JP2023044492A - Information processing device, information processing method, and information processing program - Google Patents

Abstract

To provide an information processing device capable of appropriately selecting information for a transaction object provided to a user, an information processing method, and an information processing program.SOLUTION: In an information processing system 1, an information processing device 100 acquires user information and transaction object information from an external device 20 and receives a search query entered by the user from a terminal device 10. The information processing device comprises a seed selection unit 134 and a transaction object selection unit 135. The seed selection unit selects a seed selection object serving as a seed used to select a transaction object provided to the user from among browsing transaction objects serving as transaction objects browsed by users indicated by a user action history, on the basis of at least one standard among a plurality of standards on selection of transaction objects provided to users. The transaction selection unit selects a transaction object displayed in prescribed content from a transaction object group using a seed transaction object selected by the seed selection unit, when displaying a prescribed content.SELECTED DRAWING: Figure 5

Description

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

Conventionally, techniques for providing various information to users are known. For example, a technique is provided for selecting content to be provided to a user based on the user's viewing of the content using a recommendation system.

JP 2016-051357 A

However, the above conventional techniques have room for improvement. In the conventional technology described above, contents are only distributed according to the user's attributes, and it is not always possible to appropriately select information other than the contents.

The present application has been made in view of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can appropriately select information on a transaction target to be provided to the user. .

An information processing apparatus according to the present application includes a logic selection unit that selects a selection logic from among a plurality of selection logics for selecting a seed transaction object used for selecting a transaction object to be provided to a user; a seed selection unit that selects the seed transaction object from among the viewed transaction objects that are the transaction objects viewed by the user indicated by the action history of the user, using the selection logic selected by the selection unit; It is characterized by having

According to one aspect of the embodiment, there is an effect that it is possible to appropriately select the information of the transaction target to be provided to the user.

FIG. 1 is a diagram illustrating an example of information processing executed by an information processing apparatus according to an embodiment; FIG. 2 is a diagram showing a specific example of order of transaction targets according to the embodiment. FIG. 3 is a diagram showing a specific example of content according to the embodiment. FIG. 4 is a conceptual diagram relating to browsing of transaction targets by the user. FIG. 5 is a diagram illustrating a configuration example of an information processing system according to the embodiment; 6 is a diagram illustrating an example of a user information storage unit according to the embodiment; FIG. FIG. 7 is a diagram illustrating an example of a transaction target information storage unit according to the embodiment; 8 is a diagram illustrating an example of a content storage unit according to the embodiment; FIG. 9 is a diagram illustrating an example of a reference information storage unit according to the embodiment; FIG. 10 is a flowchart illustrating an example of the flow of information processing executed by the information processing apparatus according to the embodiment; FIG. FIG. 11 is a diagram illustrating an example of processing related to collaborative filtering. FIG. 12 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus.

Embodiments for implementing an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail below with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment. Further, each embodiment can be appropriately combined within a range that does not contradict the processing contents. Also, in each of the following embodiments, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

(embodiment)
[1. Example of information processing]
First, an example of information processing executed by the information processing apparatus 100 will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing executed by an information processing apparatus 100 according to an embodiment. The information processing device 100 executes information processing on a transaction target traded in an electronic commerce (EC) service. Here, the transaction object is the use of goods or services. Transaction objects traded in electronic commerce services include transaction objects traded in various modes such as online shopping sites, auction sites, and flea market sites. Note that FIG. 1 shows an example of information processing for a transaction object traded on an auction site.

First, an overview of the flow of information processing performed by the information processing apparatus 100 will be described. First, the information processing apparatus 100 selects a selection logic from among a plurality of selection logics for selecting a seed (also referred to as a "seed transaction target") used for selecting a transaction target to be provided to the user. Then, the information processing apparatus 100 selects a seed transaction object from the transaction objects browsed by the user (also referred to as “browsed transaction object”) using the selected selection logic. Then, when the user displays predetermined content, the information processing apparatus 100 selects a transaction object displayed in the predetermined content (also referred to as a “display transaction object”) from among the transaction object group as a seed transaction object. Select using . Then, the information processing device 100 provides content including the selected transaction object. A flow of information processing performed by such an information processing apparatus 100 will be described with reference to FIG.

First, the information processing device 100 acquires user information about a user from the external device 20 (step S1). The external device 20 transmits user information about the user to the information processing device 100 . In FIG. 1, the information processing apparatus 100 acquires the user's action history as user information about the user. The information processing device 100 acquires from the external device 20 information indicating the transaction target for which the user viewed information and the date and time when the viewing was performed. The information processing device 100 acquires from the external device 20 information indicating the transaction target whose information is displayed on the terminal device 10 used by the user and the date and time when the display was performed. In addition, the terminal device 10 is one or more terminal devices (devices) used by the user, and if the user account (user ID, etc.) is the same, a smartphone (smartphone), a PC (personal computer), etc. Transaction object histories are recorded in common for a plurality of terminal devices 10 used by one user.

For example, the information processing apparatus 100 acquires from the external device 20 the user's action history indicating the user's viewing of the transaction object, such as the display history of the content including the transaction object on the terminal device 10 . For example, the information processing device 100 acquires from the external device 20 information indicating the transaction target included in the content provided to the user. For example, the information processing apparatus 100 acquires user information each time a content provision request is received from the terminal apparatus 10 (every step S3 in FIG. 1). The information processing apparatus 100 may acquire the user information from the external apparatus 20 every predetermined period (for example, 5 hours, 1 day, etc.). In FIG. 1 , the information processing apparatus 100 stores, as user information of each user, an action history indicating browsed transaction targets for which each user such as the user U1 browsed information and the date and time when the information was browsed, as user information of an external device. 20. Note that in FIG. 1, the information processing apparatus 100 stores what kind of action history in the external device 20 if it is possible to identify the transaction target for which each user such as the user U1 browsed information and the date and time when the information was browsed. may be obtained from

Moreover, the above is merely an example, and the user information acquired by the information processing apparatus 100 is not limited to the user's action history, and may include various information as long as it is information related to the user. For example, when a user has registered as a member of a predetermined service, the information processing apparatus 100 may acquire information registered by the user at the time of member registration as user information. For example, the information processing apparatus 100 stores, as user information, attribute information on attributes such as the user's gender, age, telephone number, address, etc., and purchase history on Internet shopping, electronic shopping malls, auction sites, flea market sites, and the like. may be obtained.

In addition, the information processing device 100 acquires information about the transaction target from the external device 20 (step S2). For example, the information processing device 100 acquires from the external device 20 information about a group of trading objects traded on an auction site. For example, the information processing device 100 acquires from the external device 20 information about a group of transaction objects (such as sporting goods) that are being bid on at an auction site. For example, the information processing device 100 acquires information on the transaction target from the external device 20 at regular intervals.

