WO2021182581A1

WO2021182581A1 - Information processing system, information processing device, terminal device, information processing method, and program

Info

Publication number: WO2021182581A1
Application number: PCT/JP2021/009863
Authority: WO
Inventors: 慧池上; 旦松下; 恭平奥村
Original assignee: 慧池上; 旦松下; 恭平奥村
Priority date: 2020-03-11
Filing date: 2021-03-11
Publication date: 2021-09-16
Also published as: JP2023052714A

Abstract

[Problem] To make a more satisfactory recommendation for the entirety of a plurality of users. [Solution] An information processing system 1 comprises a user terminal 10 and a server 20. At the user terminal 10, a UI display control unit 51 acquires, for a plurality of selection targets, request information expressing one or more selection targets for which a user has requested selection. In accordance with the request information, the UI display control unit 51 displays recommendation information presented by the server 20. At the server 20, a user information acquisition unit 152 receives, from a plurality of user terminals 10, request information relating to a plurality of users. A recommendation information generation unit 153 treats the selection targets expressed by the request information relating to the plurality of users as an equilibrium problem for the plurality of selection targets, and acquires a solution to the equilibrium problem. A UI screen generation unit 151 transmits, to the user terminals and as a proposal in response to the request information, the equilibrium problem solution acquired by the recommendation information generation unit 153.

Description

Information processing system, information processing device, terminal device, information processing method and program

The present invention relates to an information processing system, an information processing device, a terminal device, an information processing method and a program.

Conventionally, a system for providing information for recommendation, guidance, etc. to a user has been known.
For example, when a user browses or purchases a product on a shopping site, the system provides the user with product recommendation information based on the history.
Further, when the destination is set by the car navigation system, the route information reflecting the congestion status of the road is provided to the user.
In addition, Patent Document 1 discloses a technique for optimizing the overall situation of the behavior of a large number of users.

Japanese Unexamined Patent Publication No. 2017-05909

However, in the technique described in Patent Document 1, a user who can easily accept the recommendation provided by the system is selected to alleviate congestion and the like.
Therefore, the situation achieved by the system recommendation may not always be sufficiently optimized as the satisfaction level of the entire user.
That is, in the conventional technique, it is difficult to make a recommendation with a high degree of satisfaction as a plurality of users as a whole.

An object of the present invention is to make a recommendation with a higher degree of satisfaction as a plurality of users as a whole.

In order to solve the above problems, the information processing system according to the embodiment of the present invention is
An information processing system including a terminal device used by a user and a server configured to be able to communicate with the terminal device.
The terminal device is
A request information acquisition means for acquiring request information representing one or a plurality of the selection targets for which the user requests selection for a plurality of selection targets.
It is provided with a recommendation information display means for displaying the recommendation information presented from the server in response to the request information.
The server
A request information receiving means for receiving the request information regarding a plurality of users from the plurality of terminal devices, and
An equilibrium processing means for acquiring a solution of the equilibrium problem by using the selection target represented by the request information regarding a plurality of users as an equilibrium problem for the plurality of selection targets.
A recommendation information transmitting means for transmitting the solution of the equilibrium problem acquired by the equilibrium processing means to the terminal device as a proposal for the required information, and
It is characterized by having.

According to the present invention, it is possible to make a recommendation with a higher degree of satisfaction as a plurality of users as a whole.

It is a schematic diagram which shows the structure of the whole information processing system 1 which concerns on this invention. It is a figure which shows the hardware configuration of the information processing apparatus 800 which constitutes each apparatus. It is a block diagram which shows the functional structure of the user terminal 10. It is a block diagram which shows the functional configuration of a server 20. It is a schematic diagram for demonstrating the algorithm which generates the recommendation information. It is a schematic diagram for demonstrating the algorithm which generates the recommendation information. It is a flowchart explaining the flow of UI display processing executed in a user terminal 10. It is a flowchart explaining the flow of the recommendation processing executed by the server 20. It is a flowchart explaining the flow of the equilibrium processing executed by the server 20. It is a block diagram which shows the functional structure when the present invention is mounted on a single information processing apparatus 800.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[First Embodiment]
[composition]
FIG. 1 is a schematic view showing the configuration of the entire information processing system 1 according to the present invention.
The information processing system 1 according to the present embodiment acquires an option that can be accepted by each of a plurality of users among the options of the target event, and has a probability according to the utility of the option for each user. Assign each user to one of the options. Then, when the allocation of all the plurality of users matches the convergence condition, the options assigned to each user are presented to each user as recommendation information. That is, the information processing system 1 presents recommendation information as a solution to an equilibrium problem that balances competition among a plurality of users according to a probability according to the utility of options for each user.
Therefore, each user is recommended among the acceptable options, and each user follows the recommendation information by the information processing system 1, so that the highest utility can be obtained for a plurality of users as a whole. It can be converged to a certain range (range of stochastic variation).
Therefore, according to the information processing system 1, it is possible to make a recommendation with a higher degree of satisfaction as a plurality of users as a whole.
Hereinafter, the configuration of the information processing system 1 will be specifically described.

