network may be either wired or wireless. Examples of the network include a mobile communication network, the Internet, and a WAN (Wide Area Network). In the following description, the description focuses on one terminal device 10, but the same applies to the other terminal devices 10.

The terminal device 10 is used by a user U. Examples of the terminal device 10 include mobile terminals including smartphones and tablet terminals. The terminal device 10 stores the user U's place of residence and travel preference information related to the user U's travels. The travel preference information is, for example, responses to a questionnaire about travel preferences that are input in advance by the user U into the terminal device 10.

The terminal device 10 manages the schedule (plans) of the user U using an application such as a scheduler, and generates destination candidate information. The user U may input the schedule, or the application may input a schedule detected from an email or the like. The schedule information includes the location where the schedule will take place, including the destinations (tourist attractions) that the user U plans to visit, and the future date and time when the schedule will take place. The destination candidate information is used in the process of determining the decided destination information, which will be described later.

The terminal device 10 acquires destination candidates based on the schedule information. Specifically, the terminal device 10 acquires destination candidates by, for example, transmitting input schedule information to an external server or the like and receiving information indicating destinations that the user U plans to visit from the external server or the like. The terminal device 10 then generates destination candidate information indicating the destination candidates and transmits the destination candidate information to the recommendation device 80. Note that if the terminal device 10 does not acquire destination candidates based on the schedule information, for example, if the schedule information does not include a destination that the user U plans to visit, the terminal device 10 does not generate destination candidate information. The terminal device 10 transmits travel preference information and destination candidate information to the recommendation device 80 each time a recommendation process described below is performed.

The terminal device 10 generates recommendation condition information. The recommendation condition information indicates the departure point and departure time from which the user U departs, multiple destinations to which the user U will travel, and the return point and return time to which the user U will return. The recommendation condition information is obtained when the user U executes an application for recommending a travel route on the terminal device 10 and specifies each of the above items in the application. The terminal device 10 transmits the recommendation condition information to the recommendation device 80 each time the user U specifies each of the above items.

The terminal device 10 generates user setting information. The user setting information is information indicating a number of setting items specified by the user U in an application for recommending travel routes. The multiple setting items are information indicating the user U's preferred method of travel when traveling between multiple destinations. Specifically, the multiple setting items include an acceptable walking range, information on the means of transportation used, priority cost information, and priority items.

The allowable walking range is the allowable range of time or distance for user U to travel on foot. The allowable walking range is obtained by user U setting, for example, "X minutes" and "Ym". Note that, for the process of determining the allowable walking time described later, when user U sets the allowable walking range as "Ym", the terminal device 10 converts "Ym" into a value obtained by dividing a predetermined speed, for example, "80 m/min" (i.e., a value obtained by converting distance into time). The information on the transportation means used is the transportation means specified by user U. Examples of the transportation means specified by user U include, for example, walking, train, bus, taxi, and rental bicycle. The information on the transportation means used is obtained by user U specifying the transportation means. User U can specify multiple transportation means.

The priority cost information is information that indicates whether user U prioritizes money or time. "User U prioritizes money" means that user U prioritizes travel with a smaller money cost. "User U prioritizes time" means that user U prioritizes travel with a smaller time cost. The priority cost information is obtained by user U selecting either money or time.

The priority items are matters that the user U prioritizes when traveling between multiple destinations. Specifically, the priority items include scenery, an abundance of restaurants, and an abundance of shops. Designating scenery as a priority item means that the user U prioritizes traveling by a means of transportation that takes a route that allows for enjoying the scenery. For example, when traveling along the coast between two destinations, examples of means of transportation that allow for enjoying the scenery include walking and rental bicycles. Designating an abundance of restaurants as a priority item means that the user U prioritizes traveling by a means of transportation that takes a route that allows for enjoying the scenery. Designating an abundance of shops as a priority item means that the user U prioritizes traveling by a means of transportation that takes a route that allows for enjoying the restaurants. Designating an abundance of shops as a priority item means that the user U prioritizes traveling by a means of transportation that takes a route that allows for enjoying the shops. An example of a shop is a souvenir shop in a tourist spot. The priority items are obtained by designation by the user U. The user U can designate multiple priority items. The terminal device 10 transmits the user setting information to the recommendation device 80 every time it generates user setting information.

The terminal device 10 generates behavioral information of the user U. The behavioral information is information about the behavior performed by the user U using the terminal device 10. The behavioral information is generated based on information stored in the terminal device 10.

For example, the terminal device 10 stores the history of user U's use of rental bicycles, taxis, and restaurants, and the history of user U's purchases of products. The history of user U's use of rental bicycles, etc., and the history of user U's purchases of products are obtained by user U making payments using a payment application installed on the terminal device 10. The terminal device 10 stores information that can identify the restaurants used by user U, and information that can identify the stores from which user U purchased products. The terminal device 10 stores the period during which user U has continuously walked. The period during which user U has continuously walked is obtained by user U walking continuously using a pedometer application installed on the terminal device 10.

The terminal device 10 stores information indicating that the user U has participated in a campaign. The information indicating that the user U has participated in a campaign is obtained by participating in the campaign using a campaign participation application installed in the terminal device 10. The campaign is a campaign that provides the user U with monetary benefits, such as points having monetary value and discount coupons. The terminal device 10 then generates behavioral information based on information regarding the behavior performed by the user U using the terminal device 10 during a target period (e.g., one year). The terminal device 10 generates behavioral information each time the target period elapses. Details of the behavioral information will be described later. For example, the terminal device 10 transmits behavioral information to the behavioral information DB 20 each time it generates behavioral information.

The behavioral information DB20 is a database that stores behavioral information of each user U. As shown in FIG. 2, the behavioral information includes a user ID, walking information, the number of times a rental bicycle was used, the number of times a taxi was used, the number of times a campaign was participated in, the number of times a product was purchased, and the number of times a restaurant was used. The user ID is information that allows the user U to be uniquely identified. The walking information indicates the third quarter of the period during which the user U walked continuously during the target period. The number of times a rental bicycle was used indicates the number of times the user U used a rental bicycle during the target period. The number of times a taxi was used indicates the number of times the user U used a taxi during the target period. The number of times a campaign was participated in indicates the number of times the user U participated in a campaign during the target period.

The number of product purchases indicates the number of times that user U purchased a product while traveling. As an example, the number of product purchases is the average number of times that user U purchased a product on the days that user U is estimated to have traveled during the target period. For example, the terminal device 10 obtains the location of the store from an external server (not shown) based on the identification information of the store where user U made payment, and if the residence of user U stored in the terminal device 10 is separated by a predetermined distance or more from the location of the store, it is determined that user U purchased a product while traveling. Then, the number of product purchases is obtained according to the number of times that user U is determined to have purchased a product while traveling by the terminal device 10. Note that the number of product purchases is not limited to the above example, and may be, for example, the median number of times that user U purchased a product on the days that user U is estimated to have traveled during the target period.

The number of times a restaurant is used indicates the number of times that the user U used a restaurant during the trip. As an example, the number of times a restaurant is used is the average number of times that the user U used a restaurant on the days on which the user U is estimated to have traveled during the target period. For example, the terminal device 10 acquires the location of the restaurant from an external server (not shown) based on the identification information of the restaurant where the user U paid, and if the residence of the user U stored in the terminal device 10 is separated by a predetermined distance or more from the location of the restaurant, it is determined that the user U used a restaurant during the trip. Then, the number of times the restaurant is used is obtained according to the number of times that the terminal device 10 determines that the restaurant was used. Note that the number of times a restaurant is used is not limited to the above example, and may be, for example, the median number of times that the user U used a restaurant on the days on which the user U is estimated to have traveled during the target period. Note that the behavior information further includes identification information of the store where the user U paid and identification information of the restaurant. The identification information of the store and the identification information of the restaurant are used in the process for identifying the location of the store and the restaurant, which will be described later.