In the above example, the information processing device 100 performs the acquisition process in steps S1 and S2. Information about the object may be obtained at the same time.

The information processing device 100 also receives a content provision request from the terminal device 10 (step S3). For example, the information processing apparatus 100 receives a request for provision of a portal site from the terminal device 10 as an example of content.

In the above example, the information processing apparatus 100 executes step S1 and step S2, and then executes step S3. However, the information processing apparatus 100 executes step S3, Step S1 and step S2 may be performed.

Then, the information processing device 100 selects a selection logic from among a plurality of selection logics for selecting a seed transaction object (step S4). For example, the information processing apparatus 100 selects a selection logic from among a plurality of selection logics each corresponding to at least one of the plurality of criteria. In FIG. 1, the information processing device 100 includes a first selection logic for randomly selecting a seed transaction target from among the transaction targets viewed by the user, and A selection logic is selected from a second selection logic that selects (eg, 10) trading objects as seed trading objects. Note that the case where N is 10 is merely an example, and any number such as 5, 20, 30, etc., can be adopted for N. Also, in FIG. 1, for the sake of simplification of explanation, a case where the plurality of selection logics are only the first selection logic and the second selection logic will be described. Selection logic may be included, such as a third selection logic, a fourth selection logic, etc., based on different criteria than the selection logic.

Here, in FIG. 1, the information processing apparatus 100 selects a selection logic from among a plurality of selection logics by a multi-armed bandit method. In this way, the information processing apparatus 100 selects a selection logic from among a plurality of selection logics by a multi-armed bandit method, which is a case in which the state does not change in reinforcement learning. For example, the information processing device 100 selects a selection logic from among a plurality of selection logics by a technique related to reinforcement learning. Note that the information processing apparatus 100 may select the selection logic by appropriately using various methods other than the multi-armed bandit as long as the method is related to reinforcement learning.

For the sake of explanation, a case will be described below in which the information processing apparatus 100 selects a selection logic from among a plurality of selection logics by an epsilon greedy (ε-greedy) algorithm. For example, given a first selection logic and a second selection logic, one would expect the second selection logic to be the logic that selects the best seed, given that recent behavior indicates that user's interest. On the other hand, the first selection logic, for example, has a larger population that can be seed transactions than the second selection logic, and can cause users to recognize and select various transaction targets than the second selection logic. selection logic. The information processing device 100 selectively uses logic other than the second selection logic, such as a second selection logic corresponding to utilization in a multi-armed bandit and a first selection logic corresponding to search.

In FIG. 1, the information processing apparatus 100 selects the second selection logic with a probability of "0.8 (=1-0.2)" when ε is "0.2", and selects the second selection logic with a probability of "0.2". to select another logic (for example, the first selection logic). For example, the information processing apparatus 100 selects the second selection logic with a probability of 80% and selects the first selection logic with a probability of 20% in response to a request from the user. Note that the case where ε is "0.2" is merely an example, and the value of ε may be appropriately set, for example, to "0.5" according to the relationship of each selection logic. Also, the epsilon greedy algorithm is merely an example, and the information processing apparatus 100 may use other multi-armed bandit methods such as Softmax, which will be described later.

Then, the information processing device 100 selects a seed transaction target from among the transaction targets browsed by the user using the selected selection logic (step S5). For example, when the information processing apparatus 100 selects the first selection logic by the multi-armed bandit technique in response to a request from the user U1, the information processing apparatus 100 randomly conducts a seed transaction for all of the browsing transaction targets of the user U1. Select a target. On the other hand, when the second selection logic is selected by the multi-armed bandit technique in response to a request from user U2, information processing apparatus 100 selects N transaction targets viewed by user U2 most recently as targets. Select a seed deal target. Note that the selection logic is selected for each request, and when the user U1 makes multiple requests, the first selection logic is selected once for each of the multiple requests from the user U1, Or another time the second selection logic may be selected. In this way, the information processing apparatus 100 selects the logic to be used from a plurality of logics by the multi-armed bandit method for each request.

Then, the information processing apparatus 100 selects the display transaction object displayed in the predetermined content provided by the user from the transaction object group using the seed transaction object (step S6). For example, the information processing apparatus 100 selects a display transaction object from among the transaction object group based on the co-occurrence with the seed transaction object. In FIG. 1, the information processing apparatus 100 selects display trading objects by item (trade object)-based collaborative filtering. An example of this point will be briefly described with reference to FIG. FIG. 11 is a diagram illustrating an example of processing related to collaborative filtering.

In the example shown in FIG. 11, the seed transaction object is the transaction object SD1, and the information processing device 100 calculates a similarity score (also simply referred to as “similarity” or “score”) with other transaction objects GD1 to GD3. indicates when The information processing device 100 calculates the similarity of the browsing vector of the user for each transaction target. In FIG. 11, the information processing apparatus 100 uses a plurality of users such as users a, b, c, and d as elements for transaction object SD1 and other transaction objects GD1 to GD3, etc., as shown in table T1. Then, the similarity of the browsing vector is calculated.

The information processing device 100 calculates the degree of similarity between the transaction object SD1 and the transaction object GD1 to be 0.92. Further, the information processing device 100 calculates the degree of similarity between the transaction object SD1 and the transaction object GD2 as 0.77. Further, the information processing device 100 calculates the degree of similarity between the transaction object SD1 and the transaction object GD3 to be 0.27. Then, the information processing apparatus 100 ranks (orders) the other transaction targets GD1 to GD3, etc. in order of similarity (score), as shown in a display T2. In FIG. 11 , the information processing apparatus 100 ranks the transaction object GD1, the transaction object GD2, and the transaction object GD3 in descending order of score. A detailed description of collaborative filtering is omitted.

In FIG. 1, the information processing apparatus 100 calculates the degree of similarity (score) between each seed transaction object and other transaction objects. Then, the information processing apparatus 100 ranks the transaction objects in descending order of the score calculated for each seed transaction object.

Here, using FIG. 2, a specific example of the ranking based on the score of the trading object is shown. FIG. 2 is a diagram showing a specific example of order of transaction targets according to the embodiment. FIG. 2 shows a table TA1 in which the order of transaction targets, transaction target IDs (identifiers) that are identification information for identifying transaction targets, and similarities (scores) are associated with each other.

According to the table TA1, the rank "1st" is the transaction object ID "M15" and the score is "1.0". The rank "second" is the transaction object ID "M34" and the score is "0.94". The rank "3rd" is the transaction object ID "M7" and the score is "0.89". The rank "4th" is the transaction object ID "M162" and the score is "0.84". The rank "5th" is the transaction object ID "M41" and the score is "0.79".

