JP7713873B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

This application relates to an information processing device, an information processing method, and an information processing program.

Conventionally, when advertising is distributed via the Internet, the users to whom the advertisements are to be distributed are narrowed down, or in other words, targeted. Not only in advertising distribution, but also in information distribution via the Internet, such as the provision of various contents and information recommendations, the users to whom the information is to be distributed are narrowed down based on the attributes and behavioral history of the users that are registered in advance.

JP 2015-230717 A

However, conventional technology has room for improvement in terms of increasing the likelihood that a variety of information will be provided in information distribution. For example, it is difficult to pinpoint information about a product that is low in stock and provide that product to a user who has a strong desire to purchase that product. Furthermore, content delivered to a user who searches for a specific product may be biased toward best-selling products, and other products that are relevant to the recipient user may get lost in the mix.

The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can increase the likelihood that a variety of information will be provided in information distribution.

The information processing device according to the present application is provided with a list that identifies the content for which the user performed a predetermined action among the content provided in an order based on first score information that evaluates the target corresponding to the user and second score information for each target that evaluates in advance the relevance of each of a plurality of users who may be the recipients of content that lists information about the target, and includes an update unit that updates a synthesis ratio between the first score information and the second score information that determines the order in which the content is provided based on a comparison result between the user list that individually indicates the users identified from a plurality of users who may be the recipients of the content based on the second score information and the corresponding user who performed the predetermined action, and the list that is linked to the target corresponding to the identified content.

According to one aspect of the embodiment, it is possible to increase the likelihood that a variety of information will be provided in information distribution.

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 for explaining an example of a method for generating a user list according to the embodiment. FIG. 3 is a diagram for explaining a specific example of reranking search results according to the embodiment. FIG. 4 is a diagram illustrating an example of the configuration of an information processing device according to an embodiment. FIG. 5 is a diagram illustrating an example of product information according to the embodiment. FIG. 6 is a diagram illustrating an example of user information according to the embodiment. FIG. 7 is a diagram illustrating an example of information of a user list according to the embodiment. FIG. 8 is a diagram illustrating an example of weight information according to the embodiment. FIG. 9 is a flowchart illustrating an example of a procedure of a content providing process according to the embodiment. FIG. 10 is a flowchart illustrating an example of a procedure for updating weights of a user list according to the embodiment. FIG. 11 is a diagram showing an example of a user list according to a modified example. FIG. 12 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment.

Below, the information processing device, information processing method, and information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, information processing method, and information processing program according to the present application are not limited to the embodiments described below. Furthermore, the embodiments described below can be appropriately combined as long as they do not cause inconsistencies in the processing content. Furthermore, the same parts in the embodiments described below will be given the same reference numerals, and duplicated descriptions will be omitted.

(Embodiment)
[1. An example of information processing]
(1-1. Overview of Information Processing)
An example of information processing executed by the information processing device 100 will be described with reference to FIG. 1. FIG. 1 is a diagram showing an example of information processing executed by the information processing device according to the embodiment. The information processing device 100 executes information processing related to the distribution of content. The content includes various types of content, such as advertising content distributed in association with the use of various services, web content corresponding to a search query entered into a search engine, and content related to a trading object entered into a search bar provided on a site of an electronic commerce (EC) service. Here, the trading object is the use of a product or service. Note that the trading object traded in the electronic commerce service includes trading objects traded in various forms such as an electronic shopping mall (online mall), an online shopping site, an auction site, and a flea market site. Note that FIG. 1 shows an example of information processing for a product (an example of an "object") traded in an electronic shopping mall.

The information processing device 100 shown in FIG. 1 provides information to a user using a search query (hereinafter referred to as "query") input by a user U using the terminal device 10. Specifically, the information processing device 100 searches for content corresponding to the search query, narrows down the searched content, reranks the narrowed down content, and provides the user with a predetermined number of contents in descending order of rank. Information processing related to content distribution executed by the information processing device 100 that provides such information will be described below. Note that in the following description, the terminal device 10 may be referred to as the user U. In other words, the user U can be read as the terminal device 10.

In the example shown in FIG. 1, the information processing system SYS has multiple terminal devices 10 and an information processing device 100. The terminal devices 10 and the information processing device 100 are connected to a network N (for example, see FIG. 4) by wire or wirelessly. The terminal devices 10 and the information processing device 100 can communicate with each other via the network N. Note that the example shown in FIG. 1 is not particularly limited, and the information processing system SYS may include more terminal devices 10 and information processing devices 100 than those shown in FIG. 1.

The terminal device 10 shown in FIG. 1 is an information processing terminal used by each user U who is a user of various services provided by the information processing device 100. Each user U uses at least one terminal device 10. A typical example of the terminal device 10 is a smartphone, but it may also be realized by a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), etc.

The terminal device 10 also has a communication unit for connecting to the network N via a wireless communication network such as LTE (Long Term Evolution), 4G (4th Generation), or 5G (5th Generation: 5th generation mobile communication system), or a short-range wireless communication such as Bluetooth (registered trademark) or a wireless LAN (Local Area Network). A user U operates the terminal device 10 having the communication unit to access the information processing device 100 and use various services provided by the information processing device 100.

The terminal device 10 can also display information for utilizing various services provided by the information processing device 100 using a web browser or an application. At this time, when the terminal device 10 receives control information for realizing the display processing of information using a web browser, an application, or the like from the information processing device 100, the terminal device 10 realizes the display processing according to the received control information.