As shown in FIG. 1, the information processing system 1 includes a plurality of user terminals 10 and a server 20, and the plurality of user terminals 10 and the server 20 can communicate with each other via a network 30 such as the Internet. It is configured in.
In the following description, the event to be selected is a restaurant, and the information processing system 1 obtains a solution to the equilibrium problem related to the expected congestion situation of the restaurant and visits the user to visit the restaurant. The case of presenting the recommendation information regarding the above will be described as an example. However, the present invention can be applied to various events in which a plurality of users compete with each other, such as reservation of accommodation facilities, guidance route to a destination, reservation of transportation, purchase of tickets for an event, and the like.

The user terminal 10 is a terminal device used by each user, and is composed of an information processing device such as a smartphone, a mobile phone, a tablet terminal, or a PC (Personal Computer).
Further, the user terminal 10 displays a user interface screen (hereinafter, referred to as "UI screen") in which the user inputs and outputs information, and processes for inputting and outputting various information ("UI display processing" described later). ”) Is executed. Each user selects a restaurant he / she desires as an option from a plurality of restaurants via the UI screen, and browses information about the restaurant recommended by the server 20.
The server 20 is composed of an information processing device such as a server computer that accepts access from a plurality of user terminals 10.

The server 20 stores the data of the restaurant to be selected and also stores the data of the restaurant selected by each user. The server 20 may store the attributes of each user (name, age, gender, hobbies, tastes, behavior history, etc.).
Further, the server 20 executes a process for optimizing the competition among a plurality of users (“recommendation process” and “balance process” described later) for the selection of the restaurant, thereby causing the selected user to perform the process. Present recommendation information about the restaurant you visit.

[Hardware configuration]
Next, the hardware configuration of each device in the information processing system 1 will be described.
In the information processing system 1, each device is composed of an information processing device such as a PC, a server computer, or a tablet terminal, and the basic configuration thereof is the same.

FIG. 2 is a diagram showing a hardware configuration of the information processing device 800 constituting each device.
As shown in FIG. 2, the information processing device 800 constituting each device inputs a CPU (Central Processing Unit) 811, a ROM (Read Only Memory) 812, a RAM (Random Access Memory) 813, and a bus 814. It includes a unit 815, an output unit 816, a storage unit 817, a communication unit 818, a drive 819, and an image pickup unit 820.

The CPU 811 executes various processes according to the program recorded in the ROM 812 or the program loaded from the storage unit 817 into the RAM 813.
The RAM 813 also appropriately stores data and the like necessary for the CPU 811 to execute various processes.

The CPU 811 and ROM 812 and the RAM 813 are connected to each other via the bus 814. An input unit 815, an output unit 816, a storage unit 817, a communication unit 818, a drive 819, and an imaging unit 820 are connected to the bus 814.

The input unit 815 is composed of various buttons and the like, and inputs various information according to an instruction operation.
The output unit 816 is composed of a display, a speaker, and the like, and outputs video and audio.
When the information processing device 800 is configured as a smartphone or a tablet terminal, the input unit 815 and the display of the output unit 816 may be arranged so as to overlap each other to form a touch panel.
The storage unit 817 is composed of a hard disk, a DRAM (Dynamic Random Access Memory), or the like, and stores various data managed by each server.
The communication unit 818 controls communication with other devices via the network 30.

A removable media 831 made of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately mounted on the drive 819. The program read from the removable media 831 by the drive 819 is installed in the storage unit 817 as needed.
The image pickup unit 820 is composed of an image pickup device including a lens, an image pickup element, and the like, and captures a digital image of a subject.

[Functional configuration]
Next, the functional configuration of each device in the information processing system 1 will be described.
[Functional configuration of user terminal 10]
FIG. 3 is a block diagram showing a functional configuration of the user terminal 10.
As shown in FIG. 3, in the CPU 811 of the user terminal 10, the user interface display control unit (UI display control unit) 51, the user information transmission unit 52, and the recommendation information acquisition unit 53 function.

The UI display control unit 51 displays various input / output screens (UI screens) in the UI display process based on the information for displaying the UI screen received from the server 20 (hereinafter, referred to as "UI information"). Control. For example, the UI display control unit 51 displays a user attribute input screen for inputting information related to user attributes, a list of stores that can be selected by the user, and information related to store selection (hereinafter referred to as "request information"). ) Is transmitted to the server 20, and various screens such as a store selection screen and a recommendation information display screen for displaying information about the store recommended by the server 20 to the user are displayed.

