JP2023091676A - Information processing apparatus, information processing method, and information processing program - Google Patents

Abstract

An object of the present invention is to increase the possibility of providing various information in information distribution.
An information processing apparatus according to the present application includes a search section and a determination section. The search unit searches for a target corresponding to the user. The determination unit includes first score information obtained by evaluating an object based on user information about the user, and second score information for each object obtained by pre-evaluating the degree of relevance to the object for each of a plurality of users who can be the recipients of the information of the object. The targets to be provided to the user are determined by ranking the targets based on the score information.
[Selection drawing] Fig. 4

Description

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

2. Description of the Related Art Conventionally, in advertising distribution through the Internet, so-called targeting is performed to narrow down users to whom advertisements are to be distributed. Not limited to advertisement distribution, in information distribution through the Internet such as provision of various contents and recommendation of information, users to whom information is distributed are narrowed down based on pre-registered user attributes and action history. ing.

JP 2015-230717 A

However, conventional techniques have room for improvement in increasing the possibility of providing various information in information distribution. For example, it is difficult to pinpoint information about a product with low inventory to a user who strongly desires to purchase such product. In addition, content distributed to a user who has searched for a predetermined product may be biased toward best-selling products, and other products related to the user of the distribution destination may be buried.

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 increase the possibility of providing various information in information distribution. do.

An information processing apparatus according to the present application includes a search section and a determination section. The search unit searches for a target corresponding to the user. The determination unit includes first score information obtained by evaluating an object based on user information about the user, and second score information for each object obtained by pre-evaluating the degree of relevance to the object for each of a plurality of users who can be the recipients of the information of the object. The targets to be provided to the user are determined by ranking the targets based on the score information.

According to one aspect of the embodiment, it is possible to increase the likelihood that various 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 user list generation method 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 a configuration example of an information processing apparatus according to the 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 user list information 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 the procedure of content provision processing according to the embodiment. FIG. 10 is a flowchart illustrating an example of a procedure of weight update processing for a user list according to the embodiment. FIG. 11 is a diagram illustrating an example of user list information according to a modification. FIG. 12 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus according to the embodiment.

Hereinafter, modes for implementing an information processing apparatus, an information processing method, and an information processing program (hereinafter referred to as "embodiments") according to the present application will be described in detail with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present application are not limited to the embodiments described below. In addition, multiple embodiments described below can be appropriately combined within a range that does not contradict the processing content. In addition, in a plurality of embodiments described below, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

(embodiment)
[1. An example of information processing]
(1-1. Outline of information processing)
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 according to an embodiment; The information processing apparatus 100 executes information processing related to distribution of content. Content includes advertising content delivered with the use of various services, web content corresponding to search queries entered in search engines, and search bars provided on EC (Electronic Commerce) service sites. Various contents such as contents related to the input transaction object are included. Here, the transaction object is the use of goods or services. Transaction objects traded in electronic commerce services include transaction objects traded in various forms such as electronic shopping malls (online malls), online shopping sites, auction sites, and flea market sites. . Note that FIG. 1 shows an example of information processing for a product (an example of a “target”) traded on an electronic shopping mall.

The information processing apparatus 100 shown in FIG. 1 uses a search query (hereinafter referred to as “query” as appropriate) input by the user U who uses the terminal device 10 to provide information to the user. Specifically, the information processing apparatus 100 searches for content corresponding to a search query, narrows down the searched content, reranks the narrowed down content, and provides the user with a predetermined number of content in descending order of rank. . Information processing related to distribution of content executed by the information processing apparatus 100 that provides such information will be described below. In addition, in the following description, the terminal device 10 may be referred to as a user U in some cases. That is, the user U can be read as the terminal device 10 .

In the example shown in FIG. 1 , the information processing system SYS has a plurality of terminal devices 10 and an information processing device 100 . The terminal device 10 and the information processing device 100 are connected to a network N (see FIG. 4, for example) by wire or wirelessly. The terminal device 10 and the information processing device 100 can communicate with each other via the network N. FIG. 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 apparatuses 100 than in the case shown in FIG.

A 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 . It is assumed that each user U uses at least one terminal device 10 . A smartphone is assumed as a typical example of the terminal device 10, but it may be realized by a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. .

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

In addition, the terminal device 10 can display information for using 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 from the information processing device 100 control information for realizing information display processing by a web browser, an application, or the like, the terminal device 10 realizes display processing according to the received control information.

The information processing apparatus 100 illustrated in FIG. 1 functions as a search apparatus that provides search results to the terminal apparatus 10 used by the user U who has input a query. For example, the information processing apparatus 100 has a function as a search engine that executes search processing for products traded on an electronic shopping mall. The information processing apparatus 100 also has a database in which information about products to be searched using a query is indexed and stored, and executes search processing on the information in the database. For example, this database information is stored in the storage unit 120 (see FIG. 4, for example).