As an example, the information processing device 100 shown in FIG. 1 will be described as functioning as a search device that provides search results to the terminal device 10 used by the user U who inputted a query. For example, the information processing device 100 has a function as a search engine that executes search processing on products traded in an online shopping mall. The information processing device 100 also has a database in which information on products that are the subject of search processing using a query is indexed and stored, and executes search processing on the information in the database. For example, the information in this database is stored in the memory unit 120 (for example, see FIG. 4).

Product information may include various information. For example, product information may include various information used to provide information about the product, such as the seller, sales price, product image, category, title, description, payment method, sales period, and number of units sold. Product information may also include the sales history of the product, such as the number of reservations, orders, sales, and order amount (sales). For example, product information may include information such as the period that has passed since the date and time the product was sold, the number of views of information indicating the product, the number of reviews for the product, and the evaluation of the transaction subject. Product information may also include information on external factors related to the product, such as information posted on a social networking service (SNS).

In the information processing system SYS shown in FIG. 1, the information processing device 100 is not limited to functioning as a search device, and the information processing system SYS shown in FIG. 1 may have any configuration as long as it is possible to realize the information processing according to the embodiment. For example, the information processing system SYS may be configured to include a search device that is physically distributed from the information processing device 100.

First, the information processing device 100 generates a user list (step S1). A user list is a list linked to products published in the content. For each product (an example of a "target") published in the content, the information processing device 100 individually displays users U identified from among the multiple users U based on a score that is a pre-evaluation of the relevance of each of the multiple users U to the product, who may be the recipient of the content. The information processing device 100 generates a user list that displays, as candidate users, a predetermined number of users U identified from among the multiple users U in descending order of score. The user list can show the ranking of users U with a stronger degree of relevance in terms of the product published in the content.

The terminal device 10 also transmits the search query input by the user U to the information processing device 100 (step S2). In response, the information processing device 100 executes a search process for a product (content) corresponding to the search query based on the search query specified by the user U (step S3). For example, the information processing device 100 acquires content in which the product corresponding to the search query is posted from a database. Acquisition of information corresponding to the query is performed using existing technology, and any process may be used as long as it is possible to identify the product, and detailed explanation will be omitted.

Next, the information processing device 100 generates search results using the content acquired by the search process (step S4). For example, the information processing device 100 narrows down the products listed in each piece of content acquired by the search process based on the user information of the user U who is the sender of the search query, and generates a ranking for each product by ranking each of the narrowed down products.

Specifically, the information processing device 100 calculates a product score (an example of "first score information") evaluating the products posted in each content based on the user information, and narrows down the products based on the calculated product score. For example, the information processing device 100 narrows down the products to those with scores equal to or greater than a predetermined value. The information processing device 100 also ranks the narrowed down products based on the scores corresponding to the products. For example, the information processing device 100 assigns higher ranks to products with higher scores. Then, the information processing device 100 generates search results in which the contents posting the products with higher ranks are listed in order.

A specific method for calculating the product score will be described. For example, the information processing device 100 calculates the product score using a value (hereinafter referred to as a "partial score") obtained by multiplying each of a number of elements, such as the number of orders for the product, the order amount, and the number of views, by the weight (coefficient) of each element. For example, the information processing device 100 may calculate the sum of the partial scores of the multiple elements for the product as the product score, or may calculate the average of the partial scores of the multiple elements for the product as the product score.

The information processing device 100 may also calculate the product score using an aggregate value calculated for each of a plurality of elements, such as the number of orders for the product, the order amount, and the number of views, for each predetermined period. In this case, the information processing device 100 may calculate the product score using a value obtained by multiplying the aggregate value of the plurality of elements of the product calculated for each predetermined period by the weight (coefficient) of each element (hereinafter referred to as the "period score"). The information processing device 100 may also calculate the product score using a value obtained by multiplying the period score for each period by a decay coefficient according to the difference between the period and the calculation time point. In this case, the information processing device 100 may calculate the score of the transaction object using a value obtained by multiplying the period score for each period by a decay coefficient whose value becomes smaller the earlier the period. The information processing device 100 may also calculate the product score using an aggregate value calculated for each date for each of a plurality of elements of the product.

In addition, the information processing device 100 may use, as the product score, the inner product value of the vector of the product, an estimated CTR (Click Through Rate) for the product, or a score output by a model based on machine learning.

Note that the above-mentioned score calculation method is an example, and the information processing device 100 may calculate the product score using any method. For example, the information processing device 100 may correct the calculated product score by using a coefficient based on the evaluation of the seller (store) selling the product. For example, the information processing device 100 can correct the product score by multiplying the calculated product score by a coefficient based on the evaluation of the seller selling the product.

After generating the search results, the information processing device 100 reranks (modifies) the search results using the user list (step S5). For example, the information processing device 100 reranks the search results based on a product score (an example of "first score information") that evaluates a product based on user information on the user U, and a user score (an example of "second score information") corresponding to the user U in the user list related to the product. Specifically, the information processing device 100 ranks the products based on a sum of the product score and the user score related to the product (hereinafter referred to as a "summed score"). Specifically, the information processing device 100 calculates the summed score based on the following formula (1). Note that "n" in the following formula (1) is a predetermined weight for determining the usage mode of the user score based on the user list. Also, the following formula (1) is an example, and an arbitrary function that inputs the product score and the user score may be learned from the distribution record of the content that lists the target corresponding to the user, such as a product.
Combined score = n × product score + (1-n) × user score (1)

For example, the information processing device 100 selects either the product score or the user score based on the result of comparing the product score with the user score for this product, and ranks the products based on the selected score. Specifically, the information processing device 100 selects the larger of the product score and the user score for this product, and ranks the products based on the selected score. Alternatively, the information processing device 100 may select the smaller of the product score and the user score for this product, and rank the products based on the selected score.