The user information transmission unit 52 includes information on user attributes (name, age, gender, hobbies, preferences, etc.) input on the UI screen, request information (store name, visit time, etc.) input on the store selection screen. ) Or, information about the result of the action actually performed by the user in response to the recommendation on the recommendation information display screen (whether or not the recommendation was followed, which store / time the user visited if the recommendation was not followed, etc.) Send various entered information.

The recommendation information acquisition unit 53 acquires information about the store recommended by the server 20 when the recommendation information is presented at the timing. For example, when the user requests a recommendation to the server 20 for a store to be visited for lunch, the recommendation information acquisition unit 53 sets the lunch time zone before a predetermined time (for example, 12:00 pm lunch time zone). In that case, information about the recommended store will be acquired at 11:30 am, etc. 30 minutes before. In the present embodiment, the information about the store recommended by the server 20 is included in the UI information of the recommendation information display screen and acquired.

[Functional configuration of server 20]
FIG. 4 is a block diagram showing a functional configuration of the server 20.
As shown in FIG. 4, in the CPU 811 of the server 20, the user interface screen generation unit (UI screen generation unit) 151, the user information acquisition unit 152, and the recommendation information generation unit 153 function. Further, in the storage unit 817 of the server 20, a store information storage unit 171, a user information storage unit 172, and an action result storage unit 173 are formed.

The store information storage unit 171 contains information about each store that can be selected by the user (store name, location, number of seats, seat type (table or counter, etc.), business hours, store type (type of food to be served), menu. Etc.) are memorized.
The user information storage unit 172 stores information about the user (information about user attributes, information about store selection (request information), etc.) transmitted from the user terminal 10.
The action result storage unit 173 contains information on the user's request information and information on the action result actually performed by the user with respect to the recommendation of the server 20 (whether or not the user has followed the recommendation, or if the user has not followed the recommendation, any store.・ Whether you visited at the time, etc.) is memorized.

The UI screen generation unit 151 generates UI information for displaying the UI screen when a recommendation is requested from the user terminal 10, and transmits the generated UI information to the user terminal 10. For example, the UI screen generation unit 151 displays a user attribute input screen for inputting information related to user attributes, a list of stores that can be selected by the user, and accepts input of information (request information) related to store selection. Various UI information such as a selection screen or a recommendation information display screen that displays information about the store to be recommended to the user is transmitted to the user terminal 10.

The user information acquisition unit 152 acquires information (information about user attributes, user request information, information about action results, etc.) input to various UI screens on the user terminal 10. Further, the user information acquisition unit 152 stores the acquired information on the user's attributes in the user information storage unit 172, and stores the user's request information and the information on the action result in the action result storage unit 173.

The recommendation information generation unit 153 accumulates information on user attributes and user request information received from a plurality of users as a target for solving an equilibrium problem for making recommendations.
In addition, the recommendation information generation unit 153 is based on the information about the store that can be selected by the user, the accumulated information about the attributes of the user, and the information requested by the user when it is time to present the recommendation information. Recommendation information is acquired as a solution to an equilibrium problem that balances competition among a plurality of users according to a probability according to the magnitude of utility of an option for each user. The recommendation information acquired by the recommendation information generation unit 153 is included in the recommendation information display screen and transmitted to the user terminal 10 of each user by the UI screen generation unit 151.

In the present embodiment, when the recommendation information generation unit 153 acquires the recommendation information for each user as a solution of an equilibrium problem that balances the competition among a plurality of users, the option currently assigned to that user (here, a store). ), And the probability of the utility when moving to another option (store) is calculated, and the option to assign the user is selected according to the calculated probability. do. Then, the recommendation information generation unit 153 presents to each user the options assigned to each user as the recommendation information at the stage when the allocation of all the plurality of users matches the convergence condition. As the convergence condition used here, the trial of assigning all users to one of the options is executed a plurality of times with a probability according to the magnitude of the utility of the option for each user, and the most recent predetermined number of times (for example, , 50 times, 100 times, etc.), it can be defined that the user is assigned to each option at almost the same ratio.

5 and 6 are schematic diagrams for explaining an algorithm for generating recommendation information.
In the following description, the utility when the user i selects the option k is referred to _{as ui, k.} At this time, ui _{and k} are expressed as in the equation (1).

It should be noted that, for the λ _i, t _{_k,} information about the attributes of the user, and those that are registered in advance as information about the store.
In the present embodiment, the monetary value v _{i (k)} with each user in the choice k,
v i _(k) = 0: If the user has selected the option _{k v i (k) = -} ∞: user shall be set to the case where not selected the option k.
In this case, the user selects an acceptable option from the entire options without ranking.