The rank "6th" is the transaction object ID "M77" and the score is "0.74". The rank "7th" is the transaction object ID "M18" and the score is "0.68". The rank "8th" is the transaction object ID "M1" and the score is "0.63". The rank “9th” is the transaction object ID “M85” and the score is “0.58”. The rank "10th" is the transaction object ID "M91" and the score is "0.53".

In this way, the information processing apparatus 100 determines the order of the transaction objects by calculating the score for the transaction objects acquired from the external device 20 . For example, the information processing device 100 ranks the transaction objects in descending order of score. When there are multiple seed transaction targets, the information processing apparatus 100 may calculate multiple scores for each transaction target. In this case, the information processing apparatus 100 may use the score (maximum score) having the largest value among the calculated scores for each transaction object as the score of the transaction object. Further, the information processing apparatus 100 may use an average value (average score) of a plurality of scores calculated for each transaction object as the score of the transaction object.

Based on the score of each transaction object, the information processing device 100 selects the top six transaction objects with the highest scores as display transaction objects. In FIG. 2, the information processing apparatus 100 selects transaction objects with transaction object IDs "M7", "M8", "M9", "M10", "M11", and "M1" as display transaction objects. Note that the number of six is merely an example, and the information processing apparatus 100 selects an arbitrary number (eg, 3, 12, etc.) of display transaction objects according to, for example, the display area of the content.

Then, the information processing device 100 provides content including the displayed trading object (step S7). In FIG. 1, the information processing apparatus 100 selects six displayed transaction objects "M15", "M34", "M7", "M162", "M41", and "M77" in descending order of score. The terminal device 10 is provided with content related to the portal site, which is arranged in a predetermined display frame. Although FIG. 1 shows one request for explanation, the information processing apparatus 100 repeats the processing shown in steps S4 to S7 for each request (step S3).

Contents provided to the terminal device 10 will now be described with reference to FIG. FIG. 3 is a diagram showing a specific example of content according to the embodiment. For example, content C1 is content related to a portal site.

Also, the content C1 includes various types of information. For example, the content C1 includes a search window, information on news, information on content often displayed to users, advertising content, and the like.

Here, the content C1 includes an area AR1 as a predetermined display frame. In FIG. 3, six trading objects to be traded at A Online Shop, which is an auction service, are arranged in the area AR1. For example, in the area AR1, the upper left row is "1st" ranking "M15", the upper middle row is "2nd" ranking "M34", the upper right row is "3rd" ranking "M7", and the lower left row is "M15" ranking "2nd". Transaction objects are arranged in the order of "M162" of "4th place", "M41" of "5th place" in the lower middle row, and "M77" of "6th place" in the lower right row. FIG. 3 shows a case where display transaction objects (sports goods, etc.) such as rackets and uniforms are displayed. Note that the above arrangement is merely an example, and any arrangement mode can be employed.

Conventionally, there were cases where it was not always possible to appropriately select information other than content. Therefore, the information processing apparatus 100 according to the embodiment selects a plurality of selection logics for selecting a seed transaction object to be used for selecting a transaction object to be provided to the user, thereby appropriately switching the selection logic. , to select a seed trade target. Then, the information processing apparatus 100 selects a transaction target to be displayed in predetermined content using the selected seed transaction target. Thereby, the information processing apparatus 100 can appropriately select the information of the transaction target to be provided to the user.

For example, the presumption that the second selection logic is the optimal logic, as described above, is based on the assumption that the most recent behavior indicates the user's interest. For example, the assumption that the selection logic based on the user's attention level criteria for the traded object is the optimal logic is based on the assumption that recent behavior indicates that user's interest. However, this assumption does not necessarily hold true. Therefore, the information processing apparatus 100 selects the seed transaction object by appropriately switching the selection logic using the multi-armed bandit method, and selects the transaction object displayed in the predetermined content using the selected seed transaction object. . As a result, the information processing apparatus 100 selectively uses logic other than the second selection logic, such as the second selection logic corresponding to the utilization in the multi-armed bandit and the first selection logic corresponding to the search, to display in the predetermined content. Select a transaction target. As a result, the information processing apparatus 100 can selectively use a plurality of selection logics to increase the possibility that the user will perform a profitable action such as purchasing the transaction target.

[1-1. Other examples (softmax, popularity, diversity, recognition standards, etc.)]
It should be noted that the selection of the display transaction object described above is merely an example, and the information processing apparatus 100 may select the display transaction object using various information as appropriate. An example of this point will be described below. It should be noted that descriptions of the same points as those described above will be omitted as appropriate. For example, the process of selecting the display transaction object after selecting the seed transaction object is the same as the process described with reference to FIG. 1, so the description thereof is omitted.

As described above, the information processing apparatus 100 may use, for example, the softmax technique in the multi-armed bandit technique. Since the softmax method is well known, a detailed description thereof will be omitted. may also be left to select a seed trading object. For example, the information processing apparatus 100 may increase the probability that a viewed transaction object with a more recent history is selected. For example, the more recent browse transaction object is selected, the more recent the browse transaction object is, such as the probability that the browse transaction object browsed by the user one day ago is selected is 30 times the probability of being selected as the browse transaction object browsed by the user 30 days ago. The probability of being selected as a seed transaction target may be increased.

For example, if the probability of selecting the history (viewing transaction target) from 21 to 30 days ago is a predetermined value x, the probability of selecting the history (viewing transaction target) from 11 to 20 days ago is 2x (2 of the predetermined value x). times), and the probability of selecting a history (viewed transaction object) from 1 to 10 days ago may be 3x (three times the predetermined value x). For example, there are histories A, B, C, D, E, F, and G, and histories A and B correspond to histories from 1 to 10 days ago, histories C and D correspond to histories from E, F, and G correspond to the history of 21 to 30 days ago. In this case, the information processing apparatus 100 stores the histories A, A, A, B, B, B, C, C, D, D, E, F, and G for selection probability calculation, and the histories from 1 to 10 days ago. Doubling, doubling the history from 11 to 20 days ago. As a result, the information processing apparatus 100 sets the probability of selecting the histories A and B from 1 to 10 days ago to 3/13, the probability of selecting the histories C and D of 11 to 20 days ago to 2/13, and from 21 to 21 The probability of selecting histories E, F, and G 30 days ago is set to 1/13.

For example, the information processing apparatus 100 may create a dictionary for selection, and at this time, may pad the probability operations according to the history. In the above example, the information processing apparatus 100 performs {1:A, 2:A, 3:A, 4:B, 5:B, 6:B, 7:C, 8:C, . . . , 13:G}, and the keys of the created dictionary are randomly shuffled. The information processing apparatus 100 acquires the history of the value corresponding to the shuffled key as a set. Note that the above is merely an example, and the information processing apparatus 100 may select a seed transaction target using a technique related to Softmax or the like.