In addition, when the information processing device 100 receives a search query from a new user, the information processing device 100 may rerank the search results using a product score that evaluates a product based on information of a similar user similar to the new user, and user score information related to this product.In addition, when a new product is searched for, the information processing device 100 may rerank the search results using product scores corresponding to other products similar to the new product, and user scores related to the other products.In this way, the information processing device 100 can deal with the cold start problem.

Then, the information processing device 100 determines the products to be provided to the user U based on the reranked search results (step S6). For example, the information processing device 100 determines a predetermined number of the reranked products in descending order of rank as the listed products. Then, the information processing device 100 provides the user U with content related to the determined listed products (step S7).

In addition, the information processing device 100 identifies converted products that have undergone a predetermined conversion from among the products listed in the content provided to the user U as the search results (step S8). Examples of predetermined conversions include purchasing a product, adding a product to a shopping cart, posting on a social networking site, and viewing a page that lists detailed information about the product.

Then, the information processing device 100 updates the usage mode of the user list depending on whether or not the user list linked to the product listed in the identified content includes a user U who has performed a predetermined conversion (step S9).

For example, when a user U who has performed a predetermined conversion is included in a user list linked to a product published in the content in which the predetermined conversion has been performed, the information processing device 100 increases the weight of the user score corresponding to the user U (weight using the user list). This enables the information processing device 100 to provide product information that better reflects the degree of relevance of the user U from the perspective of the product.

In addition, for example, if a user U who has performed a predetermined conversion is not included in a user list linked to a product published in the content in which the predetermined conversion has been performed, the information processing device 100 reduces the weight of the user score corresponding to the user U (weight using the user list). This allows the information processing device 100 to provide product information that better reflects the evaluation of the product.

In addition, when updating a user list linked to a product published in content in which user U has performed a predetermined conversion, information processing device 100 may increase the score corresponding to user U who has performed the predetermined conversion and the score corresponding to similar users who are similar to user U. This allows information processing device 100 to update the user list by reflecting the results of the predetermined conversion.

(1-2. About the user list)
Hereinafter, the generation of a user list by the information processing device 100 will be described with reference to FIG. 2. FIG. 2 is a diagram for explaining an example of a method for generating a user list according to an embodiment. FIG. 2 illustrates an example of a user list showing, for each product, a user U who is ranked first among the users U in terms of products published in the content. Note that FIG. 2 illustrates a user list (Top-K (K=1)) showing, for each product, a user U who is ranked first in terms of products published in the content, but a user list showing a user U identified up to a predetermined rank, such as a user list (Top-K (K=2)) showing, for each product, a user U who is ranked up to the second highest in terms of products, can be generated arbitrarily. Also, "Product X1", "Product X2", and "Product X3" shown in FIG. 2 indicate contents in which products are published.

For example, the information processing device 100 calculates a score (an example of "second score information") that evaluates the relevance of each of the multiple users U who can be the recipients of the content for each product posted in the content. Then, the information processing device 100 generates a Top-K (K = 1) user list by identifying the user U with the highest calculated score for each content. For example, the information processing device 100 generates a user list that individually indicates candidate users who will be the recipients of the content for each product. This allows the information processing device 100 to individually identify the user who has the highest degree of relevance from the perspective of the product. Alternatively, the information processing device 100 generates list information that indicates the attributes of candidate users who will be the recipients of the content for each product. This allows the information processing device 100 to identify the attributes of the user who has the highest degree of relevance from the perspective of the product. In addition, when generating a user list, the information processing device 100 may weight the scores for a first user who has performed a predetermined conversion for the product or a second user similar to the first user, and include a predetermined number of users in the user list in order of the highest score. This allows you to generate user lists that reflect the results of specific conversions.

In FIG. 2, when viewing each user U from the perspective of "Product X1", user U3 is ranked first, when viewing each user U from the perspective of "Product X2", user U1 is ranked first, and when viewing each user U from the perspective of "Product X3", user U2 is ranked first. FIG. 2 also shows user list L2-1 and user list L2-2 generated by information processing device 100.

User list L2-1 shown in FIG. 2 is an example of a user list that individually indicates candidate users to whom content is to be provided for each product. For example, as shown in FIG. 2, user list L2-1 has a "product ID" item and a "related user ranking" item, and these items correspond to each other. The "product ID" item stores a product ID that is identification information for identifying a product. The "related user ranking" item stores a user ID that is identification information for identifying user U ranked first in terms of a product, and a score that indicates the user's relevance to the product. According to user list L2-1 shown in FIG. 2, user U ranked first (highest relevance, most matching) in terms of "product X1", "product X2", and "product X3" can be individually identified.

User list L2-2 shown in FIG. 2 is an example of a user list showing attributes of candidate users to whom content is to be provided for each product. For example, as shown in FIG. 2, user list L2-2 has a "product ID" item and a "related user attribute ranking" item, and these items correspond to each other. The "product ID" item stores the above-mentioned product ID. The "related user ranking" item stores attribute information showing the attributes of the user ranked first in terms of the above-mentioned product, and the above-mentioned score. According to user list L2-2 shown in FIG. 2, it is possible to identify the attributes of user U ranked first (most related and most matching) in terms of "product X1", "product X2", and "product X3".