As shown in FIG. 5, in the initial state, the user U1 selects stores A and B as options, and the user who includes the store A as an option is the user who includes the users U2 and U3 and the store B as an option. It is assumed that the user is U4. In addition, each user has 1000 monetary value in the currently assigned store, 800 monetary value per unit time of each user, 2 people can be processed by store A in unit time, and store B has unit time. The number of people that can be processed by is 5 people. In this case, the set of choices selected by each user x = {A, A, A, B}, the number of people selecting store A n _A ({A, A, A, B}) = 3, store B is selected. The number of people n _B ({A, A, A, B}) = 1.

At this time, the utility of each user based on the equation (1) is
User U1: 1000-800 x 3/2 = -200
User U2: 1000-800 x 3/2 = -200
User U3: 1000-800 x 3/2 = -200
User U4: 1000-800 x 1/5 = 840
Will be.
In the present embodiment, the option for assigning a user shall be selected according to the following rules.
-Each option k ∈ {1, ..., K} has a value of _{v k.}
_-Select each option with the probability pk defined by the following equation (2).

Use words, in the present invention, when assigning users to one alternative, the formula (2) rules for selecting each option with probability p _k defined by (hereinafter referred to as "logit selection rules".) The It uses the best response dynamics that it had.
According to the best response dynamics of this embodiment, in the initial state shown in FIG. 5, when performing recommendation, as shown in FIG. 6, the probability P _A the user U1 should stay in the store A is, P A ₌ e ^-200 / (E- ²⁰⁰ + e ⁶⁸⁰ _{), the probability P B} for user U1 to move to store B is P _B = e ⁶⁸⁰ / (e- ²⁰⁰ + e ⁶⁸⁰ ).

The above probabilities P _A and P _B are probabilities according to the magnitude of the utility of the options for the user U1 who allows the stores A and B as options, and the recommendation information generation unit 153 determines the user according to the _{above probabilities P A} and P _B. Repeat the trial of assigning options to U1. Then, the recommendation information generation unit 153 generates recommendation information for the user U1 by using the options assigned at the stage when the allocation of all the plurality of users matches the convergence condition as the solution of the equilibrium problem.
Since the process of allocating to the options with a probability according to the utility of the options for the user is repeated until the convergence condition is met, the initial state (assignment to each user's options) can be arbitrarily set. ..

[motion]
Next, the operation of the information processing system 1 will be described.
[UI display processing]
FIG. 7 is a flowchart illustrating a flow of UI display processing executed by the user terminal 10.
The UI display process is started in response to an instruction input to execute the UI display process via the input unit 815 of the user terminal 10.

When the UI display process is started, in step S1, the UI display control unit 51 accesses the server 20 and requests a recommendation regarding the store.
In step S2, the UI display control unit 51 receives the UI information of the user attribute input screen for inputting the information related to the user attribute from the server 20 and displays the user attribute input screen. As a result, the user is in a state where information regarding the user's attributes can be input.
In step S3, the user information transmission unit 52 transmits information (attributes such as name, age, gender, hobby or preference) regarding the user's attribute input to the user attribute input screen to the server 20.

In step S4, the UI display control unit 51 receives the UI information of the store selection screen that displays the list of stores that can be selected by the user from the server 20, and displays the store selection screen. As a result, the user can input the request information regarding the selection of the store.
In step S5, the user information transmission unit 52 transmits the request information (store name, visit time, etc.) input to the store selection screen to the server 20.

In step S6, the recommendation information acquisition unit 53 receives the UI information of the recommendation information display screen including the information about the store recommended by the server 20 when the recommendation information is presented, and displays the recommendation information. Display the screen.
In step S7, the user information transmission unit 52 visits the store / time regarding the result of the action actually performed by the user with respect to the recommendation on the recommendation information display screen (whether or not the recommendation is followed, or if the recommendation is not followed, at any store / time). Etc.) is transmitted to the server 20. The result of the action actually performed by the user for the recommendation on the recommendation information display screen is input by the user who has performed the action for the recommendation.
After step S7, the UI display process ends.

[Recommendation processing]
FIG. 8 is a flowchart illustrating a flow of recommendation processing executed by the server 20.
The recommendation process is started when the server 20 is started and is repeatedly executed.
When the recommendation process is started, in step S11, it is determined whether or not the user terminal 10 has accessed to request the recommendation regarding the store.
If the user terminal 10 has not accessed to request a recommendation regarding the store, NO is determined in step S11, and the process of step S11 is repeated.
On the other hand, when the user terminal 10 accesses to request a recommendation regarding the store, it is determined as YES in step S11, and the process proceeds to step S12.

In step S12, the UI screen generation unit 151 generates UI information of the user attribute input screen for inputting information regarding the user's attributes and transmits it to the user terminal 10.
In step S13, the user information acquisition unit 152 acquires information related to the user's attributes from the user terminal 10. The information regarding the user's attributes acquired at this time is stored in the user information storage unit 172.
In step S14, the UI screen generation unit 151 generates UI information on the store selection screen that displays a list of stores that can be selected by the user and accepts input of information (request information) related to store selection, and causes the user terminal 10 to generate UI information. Send.