When the behavior information DB 20 receives behavior information of the user U from each terminal device 10, it updates the behavior information of the user U. The behavior information DB 20 stores behavior information for each terminal device 10 (user U).

The node information DB30 is a database that stores node information. As shown in FIG. 3, the node information includes a destination name/start point name/return point name, a node ID, location information, and a first utility function. The destination name is the name of the destination. The node ID is information that can uniquely identify a node. The node corresponds to the destination. The location information indicates, for example, the absolute location of the destination. The first utility function is a function for calculating the first utility. The first utility function differs for each node (destination). Details of the first utility function and the first utility will be described later. The node information DB30 stores node information for each node.

The node information DB 30 also includes node information for points corresponding to the departure point or return point (hereinafter referred to as "departure point/return point"). The departure point/return point node information includes the departure point/return point name, node ID, and location information, but does not include a first utility function. The departure point name/return point name are the names of the departure point/return point. The nodes corresponding to the departure point/return point are dummy nodes for which the first utility described below is not calculated. The departure point/return point node information is used in the process of estimating the visiting time, etc., described below.

The edge information DB40 is a database that stores edge information. As shown in FIG. 4, the edge information includes an edge ID, a section node ID, a means of transportation, and a second utility function. The edge ID is information that can uniquely identify an edge. The section node ID indicates two nodes that correspond to the two end points of the edge indicated by the edge ID. The edge indicated by the edge ID corresponds to the area between the two destinations (i.e., the section). In the following description of nodes and edges, the nodes and destinations are referred to as "nodes", and the edges and sections are referred to as "edges". In the following description of nodes and edges, the node indicated by the node ID "N1" is referred to as "node N1", the edge indicated by the edge ID "E1" is referred to as "edge E1", and the two nodes indicated by the section node ID "N1-N2" are referred to as "nodes N1-N2". Note that N1 and N2 indicate any node ID, and E1 indicates any edge ID.

The means of transportation is the means of transportation of the edge indicated by the edge ID. For example, if the edge information includes a section node ID indicating nodes b-c and a means of transportation indicating a railway, it means that it is possible to travel between nodes b and c by railway. "Able to travel" means, for example, that if a first station is located near node b and a second station is located near node c, it is possible to travel between the first and second stations within a specified time (for example, within a few tens of minutes). In other words, each edge information between two nodes generally includes a means of transportation corresponding to a means of transportation that user U can take to travel. There are multiple means of transportation available between two nodes. In other words, when multiple edge information including the same section node ID is looked at, a different edge ID is assigned to each means of transportation.

The second utility function is a function for determining the second utility. The second utility function differs for each edge. Details of the second utility function and the second utility will be described later. As an example, as shown in FIG. 4, each of the edges AB1 and AB2 indicates an edge between the nodes a and b. The second utility function g _AB1 included in the edge AB1 is a second utility function when the means of transportation for traveling between the nodes a and b is walking. The second utility function g _AB2 included in the edge AB2 is a second utility function when the means of transportation for traveling between the nodes a and b is a rental cycle. In other words, there are two possible means of transportation for traveling between the nodes a and b (i.e., walking and a rental cycle). The edge information DB 40 stores edge information for each edge.

The edge information DB 40 also contains edge information between departure points and destination points, and between destination points and return points. As with edge information between destination points, this edge information contains an edge ID, a section node ID, a means of transportation, and a second utility function. Edge information between nodes departure points and destination points, and between destination points and return points, is used in the process of estimating visiting times, etc., which will be described later.

The tourist destination information DB50 is a database that stores tourist destination information, area scenery information, and route scenery information (scenery information). The tourist destination information is information about multiple tourist destinations including multiple destinations. The tourist destination information includes location information, attribute information, average stay time of tourists visiting the tourist destination, and tourist scenery information for each of the multiple tourist destinations. The area scenery information includes information indicating the quality of scenery for each tourist area. The route scenery information includes information indicating the quality of scenery for each of the multiple destinations for traveling between the two destinations. The information indicating the quality of scenery included in the route scenery information is stored by time period. The information indicating the quality of scenery is, for example, a degree of the quality of scenery (hereinafter referred to as "scenery quality degree"), which is higher for better scenery and lower for worse scenery. When there is a change in the average stay time of a tourist destination, the tourist destination information is updated.

The weather information DB 60 is a database that stores weather information. The weather information includes information indicating the weather at multiple destinations that the user U visits. Specifically, the weather information is a weather forecast for the multiple destinations every few hours. The weather information may indicate the overall weather for an area that includes all of the departure point, destination, and return point, or may indicate the weather for each divided area into which the area is divided. The weather information is updated every time a specified period of time has passed.

The traffic information DB70 is a database that stores traffic information. The traffic information includes transportation facility information, status information, delay information, and fare information. The transportation facility information is information that indicates the transportation facility. Examples of transportation facilities include railways, buses, and roads. The status information is information that indicates the status of the transportation facility. For example, if the transportation facility is normal, the status information indicates normal. If there is a delay in the railway, the status information indicates a delay. If there is congestion on the road, the status information indicates a congestion. If there is a delay in the railway, etc., the delay information indicates the delay from the normal operating time. The fare information indicates a fare table that indicates the fare for using each transportation facility. The traffic information further includes information such as a timetable used for route search. If there is a change in the status or delay time of the transportation facility, the traffic information is updated.

The recommendation device 80 is a device that presents the optimal combination. An example of the recommendation device 80 is an information processing device such as a server device. In this embodiment, the tour route is determined by reflecting the travel preferences of the user U. Specifically, the recommendation device 80 determines the tour route in either the first mode or the second mode described below, and presents the determined tour route.

The first mode is a mode in which the behavioral information stored in the behavioral information DB 20 is reflected in the determination of the tour route as the user U's preference information during the trip. In the first mode, the recommendation device 80 acquires the user U's behavioral information from the behavioral information DB 20. The second mode is a mode in which the user setting information set by the user U via the terminal device 10 is reflected in the determination of the tour route as the user U's preference information during the trip. In the second mode, the recommendation device 80 receives the user setting information from the terminal device 10. The first mode and the second mode are determined, for example, by the user U specifying the mode in advance via the terminal device 10. A detailed explanation of the first mode and the second mode will be given later.

The functional configuration of the recommendation device 80 will be described with reference to FIG. 5. FIG. 5 is a block diagram showing the functional configuration of the recommendation device 80 shown in FIG. 1. As shown in FIG. 5, the recommendation device 80 functionally comprises an acquisition unit 81, a determination unit 82, an acquisition unit 83, a calculation unit 84, a determination unit 85, and a presentation unit 86. The function (operation) of each functional unit will be described in detail in the description of the recommendation method described later, so the function of each functional unit will be briefly described here.

The acquisition unit 81 is a functional unit that acquires travel preference information, destination candidate information, and recommendation condition information. The acquisition unit 81 acquires travel preference information, destination candidate information, and recommendation condition information from the terminal device 10. Hereinafter, the travel preference information, destination candidate information, and recommendation condition information may be collectively referred to as "destination determination information." The acquisition unit 81 outputs the destination determination information to the determination unit 82, and outputs the recommendation condition information to the calculation unit 84.

The determination unit 82 is a functional unit that determines multiple destinations based on the destination determination information. The determination unit 82 determines multiple destinations based on the destination determination information received from the acquisition unit 81. The determination unit 82 outputs information indicating the multiple destinations (hereinafter referred to as "confirmed destination information") to the acquisition unit 83 and the calculation unit 84.