In addition, the information processing device 100 may weight the scores of users who have performed a specified conversion for a product, or users similar to these users, and include a specified number of users in the user list in descending order of score. This allows the information processing device 100 to reflect the results of the specified conversion in the user list.

In addition, when ranking the products listed in the content provided to user U, information processing device 100 uses user lists L2-1 and L2-2 shown in FIG. 2. For example, information processing device 100 can rank the products taking into account user scores defined in user lists L2-1 and L2-2, as described below.

The information processing device 100 can also provide information based on a user list. For example, the information processing device 100 identifies candidate users to whom content is to be provided for each product based on the user list. The information processing device 100 then provides content listing the corresponding product to the candidate users. This allows the information processing device 100 to provide information to users who are highly related to the product.

(1-3. Specific examples of reranking search results)
A specific example of reranking search results by the information processing device 100 will be described below. Fig. 3 is a diagram for explaining a specific example of reranking search results according to an embodiment. Fig. 3 illustrates a case where the user U of the terminal device 10 is user U1. Fig. 3 also illustrates a specific example of reranking search results performed by the information processing device 100 according to an embodiment, but for convenience of explanation, the information processing device 100 is omitted from the illustration.

The information processing device 100 searches for content that lists the product corresponding to the user U1 (step S11). In FIG. 3, the content searched for by the information processing device 100 includes content C1 that lists product Y1, content C2 that lists product Y2, and content C3 that lists product Y3.

Next, the information processing device 100 calculates the scores of the products listed in the searched content (step S12). In FIG. 3, a score α1 is shown as the score of the product Y1 listed in content C1, a score α2 is shown as the score of the product Y2 listed in content C2, and a score α3 is shown as the score of the product Y3 listed in content C3.

Next, the information processing device 100 narrows down the products listed in the searched content based on the product scores, ranks the products listed in the narrowed down content, and generates search results (step S13). In FIG. 3, search result L3-1 is shown, which includes product Y1 ranked first, product Y2 ranked second, and product Y3 ranked third.

In addition, in the background of the product scoring, the information processing device 100 calculates the score of user U1 in terms of the products listed in the searched content (step S14). Figure 3 shows the score β1 of user U1 in terms of product Y1 listed in content C1, the score β2 of user U1 in terms of product Y2 listed in content C2, and the score β3 of user U1 in terms of product Y3 listed in content C3.

Then, the information processing device 100 re-ranks (re-ranks) the products included in the search results based on the sum of the product scores calculated in step S12 and the score of user U1 calculated in step S14, thereby correcting the search results based on the product scores (step S15). In the search result L3-2 shown in FIG. 3, the product rankings have been changed due to the correction of the search result L3-1. According to the search result L3-2 shown in FIG. 3, the first-place product has been replaced by product Y2, the second-place product Y2 has been replaced by product Y3, and the third-place product Y3 has been replaced by product Y1.

In this way, the information processing device 100 uses the score of the user U1 from the perspective of the product to correct (rerank) the search results corresponding to the user U1, thereby increasing the possibility that various information will be provided. For example, by scoring the user U who can be the distribution destination of the content from the perspective of the product in advance, it is possible to increase the possibility that information about a product with a low inventory, such as an auction item, is provided to the user U who strongly desires to purchase such a product in a pinpoint manner. Similarly, it is possible to increase the possibility that information such as a job position with limited employment opportunities is provided to a user U who has the conditions and aptitude for the job position in a pinpoint manner. In addition, it is possible to increase the possibility that not only content containing popular products but also content containing other products that match the distribution destination user is provided to a user who searches for a specific product. In addition, even for information with unlimited resources such as news content, it is possible to increase the possibility that news that matches only a specific user is provided to the specific user.

2. Configuration of information processing device
The information processing device 100 according to the embodiment will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the configuration of the information processing device according to the embodiment. As shown in Fig. 4, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130.

(Regarding communication unit 110)
The communication unit 110 is realized by, for example, a network interface card (NIC) or the like. The communication unit 110 is connected to a network N by wire or wirelessly. The information processing device 100 transmits and receives information to and from the terminal device 10 via the network N.

(Regarding the storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. For example, the storage unit 120 has a product information storage unit 121, a user information storage unit 122, a user list storage unit 123, and a weight information storage unit 124.

(Product information storage unit 121)
The product information storage unit 121 stores information about products traded in the online shopping mall. Fig. 5 is a diagram showing an example of the product information according to the embodiment. Note that Fig. 5 shows an example of the product information according to the embodiment, and the product information may include information other than that shown in Fig. 5.

As shown in FIG. 5, the product information stored in the product information storage unit 121 has a "product ID" field and a "product information" field. These fields in the product information correspond to each other. Note that in FIG. 5, the information stored in the "product information" field has been simplified and expressed as an abstract concept.

The "Product ID" field stores identification information for identifying products traded in the online shopping mall. The "Product Information" field stores various information related to the product. For example, the information stored in the "Product Information" field may include various information used to provide information about the product, such as the product's seller, sales price, product image, category, title, description, payment method, sales period, and number of units sold. The information stored in the "Product Information" field may also include the product's sales history, such as the number of reservations, number of orders, number of sales, and order amount (sales). For example, the product-related information may include information such as the period that has passed since the date and time the product was sold, the number of views of information indicating the product, the number of reviews for the product, and the evaluation of the product. The product-related information may also include information on external factors related to the product, such as information posted on a social networking service (SNS).