In step S15, the user information acquisition unit 152 acquires request information regarding the selection of the store by the user. The user's request information acquired at this time is stored in the action result storage unit 173.
In step S16, the recommendation information generation unit 153 accumulates information on user attributes and user request information received from a plurality of users as a target for solving an equilibrium problem for making recommendations.

In step S17, the recommendation information generation unit 153 determines whether or not it is time to present the recommendation information.
If it is not the timing to present the recommendation information, NO is determined in step S17, and the process proceeds to step S11.
On the other hand, when it is time to present the recommendation information, YES is determined in step S17, and the process proceeds to step S18.

In step S18, the recommendation information generation unit 153 executes a balancing process that balances the competition among a plurality of users according to the probability according to the magnitude of the utility of the options for each user. By executing the balancing process, the recommendation information for each user is acquired.
In step S19, UI information of the recommendation information display screen that displays information about the store to be recommended to the user is generated and transmitted to the user terminal 10. The UI information on the recommendation information display screen includes the recommendation information acquired by the recommendation information generation unit 153.
After step S19, the recommendation process is repeated.

[Balance processing]
FIG. 9 is a flowchart illustrating a flow of equilibrium processing executed by the server 20.
The equilibrium processing is executed as a subflow in step S18 of the recommendation processing.
When the equilibrium process is started, in step S21, the recommendation information generation unit 153 acquires the accumulated information regarding the user's attributes and the user's request information.
_{In step S22, the recommendation information generation unit 153 calculates a probability pk} (see equation (2)) that reflects the magnitude of utility of each user for each of the options of each user.
In step S23, the recommendation information generating unit 153, based on the calculated probability p _k, assign each user to one of the choices.

In step S24, the recommendation information generation unit 153 determines whether or not the request information of the plurality of users is in equilibrium (the allocation of the plurality of users as a whole meets the convergence condition).
If the request information of the plurality of users is not balanced (the allocation of the plurality of users does not meet the convergence condition), NO is determined in step S24, and the process proceeds to step S23.
On the other hand, when the request information of the plurality of users is in equilibrium (the allocation of the plurality of users as a whole matches the convergence condition), YES is determined in step S24, and the process proceeds to step S25.

In step S25, the recommendation information generation unit 153 determines the option currently assigned to each user as the recommendation content for each user.
After step S25, the process returns to the recommendation process.

As described above, the information processing system 1 according to the present embodiment accepts the selection of options desired by the user, such as a restaurant, and the monetary value that each user has for each option, and the monetary value per unit time of the user. The utility when the user selects each option is calculated based on the value, the number of people who can process the options (stores, etc.) in a unit time, the set of options selected by the user, and the number of people who select each option. Further, the information processing system 1 calculates a probability using the calculated utility magnitude as an element, and selects an option for assigning the user according to the calculated probability. The information processing system 1 repeats the selection of such options, and when the allocation of all the plurality of users matches the convergence condition, the information processing system 1 presents the options assigned to each user to each user as recommendation information.
Therefore, each user is recommended among the acceptable options, and each user follows the recommendation information by the information processing system 1, so that the highest utility can be obtained for a plurality of users as a whole. It can be converged to a certain range (range of stochastic variation).
Therefore, according to the information processing system 1, it is possible to make a recommendation with a higher degree of satisfaction as a plurality of users as a whole.

One of the features of the information processing system 1 according to the present embodiment is that it is a recommendation system that involves voting or preference (preliminary selection voting for options by the user). If sufficient data on the votes or preferences of a plurality of users can be secured, it is possible to statistically predict the votes or preferences of the users.

In the information processing system 1 according to the present embodiment, a certain amount of time is secured for accepting the votes or preferences of other users from the voting or preference of the user to the recommendation to the user, but the voting or preference of the user or It is also possible to make immediate recommendations for preferences. For example, when a user requests an immediate recommendation at a store visited for lunch or when changing trains, the information processing system 1 may immediately make a recommendation under the conditions currently given. good. Further, it is possible to coexist a method of making a recommendation after securing a certain time for accepting a vote or preference of another user and a method of making a recommendation immediately for the vote or preference of a user.

In the information processing system 1 according to the present embodiment, when recommending to a user, the prediction result of the congestion situation that aggregates the voting or preference results of other users and the prediction of the congestion situation when each user follows the recommendation result. You may want to display both of the results, or switch between them. As a result, the user can make a decision with a sense of conviction in the recommendation.

The information processing system 1 according to the present embodiment is an existing recommendation system in that it uses information (voting or preference content) of another current user in order to acquire the recommendation content currently performed for the user. It has novelty for the recommendation system. Therefore, even if the user himself / herself provides the same information (votes or preferences), the behavior of other users changes, and the recommendation to the user himself / herself changes.