The acquisition unit 83 is a functional unit that acquires various information for utility calculation. Specifically, the acquisition unit 83 acquires recommendation condition information, multiple node information, multiple edge information, tourist destination information, weather information, and traffic information. In the first mode, the acquisition unit 83 further acquires behavioral information.

The acquisition unit 83 acquires recommendation condition information from the terminal device 10. The acquisition unit 83 acquires multiple pieces of node information by referring to the recommendation condition information and the confirmed destination information, and extracting a node corresponding to the departure point (hereinafter referred to as the "departure point node"), multiple pieces of node information corresponding to multiple destinations, and a node corresponding to the return point (hereinafter referred to as the "return point node") from the multiple pieces of node information stored in the node information DB 30.

The acquisition unit 83 acquires multiple pieces of edge information from multiple pieces of edge information stored in the edge information DB 40 by referring to the acquired recommendation condition information and confirmed destination information. Specifically, the acquisition unit 83 acquires edge information for each of all possible pairs of nodes from among the node corresponding to the departure point, all nodes included in the confirmed destination information, and the node corresponding to the return point. Each pair of nodes corresponds to between two destinations. The multiple pieces of edge information are acquired by extracting multiple pieces of edge information for each section indicated by the order candidates.

The acquisition unit 83 refers to the confirmed destination information received from the determination unit 82, and extracts multiple tourist destination information corresponding to multiple destinations from the multiple tourist destination information stored in the tourist destination information DB 50, thereby acquiring multiple tourist destination information. The acquisition unit 83 refers to the confirmed destination information, and extracts multiple route scenery information corresponding to between multiple destinations from the tourist destination information DB 50, thereby acquiring multiple route scenery information. The acquisition unit 83 refers to the confirmed destination information and the location information included in the acquired node information, and extracts weather information for multiple destinations and between multiple destinations from multiple weather information stored in the weather information DB 60, thereby acquiring weather information. The acquisition unit 83 refers to the confirmed destination information and the location information, and acquires traffic information by extracting traffic information for each edge from multiple traffic information stored in the traffic information DB 70, thereby acquiring traffic information.

In the first mode, the acquisition unit 83 acquires behavioral information by extracting behavioral information of the user U from multiple pieces of behavioral information stored in the behavioral information DB 20. In the second mode, the acquisition unit 83 acquires user setting information from the terminal device 10. Hereinafter, the multiple node information, multiple edge information, tourist destination information, weather information, traffic information, behavioral information (in the first mode), and user setting information (in the second mode) may be collectively referred to as "utility calculation information." The acquisition unit 83 outputs the utility calculation information to the calculation unit 84. Note that "between multiple destinations" refers to between multiple nodes corresponding to all of the above node pairs.

The calculation unit 84 is a functional unit that calculates the first utility of each node and the second utility of each edge. The calculation unit 84 calculates the first utility of each node and the second utility of each edge based on the recommendation condition information received from the acquisition unit 81, the confirmed destination information received from the determination unit 82, and the utility calculation information received from the acquisition unit 83. The calculation unit 84 outputs the first utility of each node and the second utility of each edge to the determination unit 85.

The determination unit 85 is a functional unit that determines an optimal combination based on the first utility of each node and the second utility of each edge. The determination unit 85 determines an optimal combination based on the first utility of each node and the second utility of each edge received from the calculation unit 84. The determination unit 85 generates recommendation information indicating the optimal combination and outputs the recommendation information to the presentation unit 86.

The presentation unit 86 is a functional unit that presents recommendation information. The recommendation information is information that indicates an optimal combination. For example, when the presentation unit 86 receives an optimal combination from the determination unit 85, the presentation unit 86 generates recommendation information and outputs the recommendation information to the terminal device 10. In this way, the recommendation information is presented to the user U.

Next, the recommendation method performed by the recommendation device 80 will be described with reference to Figures 6 to 10. Figure 6 is a flowchart showing a series of processes of the recommendation method performed by the recommendation device 80 shown in Figure 1. Figure 7 is a diagram showing an example of multiple destinations. Figure 8 is a diagram showing an example of multiple order candidates. Figure 9 is a flowchart showing the calculation process of Figure 6 in detail. Figure 10 is a diagram showing an example of a screen displayed on the terminal device 10 shown in Figure 1. The series of processes shown in Figure 6 is started, for example, when the recommendation device 80 receives a request for recommending a travel route from a recommendation application in the terminal device 10 of user U.

As shown in FIG. 6, first, the acquisition unit 81 acquires destination determination information (travel preference information, destination candidate information, and recommendation condition information) from the terminal device 10 (step S01). Then, the acquisition unit 81 outputs the destination determination information to the determination unit 82 and outputs the recommendation condition information to the calculation unit 84.

Next, when the determination unit 82 receives the destination determination information from the acquisition unit 81, the determination unit 82 determines multiple destinations based on the destination determination information (step S02). As an example, the determination unit 82 selects multiple destination candidates using multiple methods and determines multiple destinations from the multiple destination candidates. First, the determination unit 82 selects, for example, each of the multiple destinations to be visited by the user U, which are included in the recommendation condition information received from the acquisition unit 81, as a destination candidate.

The determination unit 82, for example, selects destination candidates indicated by the destination candidate information received from the acquisition unit 81 (destination candidate information acquired based on schedule information) as destination candidates. The determination unit 82 also estimates areas of interest of the user U based on the travel preference information received from the acquisition unit 81. The determination unit 82 then refers to the tourist destination information DB 50 and selects, as destination candidates, tourist spots that are located near multiple destinations visited by the user U and that are included in the recommendation condition information and that correspond to the areas of interest of the user U.

Then, the determination unit 82 determines multiple destinations from the selected multiple destination candidates. As an example, the determination unit 82 outputs information indicating the multiple destination candidates to the terminal device 10, thereby causing the terminal device 10 to display the multiple destination candidates. Then, the user U selects some destination candidates from the multiple destination candidates displayed on the terminal device 10. Then, the determination unit 82 determines the multiple destination candidates selected by the user U as the multiple destinations. Note that the method of determining the multiple destinations is not limited to the above example, and the determination unit 82 may, for example, determine only the multiple destinations included in the recommendation condition information as the multiple destinations without extracting the destination candidates. In this case, the processing of step S02 is omitted. Then, the determination unit 82 outputs confirmed destination information indicating the multiple destinations to the acquisition unit 83 and the calculation unit 84.

Then, the acquisition unit 83 acquires information for utility calculation (step S03). The acquisition unit 83 acquires multiple pieces of node information from the node information DB 30 by referring to the recommendation condition information received from the acquisition unit 81 and the confirmed destination information received from the determination unit 82. Specifically, the acquisition unit 83 acquires node information corresponding to the departure point included in the recommendation condition information and node information corresponding to the return point included in the recommendation condition information. In addition, the acquisition unit 83 acquires node information including the destination name corresponding to the destination included in the confirmed destination information for each destination included in the confirmed destination information by referring to the node information DB 30.

Then, the acquisition unit 83 acquires multiple pieces of edge information from the edge information DB 40 by referring to the multiple pieces of acquired node information. Specifically, the acquisition unit 83 acquires edge information for each of all possible pairs of nodes from among the node corresponding to the departure point, all nodes included in the confirmed destination information, and the node corresponding to the return point. However, the pair of the departure point and the return point is excluded from all possible pairs of nodes. In other words, the acquisition unit 83 acquires edge information including section node IDs indicating each of all possible pairs of nodes.

Furthermore, the acquisition unit 83 acquires tourist destination information of multiple destinations and route scenery information between multiple destinations from the tourist destination information DB 50, and acquires weather information for multiple destinations and between multiple destinations from the weather information DB 60. The acquisition unit 83 acquires traffic information between multiple destinations from the traffic information DB 70. In the first mode, the acquisition unit 83 further acquires behavior information of the user U from the behavior information DB 20. In the second mode, the acquisition unit 83 further acquires user setting information from the terminal device 10. Then, the acquisition unit 83 outputs the utility calculation information to the calculation unit 84.