Further, for example, the information processing device 100 selects a seed transaction object based on at least one of a plurality of criteria for selection of a transaction object provided to the user, and uses the selected seed transaction object. , a trading object to be displayed in a predetermined content may be selected from the trading object group. For example, the information processing device 100 is based on at least one of a plurality of criteria regarding the user's attention to the transaction object, the diversity of the transaction object, and the user's recognition of the transaction object. , may select a seed trading object.

For example, the information processing device 100 may select the seed transaction object based on a criterion regarding the user's attention to the transaction object. For example, the information processing apparatus 100 may select a transaction object that attracts a high degree of user attention as a seed transaction object. For example, the information processing apparatus 100 presumes that a transaction object that has been repeatedly viewed in the user's action history is a transaction object that attracts a high degree of attention from the user (a high-profile transaction object), and determines that transaction object. It may be selected as a seed trading object. For example, the information processing apparatus 100 may select, as a seed transaction object, a transaction object (a high-profile transaction object) with a viewing frequency of a user equal to or higher than a predetermined threshold.

Here, referring to FIG. 4, browsing of transaction targets by the user will be described. FIG. 4 is a conceptual diagram relating to browsing of transaction targets by the user. The transaction object browsing history LG1 in FIG. 4 indicates the transaction object (browsed transaction object) browsed by the user U2. FIG. 4 shows a case where the user U2 has a history of viewing pages PG1 to PG5, etc. containing information on the transaction target. indicates that That is, FIG. 4 shows that the user U2 most recently browsed the transaction target, which is the fishing gear included in the page PG1. It can be assumed that the most recent behavioral history indicates user U2's interest. For example, the information processing apparatus 100 may estimate that the viewed transaction object in the most recent action history is the transaction object that attracts the attention of the user. For example, in the example of FIG. 4, the information processing apparatus 100 may estimate that the transaction target, which is the fishing tackle included in the page PG1, is the transaction target that attracts a high degree of attention from the user U2.

In addition, for example, the information processing device 100 presumes that a transaction target viewed most recently in the user's action history is a transaction target with a high degree of user attention (a high-profile transaction target). may select that trading object as a seed trading object. For example, the information processing apparatus 100 may select a predetermined number of transaction objects (high-profile transaction objects) that have been recently viewed by the user as seed transaction objects.

For example, the information processing device 100 may select seed trading objects based on a criterion relating to diversity of trading objects. For example, the information processing apparatus 100 may select seed transaction objects so as to satisfy the diversity of categories of viewed transaction objects included in the user's action history. For example, when there are multiple categories of browsed transaction objects included in the user's action history, the information processing apparatus 100 may select a transaction object corresponding to each category as a seed transaction object.

For example, the information processing apparatus 100 may select seed transaction targets in consideration of both attention and diversity. In this case, the information processing apparatus 100 may select the seed transaction object by considering the category diversity while considering the viewing frequency. For example, when there are multiple categories of browsed transaction objects included in the user's action history, the information processing apparatus 100 seeds the transaction object with the largest number of times of browsing among the transaction objects corresponding to each category. It may be selected as a trading object.

For example, the information processing device 100 may select the seed transaction object based on a criterion relating to the user's recognition of the transaction object. For example, while prioritizing the most recent action history, the information processing apparatus 100 exploratoryly selects browsing transaction targets included in the action history of the user using a multi-armed bandit algorithm to perform seed transactions. You can choose a target.

The information processing apparatus 100 may select a selection logic from among a plurality of selection logics each corresponding to at least one of the plurality of criteria, and use the selected logic. For example, the information processing device 100 includes a plurality of selection logics corresponding to at least one of a plurality of criteria including a criterion relating to the user's awareness of the transaction object and a criterion relating to the user's attention to the transaction object. The selection logic may be selected from.

For example, the information processing device 100 selects a selection logic from among a plurality of selection logics including a first selection logic that is a selection logic based on the user's recognition criteria for the transaction object or the diversity of the transaction object. good too. For example, the information processing device 100 may select a selection logic from among a plurality of selection logics including a second selection logic which is a selection logic based on the user's degree of attention to the transaction target. For example, the information processing device 100 may select a selection logic from among a plurality of selection logics including a selection logic (for example, a third selection logic) based on a criterion of diversity of transaction targets.

[2. Configuration of information processing system]
As shown in FIG. 5 , the information processing system 1 includes a terminal device 10 , an external device 20 and an information processing device 100 . The terminal device 10, the external device 20, and the information processing device 100 are connected via a network N so as to be communicable by wire or wirelessly. The information processing system 1 shown in FIG. 5 may include a plurality of terminal devices 10, a plurality of external devices 20, and a plurality of information processing devices 100. FIG.

The terminal device 10 according to the embodiment is an information processing device used by a user who accesses content such as web pages displayed on a browser and content for applications. For example, the terminal device 10 is a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), or the like. Note that the terminal device 10 is not limited to the above example, and may be, for example, a smart watch or a wearable device.

The external device 20 according to the embodiment is an information processing device that provides various types of information, and is realized by, for example, a server device or a cloud system. For example, the external device 20 provides user information as various information. As another example, the external device 20 may be an Internet shopping site, an electronic shopping mall, a flea market site, an auction site, a travel or restaurant reservation site, a credit card contract site, a financial product providing site, or the like. provide information about traded objects in

The information processing device 100 according to the embodiment is an information processing device that can communicate with various devices via a predetermined network N such as the Internet, and is realized by, for example, a server device or a cloud system. For example, the information processing device 100 is communicably connected to various other devices via a network N. FIG.

[3. Configuration of Information Processing Device]
An example of the functional configuration of the information processing apparatus 100 described above will be described below. FIG. 5 is a diagram illustrating a configuration example of the information processing apparatus 100 according to the embodiment. As shown in FIG. 5, the information processing apparatus 100 has a communication section 110, a storage section 120, and a control section .

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information to and from other various devices.

(storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 also has a user information storage unit 121 , a transaction target information storage unit 122 , a content storage unit 123 and a reference information storage unit 124 .

(User information storage unit 121)
The user information storage unit 121 stores various user information about users. 6 is a diagram illustrating an example of a user information storage unit according to the embodiment; FIG. In the example shown in FIG. 6, the user information storage unit 121 has items such as "user ID" and "user information". For example, "user information" includes items such as "attribute information", "purchase history", and "browsing history".

"User ID" is an identifier that identifies a user. The "attribute information" is attribute information related to attributes of the user associated with the "user ID". For example, the attribute information includes age, gender, phone number, address, etc. of the user.