The information processing system 1 according to the present embodiment follows the recommendation from the information system 1 even in a situation where participants who are not users of the information system 1 and participants who are users of the information system 1 coexist. It makes it possible to choose a more appropriate option. This is as a solution to the equilibrium problem for at least some participants, as compared to the case where none of the participants take action in light of information about the votes or preferences of others and choose the option they want to choose the most. This is because recommendations are being made.

[Modification 1]
In the above-described embodiment, after presenting the recommendation information to the user, the information regarding the action result actually performed by the user for the recommendation is acquired, but based on the information regarding the action result acquired at this time, the recommendation information is acquired. Various parameters (conditions for obtaining the solution of the equilibrium problem) used in the recommendation process may be corrected.
For example, if the result of the action actually taken by the user for the recommendation does not match the recommendation at a high rate, the utility when the user selects an option may not be an appropriate value. It is possible to make corrections such as increasing (or decreasing) the monetary value per unit time of.
As a result, each time the user receives a recommendation from the information processing system 1 and repeats an action, a more appropriate recommendation is made for the user, which makes it possible to improve the convenience of the user.

[Modification 2]
In the above-described embodiment, the case where the present invention is configured as the information processing system 1 has been described as an example, but the present invention is not limited thereto. That is, the present invention can be implemented in a single information processing device 800.
FIG. 10 is a block diagram showing a functional configuration when the present invention is mounted on a single information processing device 800.
As shown in FIG. 10, when the present invention is implemented in a single information processing device 800, the UI display control unit 51 of the user terminal 10, the UI screen generation unit 151 of the server 20, the user information acquisition unit 152, and the recommendation information generation unit The CPU 811 may be provided with the functions of 153, and the store information storage unit 171, the user information storage unit 172, and the action result storage unit 173 included in the server 20 may be provided in the storage unit 817.

The information processing system 1 configured as described above includes a user terminal 10 and a server 20. The user terminal 10 includes a UI display control unit 51.
The UI display control unit 51 acquires request information representing one or a plurality of selection targets for which the user requests selection for the plurality of selection targets.
The UI display control unit 51 displays the recommendation information presented by the server 20 in response to the request information.
The server 20 includes a UI screen generation unit 151, a user information acquisition unit 152, and a recommendation information generation unit 153.
The user information acquisition unit 152 receives request information regarding a plurality of users from the plurality of user terminals 10.
The recommendation information generation unit 153 acquires the solution of the equilibrium problem by setting the selection target represented by the request information regarding the plurality of users as the equilibrium problem for the plurality of selection targets.
The UI screen generation unit 151 transmits the solution of the equilibrium problem acquired by the recommendation information generation unit 153 to the user terminal 10 as a proposal for the request information.
As a result, the recommendation is made for each user among the acceptable options, and each user follows the recommendation information by the information processing system 1, so that the competition is balanced for the plurality of users as a whole. can do.
Therefore, according to the information processing system 1, it is possible to make a recommendation with a higher degree of satisfaction as a plurality of users as a whole.

Further, the recommendation information generation unit 153 selects a plurality of users based on the probability that each of the selection targets represented by the request information has the magnitude of utility possessed by the user who selected the selection target as an element. Get the solution of the equilibrium problem by assigning to.
This makes it possible to assign each user to an option according to the probability of reflecting the utility that each user has for each option.

Further, the recommendation information generation unit 153 repeats the process of assigning a plurality of users to any of the selection targets based on the above probability, and when the allocation of the plurality of users matches the set convergence condition, each user is assigned. The currently assigned option is the solution to the equilibrium problem.
As a result, it is possible for a plurality of users as a whole to make recommendations that converge from the state in which the highest utility can be obtained to a certain range (range of stochastic variation).

In addition, the user information acquisition unit 152 acquires information on the result of the action actually performed by the user with respect to the above proposal transmitted by the UI screen generation unit 151.
The recommendation information generation unit 153 corrects the condition for subsequently acquiring the solution of the equilibrium problem based on the information regarding the action result acquired by the user information acquisition unit 152.
As a result, each time the user receives a recommendation from the information processing system 1 and repeats an action, a more appropriate recommendation is made for the user, which makes it possible to improve the convenience of the user.

In addition, the recommendation information generation unit 153 acquires the solution of the equilibrium problem related to the expected competition of the selection target in the event in which the actual action of the user with respect to the selection target is the selection result.
This makes it possible to make recommendations by the information processing system 1 in a system in which a plurality of users are selected in real time.

In addition, the recommendation information generation unit 153 acquires the solution of the equilibrium problem related to the competition of the scheduled selection target in the event in which the assertion of the action schedule of the user with respect to the selection target results in the selection result.
As a result, the information processing system 1 can make a recommendation in a system that can accumulate the user's selection result for the recommendation.