Then, the calculation unit 84 performs a calculation process when it receives the confirmed destination information from the determination unit 82 and the utility calculation information from the acquisition unit 83 (step S04). The first utility is a value indicating the user U's satisfaction with the node. In this embodiment, the first utility varies depending on the visiting time when the user U visits the destination (node) and the weather at the node. The second utility is a value indicating the user U's satisfaction with the means of transportation. In this embodiment, the second utility varies depending on the travel time between two destinations (edges), the travel fare, the weather, the quality of the scenery, the abundance of shops, and the abundance of restaurants.

Here, an example of a method for calculating the first utility and the second utility will be described using a specific example and FIG. 9. Note that the method for calculating the first utility by the calculation unit 84 is common to both the first mode and the second mode. On the other hand, the method for calculating the second utility by the calculation unit 84 differs depending on whether it is the first mode or the second mode.

9, in the calculation process of the first utility and the second utility, the calculation unit 84 first selects one order candidate from among multiple order candidates (step S21). The multiple order candidates are candidates for the order of visiting multiple destinations included in the confirmed destination information. In this embodiment, the multiple order candidates are all possible order candidates when visiting all destinations included in the confirmed destination information. In the specific example shown in FIG. 7 and FIG. 8, multiple destinations A to E are determined as multiple destinations. In FIG. 8, order candidates K1, K2, and K3 included in the multiple order candidates are shown. In the specific example below, for the sake of convenience, it is assumed that destinations A to C are determined as multiple destinations in step S02, and order candidate K1 is selected in step S21. Note that the calculation unit 84 refers to multiple node information, replaces each destination for each order candidate with a node ID, and performs the following processes.

Then, the calculation unit 84 determines all patterns in the selected sequence candidates and estimates the travel period, etc., for each pattern (step S22). "All patterns" here refers to all combinations of multiple transportation mode candidates available in each section of the selected sequence candidates. The calculation unit 84 refers to the selected sequence candidates and the multiple pieces of edge information obtained, and determines all patterns in the selected sequence candidates.

In the specific example of sequence candidate K1, the candidate modes of transportation for the section [start node-node a] are walking and rail, and the candidate modes of transportation for the section [node a-node b] are walking and rental bicycle. The candidate modes of transportation for the section [node b-node c] are walking and rail, and the candidate modes of transportation for the section [node c-destination node] are walking and taxi. Therefore, the calculation unit 84 determines all possible patterns of candidate modes of transportation in the sequence indicated by the selected sequence candidate (node a-node b-node c), such as [start point->railroad->node a->walk->node b->walk->node c->walk->destination], [start point->railroad->node a->walk->node b->walk->node c->taxi->destination], and so on.

Then, the calculation unit 84 calculates the travel time estimated for user U to travel between nodes, the visiting time estimated for visiting the node, the stay time estimated for staying at the node, and the travel period estimated for travel between nodes for each pattern. The travel period indicates the time estimated to depart from one node to the time estimated to arrive at the next node (i.e., the visiting time).

The calculation unit 84 estimates the travel time, visit time, stay time, and travel period for each pattern by referring to the departure point and departure time, and the return point and return time included in the recommendation condition information received from the acquisition unit 81. Below, the method of estimating the travel time, visit time, stay time, and travel period for each pattern will be explained using a specific example of order candidate K1. First, the calculation unit 84 estimates the travel time required to travel the section [departure point-node a] for the candidate transportation means for the section [departure point-node a]. The estimation of the travel time differs depending on the transportation means.

When the candidate transportation means are taxi, train, and bus, the calculation unit 84 estimates the travel time using the departure time, traffic information, and location information included in the node information. The travel time can be estimated using, for example, known technology, and detailed explanation is omitted. In general, the degree of congestion on trains and roads varies depending on the time of day when the user U travels by train or road. Therefore, when the candidate transportation means are taxi, train, and bus, the travel time when traveling between nodes may vary depending on the travel period during which the user U travels.

When the candidate transportation means are walking and rental bicycles, the calculation unit 84 estimates the travel time using the location information included in the node information and a map application stored in an external server or the like. For example, when the candidate transportation means is walking, the calculation unit 84 refers to the location information included in the node information and the map application to estimate the distance of the section when traveling on foot, and estimates the travel time by dividing the estimated distance by the estimated walking speed. When the candidate transportation means is a rental bicycle, the calculation unit 84 estimates the travel time using the same method as in the case of walking. The estimated walking speed is, for example, 80 m/min, and the estimated speed of a rental bicycle is, for example, 150 m/min.

The calculation unit 84 estimates the visit time of node a to be the departure time plus the travel time for the section [start point - node a]. The calculation unit 84 then estimates the period from the time of departure from the departure node to the visit time of node a (the time of arrival at node a) to be the travel period for the section [start point node - node a]. The calculation unit 84 then estimates the stay time at node a. The calculation unit 84 estimates the average stay time included in the tourist destination information corresponding to node a to be the stay time at node a. The calculation unit 84 then estimates the time of departure from node a to be the visit time of node a plus the stay time at node a.

The calculation unit 84 then estimates the travel time required to travel the section [node a - node b] for the candidate means of transportation for the section [node a - node b]. The calculation unit 84 then estimates the visit time of node b to be the time obtained by adding the travel time for the section [node a - node b] to the time of departure from node a. The calculation unit 84 then estimates the travel period for the section [node a - node b] to be the time from the time of departure from node a to the visit time of node b (the time of arrival at node b). The calculation unit 84 repeats the above process to estimate the travel time, visit time, stay time, and travel period for each pattern.

Next, the calculation unit 84 calculates the first utility of each node using the first utility function included in each node information received from the acquisition unit 83 (step S23).

In step S23, the calculation unit 84 calculates the first utility for each piece of node information (for the node indicated by the node information) using the first utility function shown in the following formula (1). The following description focuses on the method of calculating the first utility for an arbitrary node n. In this embodiment, a larger first utility indicates a higher level of satisfaction for user U, and a smaller first utility indicates a lower level of satisfaction for user U.

The variable _Vnt is a variable into which the visiting time when the user U visits the node n (or a value corresponding to the visiting time) is substituted. The variable _Vnw is a variable into which a value that varies depending on the weather at the node n is substituted. The weather at the node n is the weather indicated by the weather information at the visiting time when the user U visits the node n. In other words, the first utility varies depending on the visiting time when the user U visits the node n and the weather at the node n. The calculation unit 84 determines the value of the variable _Vnw based on the weather at the visiting time estimated in step S22. The calculation unit 84 substitutes a value based on the weather at the node n indicated by the weather information received from the acquisition unit 83 into the variable _Vnw . The value substituted into the variable _Vnw is, for example, a discrete numerical value.

The first utility function differs for each node depending on the relationship between the characteristics of the destination corresponding to the node and the satisfaction level of the user U. Specifically, the first utility function is set so that when a predetermined time is substituted for the variable _Vnt , the first utility becomes high, and the first utility becomes smaller as the time substituted for the variable _Vnt is farther from the predetermined time. The predetermined time is set to a time at which the satisfaction level of the user U visiting the node is estimated to be maximum. As an example, when the node a is a shrine, the satisfaction level of the user U may be maximum in the morning when it is quiet, so the time is set to 10:00 a.m.

In addition, the first utility function corresponding to a node whose satisfaction level of the user U is easily affected by the weather is set so that the rate of fluctuation of the first utility is larger according to the value substituted for the variable _Vnw , compared to the first utility function corresponding to a node whose satisfaction level of the user U is not easily affected by the weather.