Figure 5 shows that the product information for the product identified by the product ID: "Product #1" is "Product Information #1."

(User information storage unit 122)
The user information storage unit 122 stores user information about a user U who uses the online shopping mall. Fig. 6 is a diagram showing an example of the user information according to the embodiment. Note that Fig. 6 shows an example of the user information according to the embodiment, and may include information other than that shown in Fig. 6.

As shown in FIG. 6, the user information stored in the user information storage unit 122 has multiple items such as a "user ID", a "personal information", a "search history", a "purchase history", and a "posting history". These items of user information are mutually associated. Note that in FIG. 6, the information stored in the "personal information", "search history", "purchase history", "posting history", and other items is simplified and expressed as an abstract concept.

The "User ID" item stores identification information for identifying user U. The "Personal Information" item stores personal information belonging to user U. Personal information may include information such as name, gender, age, family composition, living arrangement, annual income, interests, and preferences.

The "search history" field stores the history of search queries entered by user U. The "purchase history" field stores purchase history, which is the history of purchases made by user U. The "post history" field stores post history, which is the history of posts made by user U.

According to FIG. 6, user U, identified by user ID: "U#1", is specified by "personal information": "personal information #1", performs a search using a search query stored in search history: "search history #1", makes purchases as indicated in purchase history: "purchase history #1", and makes posts as indicated in post history: "post history #1".

(User list storage unit 123)
The user list storage unit 123 stores information of a user list. Fig. 7 is a diagram showing an example of information of a user list according to an embodiment. Note that Fig. 7 shows an example of information of a user list according to an embodiment, and information other than that shown in Fig. 7 may be included.

As shown in FIG. 7, the user list information stored in the user list storage unit 123 has a "product ID" field and a "related user ranking" field. These fields in the user list information are associated with each other.

The "Product ID" field stores identification information for identifying products traded in the online shopping mall. The identification information stored in the "Product ID" field may be the same as the identification information stored in the "Product ID" field of the above-mentioned product information.

The "Related User Ranking" item has multiple items for storing information on user IDs and scores for each user's ranking in terms of products. Figure 7 shows an item for storing the first place user ID and score, an item for storing the second place user ID and score, and an item for storing the third place user ID and score.

According to FIG. 7, from the perspective of the product identified by the product ID: "product #1", the user U identified by the user ID: "U#3" is ranked first, and the score indicating the relevance of the user U identified by "U#3" is "score SC-1". Also, from the perspective of the product identified by the product ID: "product #1", the user U identified by the user ID: "U#4" and the user U identified by the user ID: "U#11" are tied for second place, and the score indicating the relevance of each of the users U identified by "U#4" and "U#11" is "score SC-2". Also, from the perspective of the product identified by the product ID: "product #1", the user U identified by the user ID: "U#5" is ranked third, and the score indicating the relevance of the user U identified by "U#5" is "score SC-3".

(Weight information storage unit 124)
The weight information storage unit 124 stores weight information for determining the usage mode of the user list. Fig. 8 is a diagram showing an example of the weight information according to the embodiment. Note that Fig. 8 shows an example of the weight information according to the embodiment, and may include information other than that shown in Fig. 8.

As shown in FIG. 8, the weight information stored in the weight information storage unit 124 has the items "user ID", "weight of product score", and "weight of user score (product → user)". These items in the weight information are mutually associated.

The "User ID" field stores identification information for identifying user U. The identification information stored in the "User ID" field is the same as the identification information stored in the "User ID" field of the user information described above.

The "Product Score Weight" field stores information on the weight by which the product score is multiplied when correcting product search results. The weight information stored in the "Product Score Weight" field corresponds to the value of "n" in formula (1) above. The "User Score Weight" field stores information on the weight by which the user score (score defined in the user list) from the product's perspective is multiplied when correcting product search results. The weight information stored in the "User Score Weight" field corresponds to the value of "1-n" in formula (1) above.

Figure 8 shows that when revising search results for products corresponding to user U identified by user ID: "U#1", the weight multiplied by the product score is "0.8", and the weight of the score multiplied by the user score from the product's perspective is "0.2".

(Regarding the control unit 130)
The control unit 130 is realized by a central processing unit (CPU) or a micro processing unit (MPU) executing various programs stored in a storage device inside the information processing device 100 using a RAM as a working area. The control unit 130 is also realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

The control unit 130 shown in FIG. 4 has a search unit 131, a generation unit 132, an identification unit 133, a determination unit 134, a provision unit 135, and an update unit 136, and these units realize or execute the functions and actions of the information processing described below. Note that the control unit 130 may have multiple internal configurations divided into processing units that realize or execute the functions and actions of the information processing described below. It is not limited to the configuration shown in FIG. 4, and other configurations may be used as long as they perform the information processing described below.

(Search unit 131)
The search unit 131 searches for a product (an example of a "target") corresponding to the user U. For example, the search unit 131 searches for content listing a product corresponding to a search query specified by the user U from among the product information stored in the product information storage unit 121. Note that the search by the search unit 131 may be performed by a neighborhood search.