The present invention is not limited to the above-described embodiment, and modifications, improvements, and the like within the range in which the object of the present invention can be achieved are included in the present invention.
That is, the present invention can be applied to a system in which a plurality of users are selected in real time, such as selection of a store during lunch time and selection of a route to a destination in a navigation system. In a system in which a plurality of users are selected in real time, the information processing system 1 acquires a solution of a balance problem related to a competition (expected congestion situation) of an expected selection target, and makes a recommendation from the information processing system 1. On the other hand, the actual behavior of the user is the selection result. That is, the user's action is directly performed (that is, the action for the recommendation is performed only once) with respect to the recommendation from the information processing system 1.

Further, the present invention can be applied to a system capable of accumulating user selection results for recommendations, such as reservation of accommodation facilities and application for tickets for events (concerts, etc.) in which multiple performances are performed. In a system capable of accumulating the user's selection results for recommendations, the information processing system 1 acquires a solution of a balance problem related to the planned competition (concentration of future actions) of the selection target, and the information processing system 1 provides a solution. It is possible to accumulate the selection results of the users for the recommendations, refer to the selection results of a plurality of users, and perform the recommendation again from the information processing system 1. That is, in a system that can accumulate the user's selection result for the recommendation, the user's selection result for the recommendation (reservation or lottery that expresses the action schedule) in a situation where the user's future behavior such as reservation or lottery application is grasped. It is possible to make recommendations to users multiple times while accumulating the results of changes in) and sequentially acquiring solutions to equilibrium problems.

Further, in the above-described embodiment, when making a recommendation to the user, along with the recommendation information, information giving added value to the user (for example, information on coupons available at the recommended store or when the recommendation is followed). Information on points given to) may be presented. Furthermore, it analyzes whether or not there is a change in the user's behavior result depending on whether the information that adds value to the user is presented together with the recommendation information or not, and according to the analysis result, the user is notified. Information that adds value may be used as information that controls the feasibility of recommendations.

The series of processes described above can be executed by hardware or software.
In other words, the functional configurations of FIGS. 1 and 3 are merely examples and are not particularly limited. That is, it suffices if the information processing system 1 is provided with a function capable of executing the above-mentioned series of processes as a whole, and what kind of functional block is used to realize this function is not particularly limited.
Further, one functional block may be configured by a single piece of hardware, a single piece of software, or a combination thereof.
The functional configuration in the present embodiment is realized by a processor that executes arithmetic processing, and the processor that can be used in the present embodiment is composed of various processing devices such as a single processor, a multiprocessor, and a multicore processor. In addition to the above, the present invention includes a combination of these various processing devices and processing circuits such as an ASIC (Application Specific Integrated Circuit) and an FPGA (Field-Programmable Gate Array).

When a series of processes are executed by software, the programs constituting the software are installed on a computer or the like from a network or a recording medium.
The computer may be a computer embedded in dedicated hardware. Further, the computer may be a computer capable of executing various functions by installing various programs, for example, a general-purpose personal computer.

The recording medium containing such a program is not only composed of removable media distributed separately from the device main body in order to provide the program to the user, but is also provided to the user in a state of being preliminarily incorporated in the device main body. It is composed of a recording medium and the like. The removable media is composed of, for example, a magnetic disk (including a floppy disk), an optical disk, a magneto-optical disk, or the like. The optical disk is composed of, for example, a CD-ROM (Compact Disk-Read Only Memory), a DVD (Digital Versailles Disk), a Blu-ray (registered trademark) Disc (Blu-ray Disc), or the like. The magneto-optical disk is composed of an MD (Mini-Disc) or the like. Further, the recording medium provided to the user in a state of being preliminarily incorporated in the apparatus main body is composed of, for example, a ROM (Read Only Memory) in which the program is recorded, a semiconductor memory included in the storage unit 20B, or the like.

Although some embodiments of the present invention have been described above, these embodiments are merely examples and do not limit the technical scope of the present invention. The present invention can take various other embodiments, and various modifications such as omission and substitution can be made without departing from the gist of the present invention. These embodiments and modifications thereof are included in the scope and gist of the invention described in the present specification and the like, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

1 Information processing system, 10 user terminals, 20 servers, 30 networks, 51 user interface display control unit (UI display control unit), 52 user information transmission unit, 53 recommendation information acquisition unit, 151 user interface screen generation unit (UI screen generation) Department), 152 User information acquisition unit, 153 Recommendation information generation unit, 171 Store information storage unit, 172 User information storage unit, 173 Action result storage unit, 800 Information processing device, 811 CPU, 812 ROM, 813 RAM, 814 bus, 815 input unit, 816 output unit, 817 storage unit, 818 communication unit, 819 drive, 820 imaging unit, 831 removable media