Specifically, if node a is an outdoor shrine, node a can be said to be a node whose satisfaction level of user U is easily affected by the weather. On the other hand, if node b is an indoor art museum, node b can be said to be a node whose satisfaction level of user U is less affected by the weather. Therefore, the first utility function of node a is set so that the rate of fluctuation of the first utility is larger according to the value substituted for variable _Vnw , compared to the first utility function of node b.

Then, the calculation unit 84 excludes transportation mode candidates that do not satisfy the conditions from among all transportation modes (all transportation mode candidates) included in the multiple edge information received from the acquisition unit 83 (step S24). The calculation unit 84 then calculates the second utility (for the edge indicated by the edge information) for each edge information including the remaining transportation modes (step S25). Below, the processing of steps S24 and S25 in the first mode will be described, and then the processing of steps S24 and S25 in the second mode will be described.

In the first mode, the calculation unit 84 excludes transportation candidate means that do not satisfy the conditions by referring to the behavioral information received from the acquisition unit 83. In this embodiment, the transportation candidate means to be excluded are walking, rental bicycles, and taxis. For example, the calculation unit 84 excludes transportation candidate means that do not satisfy the conditions based on the number of times a rental bicycle has been used and the number of times a taxi has been used, which are included in the behavioral information. It is considered that a user U who uses a rental bicycle a small number of times does not like to use a rental bicycle. Similarly, it is considered that a user U who uses a taxi a small number of times does not like to use a taxi. Therefore, when the number of times a rental bicycle has been used, which is included in the behavioral information, is less than a predetermined first threshold, the calculation unit 84 excludes rental bicycles as transportation candidate means that do not satisfy the conditions. Furthermore, when the number of times a taxi has been used, which is included in the behavioral information, is less than a predetermined second threshold, the calculation unit 84 excludes taxis as transportation candidate means that do not satisfy the conditions.

The calculation unit 84 estimates the user U's allowable walking time based on the travel time of the candidate walking transportation means (see step S22) and the behavioral information, and excludes from the candidate walking transportation means those transportation means that correspond to travel periods that exceed the allowable walking time as transportation means that do not satisfy the conditions.

Specifically, the calculation unit 84 estimates the walking information included in the behavior information as the user U's allowable walking time. The walking information indicates the third quarter of the period during which the user U walked continuously during the target period. If the longest period during which the user U walked continuously in the past is taken as the walking information, if the user U has walked a long distance continuously even once against his or her will, the period will be estimated as the allowable walking time. In this embodiment, the third quarter of the period during which the user U walked continuously is estimated as the allowable walking time for the user U, so that the allowable walking time for the user U is estimated with high accuracy. Then, the calculation unit 84 compares the travel time for each candidate transportation means that is walking between each node in the selected tour order with the estimated allowable walking time, and excludes the candidate transportation means that is walking and that corresponds to a travel time that exceeds the allowable walking time as a candidate transportation means that does not satisfy the condition.

As described above, the calculation unit 84 excludes transportation candidate modes that do not satisfy the conditions from among multiple transportation candidate modes, which are either walking, rental bicycles, or taxis. Transportation candidate modes other than walking, rental bicycles, and taxis are not excluded and are used in the calculation of the second utility. Note that the processing of step S24 may be omitted. In this case, the calculation unit 84 may calculate the second utility for all transportation candidate modes (all edge information received from the acquisition unit 83).

In the specific example, in the order candidate K1, none of the transportation mode candidates are excluded and are used in the calculation of the second utility. Therefore, the calculation unit 84 receives edge information for each transportation mode candidate in the section [start node-node a], each transportation mode candidate in the section [node a-node b], each transportation mode candidate in the section [node b-node c], and each transportation mode candidate in the section [node c-destination node] from the acquisition unit 83. The calculation unit 84 then calculates the second utility for each section using the second utility function included in each piece of received edge information.

Next, the calculation unit 84 calculates the second utility based on the multiple pieces of edge information. In step S25, the calculation unit 84 calculates the second utility using a second utility function shown in the following equation (2). The following description focuses on a method of calculating the second utility for a mode of transportation between any two nodes n1-n2. In this embodiment, a larger second utility indicates a higher level of satisfaction for the user U, and a smaller second utility indicates a lower level of satisfaction for the user U.

The variable _{V_et} is a variable into which the travel time estimated in step S22 (or a value corresponding to the travel time) is substituted. The variable _{V_ef} is a variable into which the travel fare (or a value corresponding to the travel fare) between nodes n1-n2 is substituted. For example, between nodes n1-n2, the value substituted into the variable _{V_ef} when the candidate travel mode is a taxi is greater than the value substituted into the variable _{V_ef} when the candidate travel mode is a railway. The value substituted into the variable _{V_ef} is, for example, stored in advance in the edge information DB 40. Alternatively, the calculation unit 84 may obtain the value substituted into the variable _{V_ef} by referring to the travel fare included in the traffic information stored in the traffic information DB 70.

In the first mode, the weight W _ef is a weight that varies based on the number of taxi trips and the number of campaign participations included in the behavioral information. It is considered that a user U who frequently uses a taxi places more importance on reducing the cost of time than reducing the cost of travel, and a user U who frequently participates in campaigns places more importance on reducing the cost of travel than the cost of time. The calculation unit 84 sets an optimal weight W _ef based on the number of taxi trips and the number of campaign participations included in the behavioral information. As an example, the calculation unit 84 sets the weight W _ef to a larger value as the number of taxi trips is smaller. The calculation unit 84 sets the weight W _ef to a larger value as the number of campaign participations is larger.

The variable V _ew is a variable into which a value that varies depending on the weather between nodes n1-n2 is substituted. The weather between nodes n1-n2 is the weather indicated by the weather information during the travel period in which the user U travels between nodes n1-n2. The value of the variable V _ew is determined in the same manner as the value of the variable V _nw . The weight W _ew is a weight that varies for each candidate transportation means. Specifically, the calculation unit 84 sets the weight W _ew to a larger value for a candidate transportation means that is more susceptible to the weather. For example, the satisfaction of the user U with walking is more susceptible to the weather than the satisfaction of the user U with the railway. The calculation unit 84 sets the weight W _ew for a candidate transportation means that is walking to a larger value than the weight W _ew for a candidate transportation means that is the railway. That is, for each candidate transportation means, the calculation unit 84 sets the rate of variation of the second utility according to the weather between the two destinations to a larger value for the candidate transportation means that is more susceptible to the weather. The weight W _ew is, for example, stored in advance in the edge information DB 40.

The variable V _ev is a variable into which the scenery goodness degree is substituted. The calculation unit 84 estimates the scenery goodness degree based on the travel period estimated in step S22 and the route scenery information. The scenery goodness degree is a degree indicating the quality of scenery. Specifically, the calculation unit 84 compares the travel period with the route scenery information to estimate the scenery goodness degree of the route between nodes n1-n2 during the travel period.

In the first mode, the weight W _ev varies depending on the scenery preference. The scenery preference indicates the degree to which the user U attaches importance to scenery during the trip. The calculation unit 84 estimates the scenery preference based on the behavioral information received from the acquisition unit 83. Specifically, the calculation unit 84 specifies the location of the store and the restaurant by referring to the identification information of the store and the restaurant that are included in the behavioral information and that the user U paid for. The calculation unit 84 then refers to the tourist destination information DB, compares the specified locations of the store and the restaurant with the area scenery information, and estimates the number of times the user U visited the area with good scenery during the target period. The calculation unit 84 then sets the weight W _ev to a larger value, for example, as the estimated number of times is larger.