Information about products may include various types of information. For example, product information includes the seller, selling price, product image, category, title, description, payment method, sales period, sales quantity, and other product information. Various information can be included. In addition, the product information may include product sales histories such as the number of product reservations, the number of orders, the number of sales, and the amount of money ordered (sales). For example, the product information may include information such as the time elapsed since the date and time the product was sold, the number of views of information indicating the product, the number of reviews on the product, and the evaluation of the transaction target. The information on the product may include information on external factors related to the product, such as information posted on an SNS (Social Networking Service).

In the information processing system SYS shown in FIG. 1, the information processing system SYS shown in FIG. SYS may have any configuration. 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 that is associated with products listed in content. The information processing apparatus 100 uses a score obtained by pre-evaluating the degree of relevance to the product for each of the plurality of users U to whom the content can be provided, for each product (an example of a “target”) posted in the content, to determine the degree of relevance to the product. The user U specified from among is individually shown. The information processing apparatus 100 generates, for example, a user list indicating, as candidate users, a predetermined number of users U identified in descending order of the score among the plurality of users U. The user list can indicate the ranking of each user U who has a higher degree of relevance from the point of view of the product posted 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). On the other hand, based on the search query specified by the user U, the information processing apparatus 100 executes search processing for products (contents) corresponding to the search query (step S3). For example, the information processing apparatus 100 acquires content listing products corresponding to the search query from the database. Acquisition of information corresponding to the query is performed using existing technology, and any processing may be used as long as the product can be specified, and detailed description thereof will be omitted.

Next, the information processing apparatus 100 generates search results using the content acquired by the search process (step S4). For example, the information processing apparatus 100 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 ranks the narrowed-down products. to generate a ranking for each product.

Specifically, based on the user information, the information processing apparatus 100 calculates a product score (an example of “first score information”) obtained by evaluating a product posted in each content, and based on the calculated product score to narrow down the products. For example, the information processing apparatus 100 narrows down products whose scores are equal to or greater than a predetermined value. The information processing apparatus 100 also ranks the narrowed down products based on the scores corresponding to the products. For example, the information processing apparatus 100 assigns higher ranks to products with higher scores. Then, the information processing apparatus 100 generates a search result in which the content is arranged in descending order from the content listing the product given the highest ranking.

A method for calculating the product score will be specifically described. For example, the information processing apparatus 100 multiplies each of a plurality of elements, such as the number of items ordered, the order amount, and the number of views, by the weight (coefficient) of each element (hereinafter referred to as a "partial score"). ) to calculate the product score. For example, the information processing device 100 may calculate the sum of the partial scores of each of the plurality of elements regarding the product as the product score, or calculate the average of the partial scores of each of the plurality of elements regarding the product as the product score. may be calculated as

Further, the information processing apparatus 100 may calculate a product score using a total value calculated for each predetermined period for each of a plurality of factors such as the number of product orders, the order amount, and the number of views. In this case, the information processing apparatus 100 uses a value (hereinafter referred to as a "period score") obtained by multiplying the total value of a plurality of elements of the product, which are totaled for each predetermined period, by the weight (coefficient) of each element. may be used to calculate product scores. Further, the information processing apparatus 100 may calculate the product score using a value obtained by multiplying the period score of each period by an attenuation coefficient according to the difference between the period and the time of calculation. In this case, the information processing apparatus 100 may calculate the score of the transaction target using a value obtained by multiplying the period score of each period by an attenuation coefficient whose value decreases in the past period. In addition, the information processing apparatus 100 may calculate the product score using a total value calculated for each date for each of a plurality of elements of the product.

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

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

After generating the search results, the information processing apparatus 100 uses the user list to rerank (correct) the search results (step S5). For example, the information processing apparatus 100 may calculate a product score (an example of “first score information”) obtained by evaluating a product based on user information about user U, and a user score (“ The search results are reranked based on "second score information" (an example). Specifically, the information processing apparatus 100 ranks the products based on the sum of the product score and the user score for this product (hereinafter referred to as "total score"). Specifically, the information processing device 100 calculates the total score based on the following formula (1). Note that "n" shown in the following formula (1) is a predetermined weight for determining the utilization mode of the user score based on the user list. In addition, the formula (1) shown below 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 publishes the target corresponding to the user such as the product.
Total score = n x product score + (1-n) x user score (1)

Further, for example, the information processing device 100 selects either one of the product score and the user score based on the comparison result between the product score and the user score for this product, and based on the selected score, selects the product rank the Specifically, the information processing apparatus 100 selects the larger one of the product score and the user score regarding this product, and performs ranking based on the selected score. Alternatively, the information processing apparatus 100 may select the smaller one of the product score and the user score regarding this product, and perform ranking based on the selected score.

In addition, when receiving a search query from a new user, the information processing apparatus 100 uses the product score obtained by evaluating the product based on the information of similar users similar to the new user and the user score information related to this product to obtain the search result may be reranked. In addition, when a new product is searched, the information processing device 100 uses the product scores corresponding to other products similar to the new product and the user scores related to the other products to rerank the search results. may By doing so, the information processing apparatus 100 can cope with the cold start problem.