The search unit 131 also performs search results using the content acquired by the search process. For example, the search unit 131 narrows down the products listed in each content acquired by the search process based on the user information of the user U who is the sender of the search query, and generates a ranking for each product by ranking the narrowed-down products. Specifically, the information processing device 100 calculates a score (an example of "first score information") for evaluating the products listed in each content based on the user information, and narrows down the products based on the calculated score. For example, the information processing device 100 extracts products with a score equal to or greater than a predetermined value. Then, the information processing device 100 ranks the narrowed-down products based on the scores corresponding to the products. For example, the information processing device 100 assigns higher ranks to products with higher scores.

(Generation unit 132)
The generation unit 132 calculates a score (an example of "second score information") that evaluates the relevance of each of a plurality of candidate users who may be recipients of the content to the product for each product listed in the content. The generation unit 132 then generates a user list by identifying the user U for each product based on the calculated score.

For example, the generation unit 132 can generate a user list that indicates candidate users individually for each product. Specifically, the generation unit 132 identifies a predetermined number of users for each product in descending order of score, and generates a user list in which the identification information and scores of the identified users are associated with a ranking based on the score. For example, when generating a user list that indicates a user that is ranked first in terms of products published in content, the generation unit 132 identifies the user with the highest score for each product, and generates a user list by associating the identification information of the identified user with the score. Note that the generation unit 132 can treat users with the same score as having the same ranking.

The generation unit 132 may also generate, for each product, a user list indicating attributes of candidate users to whom the content in which the product is posted will be provided. Specifically, the generation unit 132 identifies a predetermined number of users for each product in descending order of score, and generates a user list in which attribute information and scores linked to the identified users are associated with a ranking based on the scores. For example, when generating a user list indicating users ranked first in terms of the product posted in the content, the generation unit 132 identifies the user with the highest score for each product, and generates a user list by associating identification information linked to the identified user with the score. Note that, when there are multiple users with the same score, the generation unit 132 can acquire attribute information common to the users, and associate the acquired attribute information with the user list.

(Specific part 133)
The identification unit 133 identifies candidate users to whom the content is to be provided, for each product listed in the content, based on the information of the user list stored in the user list storage unit 123. For example, when advertisement data is input by an advertiser who wishes to distribute an advertisement, the identification unit 133 can identify candidate users by referring to a user list linked to a product corresponding to the advertisement.

(Determination Unit 134)
The determination unit 134 determines which products to provide to a user by ranking the products based on a product score (an example of "first score information") obtained by evaluating the products based on user information about the user, and a user score for each product (an example of "second score information") obtained by previously evaluating the relevance of the product to each of multiple users who may be recipients of the product information.

First, the determination unit 134 reranks (modifies) the search results generated by the search unit 131 based on the user list. Specifically, the determination unit 134 re-ranks (re-ranks) the products included in the search results corresponding to the user based on the combined product score and user score calculated by the above-mentioned formula (1). That is, the determination unit 134 modifies the search results based on the product scores by taking into account the user score for each product.

For example, the determination unit 134 may select either the product score or the user score based on the comparison result between the product score and the user score, and re-rank (re-rank) the products included in the search results corresponding to the user based on the selected score.

Then, the determination unit 134 determines the offered products to be included in the search results to be provided to the user U based on the revised search results. For example, the determination unit 134 determines a predetermined number of products from the revised search results in descending order of score as offered products.

For example, when the determination unit 134 receives a search query from a new user, the determination unit 134 may rerank the search results using a product score that evaluates a product based on information of a similar user similar to the new user, and user score information related to this product. When a new product is searched for, the information processing device 100 may rerank the search results using product scores corresponding to other products similar to the new product, and user scores related to the other products. In this way, the information processing device 100 can deal with the cold start problem.

(Providing unit 135)
The providing unit 135 provides the content listing the product determined by the determining unit 134 to the user U who inputted the query. In addition, the providing unit 135 provides the content listing the corresponding product to the candidate user identified by the identifying unit 133.

(Update unit 136)
The update unit 136 updates the usage mode of the user list. For example, the update unit 136 specifies the content in which the user U performed a predetermined action among the contents provided in the order based on the product score obtained by evaluating the product corresponding to the user U and the user score for each product obtained by evaluating in advance the relevance of each of the multiple users who may be the recipients of the content that lists information about the product. Then, the update unit 136 updates the combination ratio of the product score and the user score that determines the order in which the content is provided, based on a comparison result between the user list that is linked to the product listed in the specified content and indicates individually the users specified from the multiple users who may be the recipients of the content based on the user score and the users who performed the predetermined action.

Specifically, for example, if a user U who has performed a predetermined conversion is included in a user list linked to a product published in the content in which the predetermined conversion has been performed, the update unit 136 increases the weight of the user score corresponding to this user U (weight using the user list). This allows the information processing device 100 to provide product information that better reflects the user score (degree of relevance of the user from the product) when providing content. Also, if a user U who has performed a predetermined conversion is not included in a user list linked to a product published in the content in which the predetermined conversion has been performed, the update unit 136 decreases the weight of the user score corresponding to the user U (weight using the user list). This allows the information processing device 100 to provide product information that better reflects the product score based on user information when providing content.