The variable V _es is a variable into which the first degree of fulfillment is assigned. The first degree of fulfillment indicates the degree of fulfillment of shops on the route taken by the user U when moving between nodes n1-n2 by means of transportation. The first degree of fulfillment is larger as the shops are more fulfilled and is smaller as the shops are less fulfilled. The variable V _es is, for example, stored in advance in the edge information DB 40.

In the first mode, the weight W _es is a weight that varies depending on the first preference level. The first preference level indicates the degree to which the user U is interested in stores while traveling. The first preference level is the number of product purchases included in the behavioral information. In the first mode, the calculation unit 84 sets the weight W _es to a larger value based on the behavioral information received from the acquisition unit 83, for example, as the number of product purchases included in the behavioral information increases.

The variable _{V_er} is a variable into which the second degree of fulfillment is assigned. The second degree of fulfillment indicates the degree of fulfillment of restaurants on the route taken by the user U when traveling between nodes n1-n2 by means of transportation. The second degree of fulfillment is larger as the number of restaurants increases and is smaller as the number of restaurants decreases. The variable _{V_er} is stored in advance in the edge information DB 40, for example.

In the first mode, the weight W _er is a weight that varies depending on the second preference level. The second preference level indicates the degree to which the user U is interested in restaurants while traveling. The second preference level is the number of times the user has visited a restaurant, which is included in the behavioral information. In the first mode, the calculation unit 84 sets the weight W _er to a larger value based on the behavioral information received from the acquisition unit 83, for example, as the number of times the user has visited a restaurant, which is included in the behavioral information, is larger.

As described above, the calculation unit 84 obtains the second utility based on the variables V _et , V _ef , V _ew , V _ev , V _es , and V _er of the second utility function and the weights W _ef , W _ew , W _ev , W _es , and W _er . That is, the second utility varies depending on the travel time, the usage fee, the weather between nodes n1 and n2, the quality of the scenery, the degree of availability of shops, and the degree of availability of restaurants.

The above-mentioned travel time, weather information, and scenery information are included in variable information that changes depending on the travel period that user U takes to travel between two destinations. The above-mentioned variable information (travel time, weather information, and scenery information), the first satisfaction level, and the second satisfaction level are included in point-to-point information relating to the two destinations. The scenery preference level, the first preference level, and the second preference level are included in preference information relating to user U's preferences. In other words, the calculation unit 84 calculates the second utility for each candidate transportation means based on the point-to-point information relating to the two destinations and the preference information relating to user U's preferences.

Next, the method of calculating the second utility in the second mode will be described, focusing mainly on the differences from the first mode. In the second mode, the calculation unit 84 refers to the used transportation means information included in the user setting information received from the acquisition unit 83, and excludes transportation means not specified by the user U from the transportation means candidates. The calculation unit 84 sets the allowable walking range included in the user setting information as the allowable walking time for the user U, and excludes from the transportation means candidates that are walking, transportation means candidates that correspond to a travel period that exceeds the allowable walking time, as transportation means candidates that do not satisfy the conditions.

Next, the calculation unit 84 calculates the second utility. The second mode differs from the first mode in that the calculation unit 84 sets the weights W _ef , W _ev , W _er , and W _es based on the user setting information. Specifically, the calculation unit 84 sets the weight W _ef to a larger value when the priority cost information included in the user setting information indicates that the user U prioritizes the amount of money compared to when the priority cost information indicates that the user U prioritizes time.

The calculation unit 84 sets the weight corresponding to the item designated by the user U among the priority items (scenery, good number of restaurants, and good number of shops) included in the user setting information to a value larger than that in the case where the user U does not designate the item. Specifically, when the user U designates scenery as a priority item, the calculation unit 84 sets the weight W _ev to a value larger than that in the case where scenery is not designated as a priority item. When the user U designates good number of shops as a priority item, the calculation unit 84 sets the weight W _es to a value larger than that in the case where good number of shops is not designated as a priority item. When the user U designates good number of restaurants as a priority item, the calculation unit 84 sets the weight W _er to a value larger than that in the case where good number of restaurants is not designated as a priority item.

The calculation unit 84 then determines whether or not all of the order candidates have been selected (step S26). If the calculation unit 84 determines that not all of the order candidates have been selected (step S26: NO), it selects the next order candidate (step S21) and repeats the processing of steps S22 to S26. If the calculation unit 84 determines that all of the order candidates have been selected (step S26: YES), it outputs the first utility and the second utility to the determination unit 85 and ends the calculation processing of step S04.

Then, the determination unit 85 determines an optimal combination based on the first utility and second utility received from the calculation unit 84 (step S05). The determination unit 85 determines an optimal combination such that the sum of the first utility for each of the multiple destinations and the second utility for each mode of transportation between two destinations is maximized. Specifically, the determination unit 85 calculates the sum for all combinations of multiple order candidates and multiple mode of transportation candidates for adjacent sections in each order candidate. The combinations correspond to the above patterns. That is, the determination unit 85 calculates the sum of the first utility of each node corresponding to the destination and the second utility of each edge corresponding to the mode of transportation candidate for each combination.

For example, in the pattern of [start point → train → node a → walking → node b → walking → node c → walking → destination] in the specific example of sequence candidate K1, the determination unit 85 calculates the sum of the first utility of each of nodes a, b, and c, the second utility of the transportation means (train) for the section [start point-node a], the second utility of the transportation means (walking) for the section [node a-node b], the second utility of the transportation means (walking) for the section [node b-node c], and the second utility of the transportation means (walking) for the section [node c-destination].

Then, the determination unit 85 determines the combination having the maximum total value among all the combinations as the optimal combination. Note that the calculation unit 84 may exclude from the optimal combinations, among all the above combinations (all patterns), combinations in which the visit time to the return destination, which corresponds to the return time to the return destination, is later than the return time included in the recommendation condition information specified by the user U. Furthermore, the calculation unit 84 may calculate the total value not for all combinations, but for multiple combinations that satisfy, for example, specific conditions. Then, the determination unit 85 outputs the recommendation information to the presentation unit 86.

Next, when the presentation unit 86 receives the recommendation information from the determination unit 85, it presents the recommendation information (step S06). The recommendation information indicates an optimal combination. In step S06, the presentation unit 86 outputs the recommendation information to the terminal device 10 that sent the recommendation request. In the example screen shown in FIG. 10, an optimal combination of the order of visiting multiple destinations and the means of transportation between the two destinations (specifically, icons indicating the means of transportation) is displayed as a tour plan. The presentation unit 86 may present other combinations in addition to the determined optimal combination. As an example, the calculation unit 84 may change any of the weights W _ef , W _ew , W _ev , W _es , and W _er included in the second utility function to calculate the second utility, and further present the combination having the maximum total value based on the first utility and the changed second utility.

This completes the series of processes in the recommendation method. Note that steps S24 and S25 may be performed before step S23, or in parallel with step S23. Furthermore, the processes in steps S22 to S25 may be performed simultaneously for multiple order candidates. In this case, the processes in steps S21 and S26 are omitted.

The recommendation device 80 described above acquires weather information indicating the weather at multiple destinations, determines an optimal combination based on the weather information, and presents recommendation information indicating the optimal combination. It can be said that the user's satisfaction with the combination of the order of visiting multiple destinations and multiple means of transportation varies depending on the weather at the destinations the user is visiting. According to the above configuration, the weather at the multiple destinations the user is visiting is taken into consideration and the optimal combination is determined from the order of visiting and the combination of means of transportation between two destinations, so that a combination that provides high satisfaction to the user U can be determined as the optimal combination (route of travel). Therefore, a route that provides high satisfaction to the user U can be presented.

For example, if it rains in the morning and clears up in the afternoon, it is considered that user U will be more satisfied if he or she goes to an outdoor destination in the morning and then walks to the next destination than if he or she goes to an indoor destination in the morning and then takes a taxi to the next destination. As in this example, the weather can be said to affect user U's satisfaction with the above combination. The recommendation device 80 determines the optimal combination by taking into account the weather at multiple destinations to be visited by the user, and can therefore present a route that will satisfy user U.