“Purchase history” is the purchase history of purchases made by the user associated with the “user ID”. For example, the purchase history includes information on the transaction object purchased by the user, the type of transaction object, the number of purchases of the transaction object, information on the date and time when the transaction object was purchased, and the like.

"Browsing history" is a history of content being browsed by the user associated with the "user ID". For example, the “browsing history” may be a history of content displayed on the terminal device 10 used by the user. For example, the browsing history includes information on content browsed (displayed) by the user, the type of content, the number of times the content was displayed, and information on the date and time the content was displayed.

For example, in FIG. 6, "U1" identified by the user ID has attribute information "CH1", purchase history "PH1", and display history "WA1". In the example shown in FIG. 6, the attribute information and the like are represented by abstract codes such as "CH1", but the attribute information and the like are represented by specific numerical values, specific character strings, and various types of information. It may be a file format or the like that includes.

It should be noted that the user information storage unit 121 may store various types of information, not limited to the above, depending on the purpose. The user information storage unit 121 may store, for each user, information indicating the number of times the information is displayed for each transaction target, for example, the number of times the user views the information.

(Transaction target information storage unit 122)
The transaction target information storage unit 122 stores various transaction target information related to the transaction target. FIG. 7 is a diagram illustrating an example of a transaction target information storage unit according to the embodiment; In the example shown in FIG. 7, the transaction object information storage unit 122 includes items such as "transaction object ID" and "transaction object".

"Transaction object ID" is an identifier for identifying a transaction object.

The “transaction object” is information related to the transaction object associated with the “transaction object ID”.

For example, in FIG. 7, "M1" identified by the trading object ID has trading object "MA1". In the example shown in FIG. 7, the transaction object is represented by an abstract code such as "MA1", but the transaction object may be in a file format or the like containing various information on the transaction object.

Note that the transaction object information storage unit 122 may store various types of information, not limited to the above, depending on the purpose. For example, the transaction target information storage unit 122 may store information indicating the category to which each transaction target corresponds. For example, the transaction target information storage unit 122 may describe information such as the score and display count corresponding to each transaction target.

(Content storage unit 123)
The content storage unit 123 stores information about content. 8 is a diagram illustrating an example of a content storage unit according to the embodiment; FIG. In the example shown in FIG. 8, the content storage unit 123 has items such as "content ID" and "content".

“Content ID” is an identifier for identifying content. "Content" is information about the content associated with the "content ID". Specifically, the content may indicate information about the contents of the content.

For example, the content is content related to a portal site. As another example, the content may be content related to a news site, an auction site, a weather forecast site, a shopping site, a finance (stock price) site, or the like.

Also, the content may be content related to a route search site, a map providing site, a travel site, a restaurant introducing site, a web blog site, an SNS (Social Networking Service) site, and the like.

For example, in FIG. 8, "C1" identified by the content ID has content "CO1". In the example shown in FIG. 8, the contents and the like are represented by abstract codes such as "CO1", but the contents and the like are represented by specific numerical values, specific character strings, and files containing various information. format or the like.

Note that the content storage unit 123 may store various types of information, not limited to the above, depending on the purpose.

(Reference information storage unit 124)
The criterion information storage unit 124 stores information regarding selection criteria. 9 is a diagram illustrating an example of a reference information storage unit according to the embodiment; FIG. The reference information storage unit 124 has items such as "reference ID", "target", "selection logic", and "contents".

“Criterion ID” indicates information for identifying a criterion. "Criteria" indicates what the criteria identified by "Criteria ID" are. "Selection Logic" indicates information identifying the selection logic corresponding to the criterion identified by "Criterion ID". "Contents" indicates the contents of what kind of processing the corresponding selection logic is.

FIG. 9 shows that the criterion (criteria CR11) identified by the criterion ID “CR11” is the criterion related to attention level. It indicates that the selection logic corresponding to reference CR11 is selection logic LG1. The selection logic LG1 indicates that the seed transaction object is selected from the ten transaction objects viewed by the user most recently.

FIG. 9 shows that the criterion (criterion CR12) identified by the criterion ID “CR12” is a criterion for recognition. It indicates that the selection logic corresponding to reference CR12 is selection logic LG2. The selection logic LG2 indicates that the seed transaction object is randomly selected from all the transaction objects browsed by the user.

It should be noted that the reference information storage unit 124 may store various types of information, not limited to the above, depending on the purpose.

(control unit 130)
The control unit 130 is a controller, and for example, various programs (information processing programs) stored in a storage device inside the information processing apparatus 100 are controlled by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. example) is implemented by executing the RAM as a work area. Also, the control unit 130 is a controller, and is implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 5, the control unit 130 includes an acquisition unit 131, a reception unit 132, a logic selection unit 133, a seed selection unit 134, a transaction target selection unit 135, and a provision unit 136. implements or performs the information processing functions and operations described in . Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 5, and may be another configuration as long as it performs information processing described later.

(Acquisition unit 131)
Acquisition unit 131 acquires various types of information. Acquisition unit 131 acquires various types of information from storage unit 120 . The acquisition unit 131 acquires various types of information from the user information storage unit 121, transaction target information storage unit 122, content storage unit 123, reference information storage unit 124, and the like.

Acquisition unit 131 receives various types of information from an external information processing device via communication unit 110 . The acquisition unit 131 receives various information from the terminal device 10 or the external device 20 . For example, the acquisition unit 131 acquires user information about the user from the external device 20 . In FIG. 1, the acquisition unit 131 obtains, as user information, user attribute information, purchase history on Internet shopping, electronic shopping malls, auction sites, flea market sites, etc., content display history, etc. from the external device 20. get. Then, the acquisition unit 131 stores this user information in the user information storage unit 121 . For example, the acquisition unit 131 acquires user information from the external device 20 and updates the user information stored in the user information storage unit 121 every predetermined period.

Also, the acquisition unit 131 acquires information about the transaction target from the external device 20 . For example, the acquisition unit 131 acquires from the external device 20 information about a transaction target traded at an auction site or a flea market site. To give a more specific example, the acquisition unit 131 acquires from the external device 20 information about sports goods that are being bid on on an auction site. Then, the acquisition unit 131 stores the information about the transaction object in the transaction object information storage unit 122 . For example, the acquisition unit 131 acquires information on the transaction object from the external device 20 and updates the information on the transaction object stored in the transaction object information storage unit 122 every predetermined period.

In addition, the acquisition unit 131 acquires from the terminal device 10 information indicating the number of times the trade object is displayed (the number of times the user browses). For example, the acquisition unit 131 acquires the display count of the content and the display count of each transaction target from the terminal device 10 . In addition, the acquisition unit 131 acquires control information for acquiring the number of times of display provided in advance together with the content. Then, the acquisition unit 131 stores the display count in the transaction object information storage unit 122 .