In addition, when updating a user list linked to a product posted in content that has undergone a predetermined conversion, the update unit 136 may increase the score corresponding to the user U who has performed the predetermined conversion and the score corresponding to a similar user similar to the user U. For example, when the user U who has performed the predetermined conversion (hereinafter referred to as the "relevant user") is included in the user list linked to the product in which the predetermined conversion has been performed, the update unit 136 may increase the score associated with the relevant user in the user list by a predetermined percentage. In addition, when the relevant user is similar to a user included in the user list linked to the product in which the predetermined conversion has been performed, the update unit 136 may increase the score associated with a user similar to the relevant user in the user list by a predetermined percentage. At this time, the update unit 136 may suppress the increase rate of the score to be lower than when the relevant user is included in the user list. In this way, the information processing device 100 can update the user list to reflect the result of the predetermined conversion.

3. Processing Procedure
(3-1. Content provision processing)
Hereinafter, the procedure of information processing executed by the information processing device 100 according to the embodiment will be described. First, an example of the procedure of the content provision processing according to the embodiment will be described with reference to FIG. 9. FIG. 9 is a flowchart showing an example of the procedure of the content provision processing according to the embodiment. The processing procedure shown in FIG. 9 is executed by the control unit 130 of the information processing device 100. The processing procedure shown in FIG. 9 is repeatedly executed while the information processing device 100 is operating.

As shown in FIG. 9, the search unit 131 searches for products corresponding to the user U (step S101). For example, the search unit 131 searches for content listing products corresponding to a search query specified by the user U from among the product information stored in the product information storage unit 121.

Next, the search unit 131 generates search results using the content acquired by the search process (step S102). For example, the search unit 131 narrows down the products listed in each piece of content acquired by the search process based on the user information of the user U who is the sender of the search query, and generates a ranking for each product by ranking each of the narrowed down products.

The determination unit 134 also modifies (reranks) the search results generated by the search unit 131 based on the user list (step S103). That is, the determination unit 134 modifies the search results based on the product scores by taking into account the user scores for each product.

Next, the determination unit 134 determines the products to be included in the search results to be provided to the user U based on the revised search results (step S104).

The providing unit 135 also provides the content listing the offered products to the user U (step S105), and ends the processing procedure shown in FIG. 9.

(3-2. User List Weight Update Processing)
Next, an example of a procedure for updating weights of a user list according to an embodiment will be described with reference to Fig. 10. Fig. 10 is a flowchart showing an example of a procedure for updating weights of a user list according to an embodiment. The procedure shown in Fig. 10 is executed by the control unit 130 of the information processing device 100. The procedure shown in Fig. 10 is repeatedly executed while the information processing device 100 is in operation.

As shown in FIG. 10, the update unit 136 identifies products for which a predetermined conversion has been made by the user U from among the products listed in the content provided to the user U as search results (step S201).

Next, the update unit 136 matches the user U who performed the specified conversion with the user U included in the user list linked to the product identified in step S201 (step S202).

Next, the update unit 136 determines whether the user U who performed the specified conversion is included in the user list linked to the product identified in step S201 (step S203).

If the update unit 136 determines that the user U who has performed the specified conversion is included in the user list linked to the product identified in step S201 (step S203; Yes), it increases the weight for using the user list for the corresponding user (step S204) and ends the processing procedure shown in FIG. 10.

On the other hand, if the update unit 136 determines that the user U who performed the specified conversion is not included in the user list linked to the product identified in step S201 (step S203; No), it reduces the weight for using the user list for the corresponding user (step S205) and ends the processing procedure shown in FIG. 10.

[4. Modifications]
The information processing device 100 according to the embodiment described above may be implemented in various different forms other than the embodiment described above. Therefore, other embodiments of the information processing device 100 will be described below.

(4-1. About the user list)
The user list generated by the information processing device 100 is not limited to the configuration of storing information on related user rankings in association with products as shown in the above-mentioned FIG. 7. For example, the information processing device 100 may generate a user list having a configuration of storing information on related product rankings in association with a user U. FIG. 11 is a diagram showing an example of a user list according to a modified example. As shown in FIG. 11, the user list according to the modified example has an item of "user ID" and an item of "related product ranking", and these items are mutually associated. According to the user list according to the modified example, processing can be performed using the user ID as a key, as in the search processing, so that it is possible to accommodate large-scale implementation.

(4-2. Application to user matching)
In the above embodiment, the process executed by the information processing device 100 can also be applied to matching between users. For example, when an influencer who introduces a certain product exists on a social networking site or the like, information on users who can become followers of the influencer can be provided to the influencer. Also, information on the influencer can be provided to users who are highly related to the product introduced by the influencer.

(4-3. Other Applications)
In the above embodiment, the information processing device 100 may associate in advance with each user a user list indicating other users who are highly related to the user, and use this user list when expanding the users to be processed. Also, the information processing device 100 may associate in advance with each content a content list indicating other content who are highly related to the content, and use this content list for "i2i" recommendations.

5. Hardware Configuration
The information processing device 100 according to the present embodiment described above is realized, for example, by a computer 1000 having a configuration as shown in Fig. 12. Fig. 12 is a hardware configuration diagram showing an example of a computer that realizes the functions of the service providing device according to the present embodiment.

The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which a calculation 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 by a bus 1090.

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 primarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), HDD, flash memory, etc.

The output IF 1060 is an interface for transmitting information to be output to an output device 1010 such as a monitor or printer, which outputs various types of information, and is realized, for example, by a connector conforming to a standard such as Universal Serial Bus (USB), Digital Visual Interface (DVI), or High Definition Multimedia Interface (HDMI (registered trademark)). The input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, keyboard, and scanner, and is realized, for example, by a USB.

The input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. The input device 1020 may also be an external storage medium such as a USB memory.