For example, if user U visits a park in the rain, user U's satisfaction with the park as the destination is considered to be low. As in this example, the weather is considered to affect user U's satisfaction with the destination, but it may also change significantly depending on the time of day when user U visits the destination. In other words, it can be said that the time of day when user U visits the destination affects user U's satisfaction with the destination. In this regard, the determination unit 85 determines an optimal combination based on a first utility indicating user U's satisfaction with the destination and a second utility indicating user U's satisfaction with the means of transportation. The first utility varies depending on the visiting time of the destination and the weather at the destination. The second utility varies depending on the weather between the two destinations. Therefore, the optimal combination is determined taking into account the weather at the time of visiting the destination, and as a result, a travel route that provides high satisfaction to user U can be presented.

The travel cost and travel time when traveling between two destinations are considered to affect the user U's satisfaction with the means of transportation. In contrast, the second utility further varies depending on the travel time and travel cost between the two destinations. In other words, the second utility is calculated taking into account the travel cost and travel time in addition to the weather information. Therefore, the second utility can be obtained with high accuracy.

The determination unit 85 determines the optimal combination so that the sum of the first utility for each of the multiple destinations and the second utility for each of the multiple means of transportation between two destinations is maximized. The combination that maximizes the sum of the first utility for each destination and the second utility for each means of transportation is the combination that maximizes the satisfaction of the user U. Therefore, a route that maximizes the satisfaction of the user U can be reliably determined.

Specifically, the determination unit 85 calculates the total value for multiple combinations of multiple order candidates and multiple transportation mode candidates, and determines the combination with the maximum total value among the multiple combinations as the optimal combination. With this configuration, it is possible to determine the optimal combination for the entire route including multiple destinations and transportation modes between two destinations. For example, even if the first utility for one destination and the second utility for one transportation mode are relatively low in a combination of a certain order candidate and multiple transportation mode candidates, if the total value is high, such as the first utility for destinations other than the above destination, the combination is determined as the combination to be recommended to the user U. In other words, the recommendation device 80 can determine the optimal combination by comprehensively considering the order of visits to all destinations that the user U can visit and the combination of all transportation modes.

For example, the impact of weather on user U's satisfaction with travel by foot is greater than the impact of weather on user U's satisfaction with travel by rail. In this regard, the calculation unit 84 increases the rate of fluctuation of the second utility depending on the weather between two destinations for a plurality of means of travel that is more susceptible to weather (i.e., changes the degree of impact of weather on the second utility depending on the type of means of travel), thereby enabling the second utility to be obtained with high accuracy.

In the recommendation device 80, the point-to-point information between the two destinations and the preference information regarding the preferences of the user U are taken into consideration to calculate the second utility for the means of transportation available between the two destinations, so that the second utility can be obtained with high accuracy. And, because the accurately obtained second utility is taken into consideration, it is possible to determine a tour combination (optimum combination) from among all combinations of multiple tour orders and multiple means of transportation available between the two destinations. Therefore, according to the above configuration, a tour route that provides high satisfaction to the user U can be presented.

For example, if user U travels on foot in the rain, user U's satisfaction with the means of transportation (walking) is considered to be low. As in this example, the weather is considered to affect user U's satisfaction with the means of transportation, but it may also change significantly depending on the period (time period) during which user U travels between two destinations in a day. In other words, it can be said that the period during which user U travels between two destinations (from the time user U departs from one destination to the time he arrives at the other destination) affects user U's satisfaction with the means of transportation. In this regard, since the point-to-point information includes variable information that changes depending on the travel period during which user U travels between two destinations, the second utility for each means of transportation is calculated taking into account the variable information that changes depending on the two travel periods. Therefore, the second utility can be obtained with high accuracy.

For example, the quality of scenery changes depending on the time of day on a route where you can see the sunset and a route where you can get a good view of the ocean during the day. Also, for example, when traveling between two destinations, the scenery can be said to be significantly different between a route where you travel by subway and a route where you travel on foot. Since the variation information includes scenery information, the second utility of each means of transportation is calculated taking the scenery information into account. Therefore, the second utility can be obtained with even greater accuracy.

The preference information includes a scenery preference degree indicating the degree to which the user U values scenery while traveling. It is considered that the scenery when traveling between two destinations will have a significant impact on the satisfaction level of the user U, who values scenery, with respect to the means of transportation. In this regard, since the preference information includes a scenery preference degree indicating the degree to which the user U values scenery while traveling, the second utility of each means of transportation is calculated taking into consideration the scenery information and the scenery preference degree. Therefore, the second utility can be obtained with greater accuracy. For example, a user U who values scenery is more likely to select a bus as a means of transportation included in the above route combination compared to the subway.

As described above, the weather, which is thought to affect the satisfaction of user U, may change depending on the time of day. Since the variation information includes weather information between the two destinations when user U travels between the two destinations, the second utility is calculated taking into account the weather between the two destinations when traveling between the two destinations. Therefore, the second utility can be obtained with even greater accuracy.

For example, even for the same road route, there is a difference in the degree of congestion between early morning and evening rush hour, so it can be said that the travel time between two destinations changes depending on the time of day. Since the variation information includes travel time indicating the time it takes for user U to travel between two destinations by transportation means, the second utility is calculated taking into account the travel time it takes to travel between the two destinations. Therefore, the second utility can be obtained with even greater accuracy.

For example, for user U who has a high interest in shops while traveling, the abundance of shops when traveling between two destinations is thought to have a large impact on user U's satisfaction. Since the preference information includes the first preference level and the location-to-location information includes the first abundance level, the second utility is calculated taking into consideration the degree to which user U is interested in shops while traveling and the abundance of shops along the route taken when traveling between two destinations by means of transportation. Therefore, the second utility can be obtained with even greater accuracy.

For example, for user U who has a high interest in restaurants while traveling, the availability of restaurants when traveling between two destinations is thought to have a large impact on user U's satisfaction. Since the preference information includes a second preference level and the location-to-location information includes restaurant availability information, the second utility is calculated taking into consideration the degree to which user U is interested in restaurants while traveling and the availability of restaurants on the route taken when traveling between two destinations by means of transportation. Therefore, the second utility can be obtained with even greater accuracy.

Although the embodiments of the present disclosure have been described above, the present disclosure is not limited to the above embodiments.

The recommendation device 80 may be configured by a single device that is physically or logically coupled, or may be configured by multiple devices that are physically or logically separated from each other. For example, the recommendation device 80 may be realized by multiple computers distributed over a network, such as in cloud computing. As described above, the configuration of the recommendation device 80 may include any configuration that can realize the functions of the recommendation device 80.

The multiple destinations to which the user U travels may be only the multiple destinations specified by the user U. In this case, the acquisition unit 81 acquires only the recommendation condition information, and the recommendation device 80 does not need to include the determination unit 82.

The recommendation device 80 may include at least one of the behavior information DB 20, the node information DB 30, the edge information DB 40, the tourist destination information DB 50, the weather information DB 60, and the traffic information DB 70. In addition, at least one of the behavior information DB 20, the node information DB 30, the edge information DB 40, the tourist destination information DB 50, the weather information DB 60, and the traffic information DB 70 may be composed of multiple databases.

The calculation method of the first utility and the second utility is not limited to the example of the above embodiment. For example, the first utility function and the second utility function may include a variable different from each of the above variables and a weight different from each of the above weights. As an example, the first utility function and the second utility function may include a variable indicating the degree of congestion. In the second utility function, the weights W _ef , W _ev , W _es , and W _er may be preset values. In this case, the recommendation device 80 may not have a setting function for the first mode and the second mode, and the recommendation system 1 may not have the behavior information DB 20. The recommendation device 80 may be preset to either the first mode or the second mode.