Claims

An information processing system including a terminal device used by a user and a server configured to be able to communicate with the terminal device.
The terminal device is
A request information acquisition means for acquiring request information representing one or a plurality of the selection targets for which the user requests selection for a plurality of selection targets.
It is provided with a recommendation information display means for displaying the recommendation information presented from the server in response to the request information.
The server
A request information receiving means for receiving the request information regarding a plurality of users from the plurality of terminal devices, and
An equilibrium processing means for acquiring a solution of the equilibrium problem by using the selection target represented by the request information regarding a plurality of users as an equilibrium problem for the plurality of selection targets.
A recommendation information transmitting means for transmitting the solution of the equilibrium problem acquired by the equilibrium processing means to the terminal device as a proposal for the required information, and
An information processing system characterized by being equipped with.
The equilibrium processing means selects a plurality of users as one of the selection targets based on the probability that each of the selection targets represented by the request information has a magnitude of utility possessed by the user who has selected the selection target as an element. The information processing system according to claim 1, wherein a solution to the equilibrium problem is obtained by assigning to.
The equilibrium processing means repeats the process of assigning a plurality of users to one of the selection targets based on the probability, and when the allocation of the plurality of users meets the set convergence condition, each user is currently assigned. The information processing system according to claim 1 or 2, wherein the option provided is a solution to the equilibrium problem.
The server
The action result acquisition means for acquiring the information about the action result actually performed by the user with respect to the proposal transmitted by the recommendation information transmission means is provided.
Any of claims 1 to 3, wherein the equilibrium processing means corrects a condition for subsequently acquiring a solution of the equilibrium problem based on the information about the action result acquired by the action result acquisition means. The information processing system according to item 1.
Claims 1 to 4 are characterized in that the equilibrium processing means obtains a solution of an equilibrium problem relating to an expected competition of the selected object in an event in which the actual action of the user with respect to the selected object results in the selection. The information processing system according to any one of the above.
From claim 1, the equilibrium processing means obtains a solution of an equilibrium problem relating to a competition of a scheduled selection target in an event in which an assertion of the user's action schedule with respect to the selection target results in a selection. The information processing system according to any one of 4.
A request information acquisition means for acquiring request information representing one or a plurality of the selection targets for which a user requests selection for a plurality of selection targets.
An equilibrium processing means for acquiring a solution of the equilibrium problem by using the selection target represented by the request information regarding a plurality of users as an equilibrium problem for the plurality of selection targets.
The recommendation information output means that outputs the solution of the equilibrium problem acquired by the equilibrium processing means as a proposal for the required information, and
An information processing device characterized by being equipped with.
A terminal device in an information processing system including a terminal device used by a user and a server configured to be able to communicate with the terminal device.
A request information acquisition means for acquiring request information representing one or a plurality of the selection targets for which the user requests selection for a plurality of selection targets.
A recommendation information display means for acquiring and displaying recommendation information, which is the result of acquiring a solution of the selection target represented by the request information regarding a plurality of users as an equilibrium problem for the plurality of selection targets, from the server.
A terminal device comprising.
Information processing device
A request information acquisition step for acquiring request information representing one or a plurality of the selection targets for which the user requests selection for a plurality of selection targets, and
An equilibrium processing step for acquiring a solution of the equilibrium problem by using the selection target represented by the request information regarding a plurality of users as an equilibrium problem for the plurality of selection targets.
A recommendation information output step that outputs the solution of the equilibrium problem acquired by the equilibrium processing means as a proposal for the required information, and
An information processing method characterized by including.
An information processing method executed by a terminal device in an information processing system including a terminal device used by a user and a server configured to be able to communicate with the terminal device.
A request information acquisition step for acquiring request information representing one or a plurality of the selection targets for which the user requests selection for a plurality of selection targets.
A recommendation information display step of acquiring and displaying recommendation information, which is the result of acquiring a solution of the selection target represented by the request information regarding a plurality of users as an equilibrium problem for the plurality of selection targets, from the server.
An information processing method characterized by including.
On the computer
A request information acquisition function for acquiring request information representing one or a plurality of the selection targets for which the user requests selection for a plurality of selection targets, and
An equilibrium processing function for acquiring a solution of the equilibrium problem by using the selection target represented by the request information regarding a plurality of users as an equilibrium problem for the plurality of selection targets.
A recommendation information output function that outputs the solution of the equilibrium problem acquired by the equilibrium processing function as a proposal for the required information, and
A program characterized by realizing.
A computer that constitutes a terminal device in an information processing system including a terminal device used by a user and a server configured to be able to communicate with the terminal device.
A request information acquisition function for acquiring request information representing one or a plurality of the selection targets for which the user requests selection for a plurality of selection targets.
A recommendation information display function that acquires and displays recommendation information, which is the result of acquiring a solution of the selection target represented by the request information regarding a plurality of users as an equilibrium problem for the plurality of selection targets, from the server.
A program characterized by realizing.