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

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

For example, when the computer 1000 functions as the information processing device 100 according to this embodiment, the arithmetic device 1030 of the computer 1000 realizes functions similar to those of the control unit 130 by executing a program (e.g., an information processing program) loaded onto the primary storage device 1040. That is, the arithmetic device 1030 realizes the processing by the information processing device 100 according to this embodiment in cooperation with the program (e.g., an information processing program) loaded onto the primary storage device 1040.

[6. Other]
Of the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the process procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified.

In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

Furthermore, the above-mentioned embodiments can be combined as appropriate to the extent that they do not cause any contradictions in the processing content.

[7. Effects]
The information processing device 100 according to the embodiment is provided with an update unit 136 that identifies content for which the user performed a specified action among content provided in an order based on first score information evaluating a target corresponding to a user and second score information for each target that has been previously evaluated for the relevance to the target for each of a plurality of users who may be recipients of content that lists information about the target, and that updates a user list that individually indicates users identified from a plurality of users who may be recipients of the content based on the second score information, and a manner of determining the order based on a comparison result between the user list and the corresponding user who performed the specified action.

As a result, the information processing device 100 according to the embodiment can flexibly change the order in which content that lists information about a target is provided based on a specific action taken by a user, thereby increasing the likelihood that a variety of information will be provided in information distribution.

In addition, for example, in the information processing device 100, when a user who performed a predetermined behavior is included in a user list linked to a target published in the content in which the predetermined behavior was performed, the update unit 136 increases the weight of using the user list for the user. This enables the information processing device 100 to provide product information that better reflects the second score information (user score) that indicates the degree of relevance of the user from the perspective of the product.

In addition, for example, in the information processing device 100, if a user who performed a predetermined action is not included in a user list linked to a target that is published in the content in which the predetermined action was performed, the update unit 136 reduces the weight of the user list for the user. This makes it possible to provide product information that better reflects the product score based on user information.

In addition, in the information processing device 100, when updating a user list linked to a target published in content in which a predetermined action was performed, the update unit 136 increases the score corresponding to the user who performed the predetermined action and the score corresponding to a similar user similar to the user. This allows the information processing device 100 to update the user list to reflect the results of the predetermined conversion.

The above describes the embodiments of the present application in detail with reference to several drawings, but these are merely examples, and the present invention can be embodied in other forms with various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the disclosure section of the invention.

The above-mentioned "section, module, unit" can be read as "means" or "circuit." For example, a control unit can be read as a control means or a control circuit.

REFERENCE SIGNS LIST 10 Terminal device 100 Information processing device 110 Communication unit 120 Storage unit 121 Product information storage unit 122 User information storage unit 123 User list storage unit 124 Weight information storage unit 130 Control unit 131 Search unit 132 Generation unit 133 Identification unit 134 Determination unit 135 Provision unit 136 Update unit

Claims (5)

Identifying the content in which the user performed a predetermined action among the content provided in an order based on first score information evaluating a target corresponding to the user and second score information for each of the targets evaluating in advance the relevance of each of the users who may be recipients of content publishing information about the target to the target, and
an update unit that updates a synthesis ratio of the first score information and the second score information that determines an order in which the content is provided based on a comparison result between a user list that is linked to the target corresponding to the specified content and the user list that indicates users that are specified from among a plurality of users that can be the provision destinations based on the second score information and the corresponding user that performed the predetermined behavior ,
The update unit is
An information processing device characterized in that, when the user in question is included in the user list linked to the target published in the content in which the specified action was performed, a weight corresponding to the second score information for the user in question is increased . The update unit is
The information processing device according to claim 1, characterized in that if the user in question is not included in the user list linked to the target published in the content in which the specified action was performed, the weight corresponding to the second score information for the user in question is reduced. The update unit is
The information processing device according to claim 1 or 2, characterized in that when updating the user list linked to the target published in the content in which the specified action was performed, a score corresponding to the user who performed the specified action and a score corresponding to a similar user similar to the user are increased. 1. A computer-implemented information processing method, comprising:
Identifying the content in which the user performed a predetermined action among the content provided in an order based on first score information evaluating a target corresponding to the user and second score information for each of the targets evaluating in advance the relevance of each of the users who may be recipients of content publishing information about the target to the target, and
an updating step of updating a synthesis ratio of the first score information and the second score information that determine an order in which the content is provided based on a comparison result between a user list that is linked to the target corresponding to the specified content and that indicates users that are specified from among a plurality of users that can be the provision destinations based on the second score information and the corresponding user that performed the predetermined behavior ,
The updating step includes:
When the user is included in the user list associated with the target published in the content in which the predetermined action was performed, the weight corresponding to the second score information is increased for the user.
23. An information processing method comprising: On the computer,
Identifying the content in which the user performed a predetermined action among the content provided in an order based on first score information evaluating a target corresponding to the user and second score information for each of the targets evaluating in advance the relevance of each of the users who may be recipients of content publishing information about the target to the target, and
an update step of updating a synthesis ratio of the first score information and the second score information that determine an order in which the content is provided based on a comparison result between a user list that is linked to the target corresponding to the specified content and indicates users that are specified from among a plurality of users who can be the provision destinations based on the second score information and the corresponding user who performed the predetermined behavior ,
The update procedure comprises:
An information processing program characterized by: increasing a weight corresponding to the second score information for the user when the user in question is included in the user list linked to the target published in the content in which the specified action was performed .