The calculation unit 84 may calculate a first utility that varies depending on the weather at a node where the user U visits the destination, and a second utility that varies depending on the weather between the two destinations. In this case, for example, the first utility function may include a variable _Vnw , and the second utility function may include a variable _Vew and a weight _Wew .

In this disclosure, "multiple means of transportation" refers to multiple ways of traveling. For example, multiple means of transportation capable of traveling one section may be a first means of transportation that travels on foot along a first route, and a second means of transportation that travels on foot along a second route different from the first route. In this case, since the first route is different from the second route, the second utility function included in the edge information corresponding to the first means of transportation is different from the second utility function included in the edge information corresponding to the second means of transportation.

The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. There are no particular limitations on the method of realizing each functional block. That is, each functional block may be realized using one device that is physically or logically coupled, or may be realized using two or more devices that are physically or logically separated and directly or indirectly connected (for example, using wires, wirelessly, etc.) and these multiple devices. The functional blocks may be realized by combining the one device or the multiple devices with software.

Functions include, but are not limited to, judgement, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, regard, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs the transmission function is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on the method of realization for either of these functions.

For example, the recommendation device 80 in one embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure. FIG. 11 is a diagram showing an example of a hardware configuration of the recommendation device 80 according to one embodiment of the present disclosure. The recommendation device 80 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, and a bus 1007.

In the following description, the term "apparatus" can be interpreted as a circuit, device, unit, etc. The hardware configuration of the recommendation apparatus 80 may be configured to include one or more of the apparatuses shown in the figure, or may be configured to exclude some of the apparatuses.

Each function of the recommendation device 80 is realized by loading a specific software (program) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be configured with a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, and a register. For example, each function of the recommendation device 80 described above may be realized by the processor 1001.

The processor 1001 reads out programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to the programs. The programs used are those that cause a computer to execute at least some of the operations described in the above-mentioned embodiments. For example, each function of the recommendation device 80 may be realized by a control program stored in the memory 1002 and running on the processor 1001. Although the above-mentioned various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

The memory 1002 is a computer-readable recording medium, and may be composed of at least one of, for example, a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), and a random access memory (RAM). The memory 1002 may also be called a register, a cache, or a main memory (primary storage device). The memory 1002 can store executable programs (program codes), software modules, and the like for implementing a method according to an embodiment of the present disclosure.

Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, and a magnetic strip. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other suitable medium including at least one of memory 1002 and storage 1003.

The communication device 1004 is hardware (transmission/reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, or a communication module. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc., to realize at least one of, for example, Frequency Division Duplex (FDD) and Time Division Duplex (TDD). For example, the above-mentioned acquisition unit 81, acquisition unit 83, and presentation unit 86 may be realized by the communication device 1004.

The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that performs output to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one structure (e.g., a touch panel).

Each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

The recommendation device 80 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

Notification of information is not limited to the aspects/embodiments described in this disclosure and may be performed using other methods.

Each aspect/embodiment described in this disclosure may be applied to at least one of systems using LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (new Radio), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth (registered trademark), other suitable systems, and next-generation systems enhanced based on these. Multiple systems may be combined (e.g., a combination of at least one of LTE and LTE-A with 5G, etc.).

The order of steps, sequences, flow charts, etc. of each aspect/embodiment described in this disclosure may be changed unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order and are not limited to the particular order presented.

Information, etc. may be output from a higher layer to a lower layer, or from a lower layer to a higher layer. Information, etc. may be input/output via multiple network nodes.

The input and output information may be stored in a specific location (e.g., memory) or may be managed using a management table. The input and output information may be overwritten, updated, or added to. The output information may be deleted. The input information may be transmitted to another device.

The determination may be based on a value represented by one bit (0 or 1), a Boolean (true or false) value, or a numerical comparison (e.g., with a predetermined value).

Each aspect/embodiment described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of specific information (e.g., notification that "X is the case") is not limited to explicit notification, but may be performed implicitly (e.g., by not notifying the specific information).

Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended as an illustrative example and does not have any limiting meaning on the present disclosure.

Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

Software, instructions, information, and the like may be transmitted and received via a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and/or wireless technologies (such as infrared, microwave), these wired and/or wireless technologies are included within the definition of a transmission medium.

The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

In addition, the terms explained in this disclosure and the terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings.

As used in this disclosure, the terms "system" and "network" are used interchangeably.

The information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values from a predetermined value, or may be expressed using other corresponding information.

The names used for the parameters described above are not limiting in any way. Furthermore, the formulas etc. using these parameters may differ from the formulas etc. explicitly disclosed in this disclosure.

The terms "determining" and "determining" as used in this disclosure may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in a memory), and the like. "Determining" and "determining" may include resolving, selecting, choosing, establishing, comparing, and the like. In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." "Judgment (decision)" may also be interpreted as "assuming," "expecting," or "considering," etc.

In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably.

A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

At least one of the base station and the mobile station may be called a transmitting device, a receiving device, or a communication device. At least one of the base station and the mobile station may be a device mounted on a moving body, or the moving body itself. The moving body may be a vehicle (e.g., a car, an airplane, etc.), an unmanned moving body (e.g., a drone, an autonomous vehicle, etc.), or a robot (manned or unmanned). At least one of the base station and the mobile station may be a device that does not necessarily move during communication operations. For example, at least one of the base station and the mobile station may be an IoT (Internet of Things) device such as a sensor.

The terms "connected" and "coupled", or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical or logical, or a combination thereof. For example, "connected" may be read as "access". As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

Any reference to elements using designations such as "first" and "second" used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Thus, a reference to a first and a second element does not imply either that only two elements may be employed or that the first element must precede the second element in any way.

The "part" in the configuration of each of the above devices may be replaced with "circuit," "device," etc.

When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Additionally, the term "or," as used in this disclosure, is not intended to be an exclusive or.

In this disclosure, where articles have been added by translation, such as "a," "an," and "the" in English, this disclosure may include that the nouns following these articles are plural.

In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combined" may also be interpreted in the same way as "different."

80: recommendation device, 83: acquisition unit, 84: calculation unit, 85: determination unit, 86: presentation unit, A to E: destinations, U: user.

Claims (5)

A recommendation device presents an optimal combination from among a plurality of combinations of a plurality of travel orders available for traveling around a plurality of destinations and a plurality of means of transportation available between two destinations, the device comprising:
an acquisition unit that acquires weather information indicating weather at the plurality of destinations;
A determination unit that determines the optimal combination based on the weather information;
a presentation unit that presents recommendation information indicating the optimal combination;
Equipped with
The determination unit determines the optimal combination based on a first utility, which is a value that varies depending on the time of visiting the destination and the weather at the destination and indicates the user's satisfaction with the destination, and a second utility, which is a value that varies depending on the weather between the two destinations and indicates the user's satisfaction with the means of transportation . The recommendation device according to claim 1 , wherein the second utility further varies depending on a travel time and a travel fare between the two destinations. The recommendation device according to claim 1 or claim 2, wherein the determination unit determines the optimal combination so that a sum of the first utility for each of the plurality of destinations and the second utility for each of the plurality of means of transportation between the two destinations is maximized. The recommendation device according to claim 3 , wherein the determination unit calculates the total value for each of the plurality of combinations, and determines a combination having a maximum total value among the plurality of combinations as the optimal combination. A calculation unit that calculates the first utility and the second utility is further provided,
The recommendation device according to claim 4 , wherein the calculation unit is configured to increase a fluctuation rate of the second utility according to the weather between the two destinations for a transportation means that is more susceptible to weather influences.

Images