(Reception unit 132)
The reception unit 132 receives various requests. The reception unit 132 receives various requests from an external information processing device. The reception unit 132 receives information indicating various requests from an external information processing device via the communication unit 110 . For example, the receiving unit 132 receives requests from the terminal device 10 or the external device 20 . The reception unit 132 receives a content provision request from the terminal device 10 . For example, the reception unit 132 receives a request for provision of a portal site from the terminal device 10 as an example of content.

(Logic selection unit 133)
The logic selection unit 133 selects various information. The logic selection unit 133 executes logic selection processing for selecting information about logic. The logic selection unit 133 executes logic selection processing based on various information received from an external information processing device. The logic selection unit 133 executes logic selection processing based on various information received from the terminal device 10 or the external device 20 . The logic selection unit 133 executes logic selection processing based on various information stored in the storage unit 120 . For example, the logic selection unit 133 executes logic selection processing based on information acquired by the acquisition unit 131 .

The logic selection unit 133 selects a selection logic from among a plurality of selection logics for selecting a seed transaction object to be used for selecting a transaction object to be provided to the user.
The logic selection unit 133 selects a selection logic from among a plurality of selection logics for selecting a seed transaction object to be used as a seed for selecting a transaction object to be traded in the electronic commerce service.

The logic selection unit 133 selects a selection logic from among a plurality of selection logics for selecting a seed transaction target, each of which corresponds to at least one of a plurality of criteria.

The logic selection unit 133 selects a selection logic from among a plurality of selection logics including a first selection logic for randomly selecting a seed transaction target for the browsing transaction target. The logic selection unit 133 selects from among a plurality of selection logics including a second selection logic for selecting a seed transaction object a predetermined number of transaction objects most recently browsed by the user among the browsed transaction objects. to select.

The logic selection unit 133 selects a selection logic from among a plurality of selection logics by a method related to reinforcement learning or a multi-armed bandit method in which the state does not change in reinforcement learning.

(Seed selection unit 134)
The seed selection unit 134 selects various information. The seed selection unit 134 executes seed selection processing for selecting information about seeds. The seed selection unit 134 executes seed selection processing based on various information received from an external information processing device. The seed selection unit 134 executes seed selection processing based on various information received from the terminal device 10 or the external device 20 . The seed selection unit 134 executes seed selection processing based on various information stored in the storage unit 120 . For example, the seed selection unit 134 executes seed selection processing based on information acquired by the acquisition unit 131 . The seed selection unit 134 executes seed selection processing based on the logic selected by the logic selection unit 133 .

The seed selection unit 134 uses the selection logic selected by the logic selection unit 133 to select a seed transaction target from the viewed transaction targets that are the transaction targets viewed by the user indicated by the user's action history. The seed selection unit 134 uses the selection logic selected by the logic selection unit 133 to select from among the browsed transaction objects that are the transaction objects to be traded in the electronic commerce service browsed by the user indicated by the user's action history, Select a seed deal target.

The seed selection unit 134 selects a browsed transaction target, which is a transaction target viewed by the user indicated by the action history of the user, based on at least one of a plurality of criteria relating to selection of a transaction target provided to the user. Among them, a seed transaction object is selected as a seed used for selecting the transaction object to be provided to the user. The seed selection unit 134 selects a seed transaction object based on at least one of a plurality of criteria including a criterion relating to user attention to the transaction object. The seed selection unit 134 selects a seed transaction object based on at least one of a plurality of criteria including a criterion relating to diversity of transaction objects. The seed selection unit 134 selects a seed transaction object based on at least one of a plurality of criteria including a criterion relating to the user's recognition of the transaction object.

When the logic selection unit 133 selects the first selection logic, the seed selection unit 134 randomly selects a seed transaction object from the viewed transaction objects. When the second selection logic is selected by the logic selection unit, the seed selection unit 134 selects a seed transaction object from a predetermined number of transaction objects.

The seed selection unit 134 may estimate various types of information. The seed selection unit 134 may estimate the interest of the user and select a seed transaction target based on the estimation result. For example, the seed selection unit 134 may select, as a seed transaction target, a transaction target estimated to attract a high degree of user attention.

(Transaction target selection unit 135)
The transaction target selection unit 135 selects various information. The transaction object selection unit 135 executes a transaction object selection process for selecting information on the transaction object. The transaction target selection unit 135 executes transaction target selection processing based on various types of information received from an external information processing device. The transaction target selection unit 135 executes transaction target selection processing based on various information received from the terminal device 10 or the external device 20 . The transaction target selection unit 135 executes transaction target selection processing based on various information stored in the storage unit 120 . For example, the transaction target selection unit 135 executes the transaction target selection process based on the information acquired by the acquisition unit 131 . The transaction object selection unit 135 executes transaction object selection processing based on the seed transaction object selected by the seed selection unit 134 .

When the user displays predetermined content, the transaction target selection unit 135 selects the seed transaction target selected by the seed selection unit 134 from the transaction target group as the transaction target displayed in the predetermined content. to select. When the user displays predetermined content, the transaction target selection unit 135 selects the transaction target displayed in the predetermined content from among the transaction target group traded in the electronic commerce service by the seed selection unit 134. selected using the provided seed trading object.

The transaction object selection unit 135 selects a transaction object to be displayed in predetermined content from among the transaction object group based on co-occurrence with the seed transaction object. The transaction target selection unit 135 selects a transaction target displayed in predetermined content by collaborative filtering. In FIG. 2, the transaction target selection unit 135 selects transaction targets whose transaction target IDs are "M7", "M8", "M9", "M10", "M11", and "M1" as display transaction targets.

(Providing unit 136)
The providing unit 136 provides various information. The providing unit 136 transmits various types of information to an external information processing device via the communication unit 110 . The providing unit 136 transmits various information to the terminal device 10 or the external device 20 . The providing unit 136 transmits content to the terminal device 10 . The providing unit 136 transmits information about the transaction target to the terminal device 10 .

The provision unit 136 provides content including the transaction object selected by the transaction object selection unit 135 . The providing unit 136 provides content in which transaction objects are arranged in a predetermined display frame.

For example, the providing unit 136 refers to the content storage unit 123 and provides the terminal device 10 with content including a predetermined number of high-ranked trading objects among the trading objects ranked based on the scores. In FIG. 1, the provision unit 136 predetermines six display transaction objects "M15", "M34", "M7", "M162", "M41", and "M77" in descending order of score. The contents arranged in the display frame of and related to the portal site are transmitted to the terminal device 10 . For example, the providing unit 136 transmits the content C1 in FIG. 3 to the terminal device 10. FIG.

[4. Processing procedure]
Next, the procedure of information processing executed by the information processing apparatus 100 according to the embodiment will be described with reference to FIG. 10 . FIG. 10 is a flowchart showing an example of the flow of information processing executed by the information processing apparatus 100 according to the embodiment.

As shown in FIG. 10, the information processing device 100 has a plurality of selection logics for selecting seed transaction objects to be seeds used for selecting transaction objects to be provided to the user. A selection logic is selected from among a plurality of selection logics corresponding to at least one criterion (step S101).

The information processing apparatus 100 uses the selected selection logic to select a seed transaction object from among the browsed transaction objects, which are the transaction objects browsed by the user indicated by the user's action history (step S102). When the user displays predetermined content, the information processing apparatus 100 selects a transaction target displayed in the predetermined content from among the transaction target group using the selected seed transaction target (step S103). . The information processing device 100 provides content including the selected transaction object (step S104).

[5. Modification]
The information processing apparatus 100 described above may be embodied in various forms other than the above embodiment. Therefore, other embodiments of the information processing apparatus 100 will be described below.

[5-1. user〕
In the above embodiment, a user registered as a member of a predetermined service has been described as an example, but it is not necessary to be limited to the above example. For example, the user may be any user, for example, a user who is not registered as a member of a predetermined service.

[5-2. Transaction target]
In the above embodiment, an example of a transaction target traded on an auction site or a flea market site has been described, but it is not necessary to be limited to the above example. For example, the trading object may be any trading object. For example, the trading object may be a limited quantity trading object. Moreover, the transaction object may be a transaction object that, when purchased by the first user, cannot be purchased by a second user who is a different user than the first user. Also, the transaction object may be a transaction object that is traded through Internet shopping, an electronic shopping mall, or the like.

[5-3. Provide information on the transaction object]
In the above embodiment, an example of information processing in which the information processing device 100 provides content to the terminal device 10 has been described, but the above example may not be limiting. For example, an external server may provide content to the terminal device 10 . In this case, the information processing device 100 may provide the external server with information on the transaction target.

For example, the external server provides content regarding portal sites as an example of content. In this case, the information processing apparatus 100 may provide the external server with an image of the transaction object, information on the layout when arranged in the content, etc., as the information on the transaction object.

[5-4. program〕
Also, the information processing apparatus 100 according to the above-described embodiment is implemented by, for example, a computer 1000 configured as shown in FIG. FIG. 12 is a diagram illustrating an example of a hardware configuration; A computer 1000 is connected to an output device 1010 and an input device 1020, and an arithmetic device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected via a bus 1090. have

The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device such as a RAM that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used for various calculations by the arithmetic device 1030 and various databases are registered. It is realized by

The output IF 1060 is an interface for transmitting information to be output to the output device 1010 that outputs various types of information such as a monitor and a printer. It is realized by a connector conforming to a standard such as HDMI (registered trademark) (High Definition Multimedia Interface). Also, the input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, keyboard, scanner, etc., and is realized by, for example, USB.

Note that the input device 1020 includes, for example, optical recording media such as CDs (Compact Discs), DVDs (Digital Versatile Discs), PDs (Phase change rewritable discs), magneto-optical recording media such as MOs (Magneto-Optical discs), and tapes. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. Also, the input device 1020 may be an external storage medium such as a USB memory.

Network IF 1080 receives data from other devices via network N and sends the data to arithmetic device 1030, and also transmits data generated by arithmetic device 1030 via network N to other devices.

The arithmetic device 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070 . For example, arithmetic device 1030 loads a program from input device 1020 or secondary storage device 1050 onto primary storage device 1040 and executes the loaded program.

For example, when the computer 1000 functions as the information processing device 100 , the arithmetic device 1030 of the computer 1000 implements the functions of the control unit 130 by executing a program loaded on the primary storage device 1040 .

[5-5. others〕
Further, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or described as being performed manually. All or part of the processing can also be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

Also, the above-described embodiments and modifications can be appropriately combined within a range that does not contradict the processing content.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

[6. effect〕
As described above, the information processing apparatus 100 according to the embodiment has the logic selection section 133 and the seed selection section 134 . The logic selection unit 133 selects a selection logic from among a plurality of selection logics for selecting a seed transaction object to be used for selecting a transaction object to be provided to the user. The seed selection unit 134 uses the selection logic selected by the logic selection unit 133 to select a seed transaction target from the viewed transaction targets that are the transaction targets viewed by the user indicated by the user's action history.

In this way, the information processing apparatus 100 according to the embodiment uses a selection logic selected from a plurality of selection logics for selecting a seed transaction object to be used for selecting a transaction object to be provided to the user. By selecting the seed transaction target from among the viewed transaction targets, which are the transaction targets viewed by the user indicated by the user's action history, it is possible to appropriately select the information on the transaction target to be provided to the user. can be done.

The information processing apparatus 100 according to the embodiment also has a transaction target selection unit 135 . When the user displays predetermined content, the transaction target selection unit 135 selects the seed transaction target selected by the seed selection unit 134 from the transaction target group as the transaction target displayed in the predetermined content. to select.

As described above, when the user displays predetermined content, the information processing apparatus 100 according to the embodiment uses the seed transaction object selected from the transaction object group as the transaction object displayed in the predetermined content. By making selections with , it is possible to appropriately select the information on the transaction object to be provided to the user.

Further, in the information processing apparatus 100 according to the embodiment, the transaction object selection unit 135 selects a transaction object displayed in predetermined content from among the transaction object group based on co-occurrence with the seed transaction object.

As described above, the information processing apparatus 100 according to the embodiment selects a transaction target displayed in predetermined content based on the co-occurrence with the seed transaction target, thereby providing the user with a transaction target. Select information appropriately.

Further, in the information processing apparatus 100 according to the embodiment, the transaction target selection unit 135 selects a transaction target displayed in predetermined content by collaborative filtering.

As described above, the information processing apparatus 100 according to the embodiment can appropriately select the information on the transaction target to be provided to the user by selecting the transaction target displayed in the predetermined content by collaborative filtering. can.

Further, the information processing apparatus 100 according to the embodiment further includes a provision unit 136 that provides content including the transaction object selected by the transaction object selection unit 135 .

In this way, the information processing apparatus 100 according to the embodiment can provide content including transaction objects that are highly appealing to the user by providing content including the selected transaction objects.

In addition, in the information processing apparatus 100 according to the embodiment, the providing unit 136 provides content in which transaction objects are arranged in a predetermined display frame.

As described above, the information processing apparatus 100 according to the embodiment provides content in which transaction objects are arranged in a predetermined display frame, thereby arranging transaction objects that are highly appealing to the user in the predetermined display frame. It is possible to provide content that has been

In addition, in the information processing apparatus 100 according to the embodiment, the logic selection unit 133 selects a selection logic from among a plurality of selection logics including a first selection logic for randomly selecting a seed transaction target for browsing transaction targets. select.

In this way, the information processing apparatus 100 according to the embodiment uses the selection logic selected from a plurality of selection logics including the first selection logic for randomly selecting the seed transaction target for the browsing transaction target, and performs the seed transaction. By selecting the target, it is possible to appropriately select information on the transaction target to be provided to the user.

Further, in the information processing apparatus 100 according to the embodiment, when the logic selection unit 133 selects the first selection logic, the seed selection unit 134 randomly selects the seed transaction object from the browsing transaction objects.

As described above, when the first selection logic is selected, the information processing apparatus 100 according to the embodiment randomly selects the seed transaction target from the viewing transaction target, thereby providing the transaction to the user. The information of interest can be appropriately selectable.

Further, in the information processing apparatus 100 according to the embodiment, the logic selection unit 133 selects a seed transaction object from a predetermined number of transaction objects viewed most recently by the user, among the browsed transaction objects. selects a selection logic from among a plurality of selection logics including

As described above, the information processing apparatus 100 according to the embodiment selects from a plurality of selection logics including the second selection logic for selecting the seed transaction target for a predetermined number of transaction targets that the user has browsed most recently. Logic can be used to select the seed transaction object, thereby making it possible to appropriately select the information of the transaction object to be provided to the user.

Further, in the information processing apparatus 100 according to the embodiment, when the second selection logic is selected by the logic selection unit, the seed selection unit 134 selects a seed transaction object from a predetermined number of transaction objects.

As described above, when the second selection logic is selected, the information processing apparatus 100 according to the embodiment selects a seed transaction object from among a predetermined number of transaction objects, thereby providing a transaction object to the user. information can be made appropriately selectable.

Also, in the information processing apparatus 100 according to the embodiment, the logic selection unit 133 selects a selection logic from among a plurality of selection logics by a technique related to reinforcement learning.

As described above, the information processing apparatus 100 according to the embodiment appropriately selects the information of the transaction target to be provided to the user by selecting a selection logic from among a plurality of selection logics by a technique related to reinforcement learning. can be made possible.

In addition, in the information processing apparatus 100 according to the embodiment, the logic selection unit 133 selects a selection logic from among a plurality of selection logics by a method regarding a multi-armed bandit.

In this way, the information processing apparatus 100 according to the embodiment selects a selection logic from among a plurality of selection logics according to a technique related to a multi-armed bandit, thereby appropriately providing information on a transaction target to the user. can be made selectable.

Further, in the information processing apparatus 100 according to the embodiment, the transaction target is a transaction target that is traded through an electronic commerce service.

In this way, the information processing apparatus 100 according to the embodiment can provide content including various transaction objects that are highly appealing to users for transaction objects that are traded in electronic commerce services.

As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to carry out the invention in other forms with modifications.

N network 1 information processing system 10 terminal device 20 external device 100 information processing device 110 communication unit 120 storage unit 121 user information storage unit 122 transaction target information storage unit 123 content storage unit 124 reference information storage unit 130 control unit 131 acquisition unit 132 Reception unit 133 logic selection unit 134 seed selection unit 135 transaction target selection unit 136 provision unit

Claims (15)

a logic selection unit that selects a selection logic from among a plurality of selection logics for selecting a seed transaction object to be used for selecting a transaction object to be provided to the user;
a seed selection unit that selects the seed transaction object from viewed transaction objects that are transaction objects viewed by the user indicated by the action history of the user, using the selection logic selected by the logic selection unit; ,
An information processing device comprising: A transaction in which, when the user displays predetermined content, a transaction target displayed in the predetermined content is selected from a group of transaction targets using the seed transaction target selected by the seed selection unit. a target selection unit,
The information processing apparatus according to claim 1, further comprising: The transaction target selection unit
3. The information processing apparatus according to claim 2, wherein a transaction object displayed in said predetermined content is selected from said transaction object group based on co-occurrence with said seed transaction object. The transaction target selection unit
4. The information processing apparatus according to claim 3, wherein a transaction target displayed in said predetermined content is selected by collaborative filtering. The information processing apparatus according to any one of claims 2 to 4, further comprising a providing unit that provides content including the transaction object selected by the transaction object selection unit. The providing unit
6. The information processing apparatus according to claim 5, wherein content is provided in which the trading object is arranged in a predetermined display frame. The logic selection unit
7. The selection logic is selected from among the plurality of selection logics including a first selection logic for randomly selecting the seed transaction object from the browsing transaction object. 1. The information processing device according to 1. The seed selection unit
8. The information processing apparatus according to claim 7, wherein when the first selection logic is selected by the logic selection unit, the seed transaction object is randomly selected from the browsing transaction object. The logic selection unit
Selecting a selection logic from among the plurality of selection logics including a second selection logic for selecting the seed transaction object from among the viewed transaction objects, targeting a predetermined number of transaction objects viewed most recently by the user The information processing apparatus according to any one of claims 1 to 8, characterized in that: The seed selection unit
10. The information processing apparatus according to claim 9, wherein when the second selection logic is selected by the logic selection unit, the seed transaction object is selected from the predetermined number of transaction objects. The logic selection unit
The information processing apparatus according to any one of claims 1 to 10, wherein a selection logic is selected from the plurality of selection logics by a technique related to reinforcement learning. The logic selection unit
12. The information processing apparatus according to any one of claims 1 to 11, wherein a selection logic is selected from the plurality of selection logics by a technique related to multi-armed bandit reinforcement learning. The transaction object is
The information processing apparatus according to any one of claims 1 to 12, wherein the information processing apparatus is a transaction object to be traded in an electronic commerce service. A computer-executed information processing method comprising:
a logic selection step of selecting a selection logic from among a plurality of selection logics for selecting a seed transaction object to be used for selecting a transaction object to be provided to the user;
a seed selection step of selecting the seed transaction object from viewed transaction objects, which are transaction objects viewed by the user indicated by the action history of the user, using the selection logic selected by the logic selection step; ,
An information processing method comprising: a logic selection procedure for selecting a selection logic from among a plurality of selection logics for selecting a seed transaction target used to select a transaction target to be provided to the user;
a seed selection procedure for selecting the seed transaction object from viewed transaction objects, which are transaction objects viewed by the user indicated by the action history of the user, using the selection logic selected by the logic selection procedure; ,
An information processing program characterized by causing a computer to execute

Images