Subsequently, the information processing apparatus 100 determines the product to be provided to the user U based on the reranked search results (step S6). For example, the information processing apparatus 100 selects a predetermined number of products from among the reranked products as products to be posted, starting from the product with the highest rank. Then, the information processing device 100 provides the user U with content related to the determined posted product (step S7).

Further, the information processing apparatus 100 identifies conversion products that have undergone a predetermined conversion among the products listed in the content provided to the user U as search results (step S8). For example, predetermined conversions include purchase of a product, addition of a product to a shopping cart, posting on an SNS, viewing of a page on which detailed information on a product is posted, and the like.

Then, the information processing apparatus 100 updates the usage mode of the user list according to whether or not the user U who has performed the predetermined conversion is included in the user list linked to the product published in the identified content. (step S9).

For example, when the user U who performed the predetermined conversion is included in the user list associated with the product posted in the content subjected to the predetermined conversion, the information processing apparatus 100 corresponds to the user U. Increase the weight of the user score (the weight of using the user list). Thereby, the information processing apparatus 100 can provide product information that further reflects the degree of relevance of the user U from the product.

Further, for example, when the user U who has performed the predetermined conversion is not included in the user list associated with the product posted in the content that has undergone the predetermined conversion, the information processing apparatus 100 allows the user U to Decrease the weight of the corresponding user score (the weight that uses the user list). Thereby, the information processing apparatus 100 can provide product information that reflects the evaluation of the product.

In addition, when updating the user list linked to the product posted in the content that the user U performed a predetermined conversion, the information processing apparatus 100 updates the score corresponding to the user U who performed the predetermined conversion and the score corresponding to the user U You may raise the score corresponding to the similar user who resembles. Accordingly, the information processing apparatus 100 can update the user list by reflecting the predetermined conversion result.

(1-2. User list)
Generation of a user list by the information processing apparatus 100 will be described below with reference to FIG. FIG. 2 is a diagram for explaining an example of a user list generation method according to the embodiment. FIG. 2 illustrates an example of a user list showing, for each product, users U ranked first in terms of products published in content among users U. As shown in FIG. Note that FIG. 2 exemplifies a user list (Top-K (K=1)) indicating the user U who ranks first in terms of products listed in the content for each product. It is possible to arbitrarily generate a user list showing users U identified up to a predetermined rank, such as a user list showing users U ranked up to the second place for each product (Top-K (K=2)). In addition, "product X1", "product X2", and "product X3" shown in FIG. 2 indicate contents in which products are posted.

For example, the information processing apparatus 100 generates a score (an example of “second score information”) obtained by evaluating the degree of relevance to each product listed in the content for each of the plurality of users U who may be the recipients of the content. Calculate Then, the information processing apparatus 100 generates a Top-K (K=1) user list by specifying the user U with the highest calculated score for each content. For example, the information processing apparatus 100 generates a user list that individually indicates candidate users to whom content is provided for each product. Thereby, the information processing apparatus 100 can individually identify the user with the highest degree of relevance from the point of view of the product. Alternatively, the information processing apparatus 100 generates list information indicating attributes of candidate users to whom content is provided for each product. Accordingly, the information processing apparatus 100 can identify the attribute of the user that has the highest degree of relevance to the product. Further, when generating the user list, the information processing apparatus 100 weights the score of the first user who performed a predetermined conversion on the product or the second user who is similar to the first user, and the score is A predetermined number of users may be included in the user list in descending order. Thereby, a user list reflecting predetermined conversion results can be generated.

In FIG. 2, when each user U is viewed from "product X1", user U3 ranks first, and when each user U is viewed from "product X2", user U1 ranks first. There is, and when each user U is viewed from "merchandise X3", it is indicated that user U2 ranks first. 2 also shows a user list L2-1 and a user list L2-2 generated by the information processing apparatus 100. FIG.

A user list L2-1 shown in FIG. 2 is an example of a user list that individually indicates candidate users to whom content is provided for each product. For example, as shown in FIG. 2, the user list L2-1 has an item of "product ID" and an item of "related user ranking", and these items are associated with each other. In the item of "product ID", a product ID, which is identification information for identifying a product, is stored. The item "related user ranking" stores a user ID as identification information for identifying the user U who ranks first in terms of product, and a score indicating the user's degree of relevance to the product. According to the user list L2-1 shown in FIG. 2, the user ranked first (highest degree of relevance and matching) from "product X1", "product X2", and "product X3" U is individually identifiable.

A user list L2-2 shown in FIG. 2 is an example of a user list indicating attributes of candidate users to whom content is provided for each product. For example, as shown in FIG. 2, the user list L2-2 has an item of "product ID" and an item of "related user attribute ranking", and these items are associated with each other. . The above-mentioned product ID is stored in the item of "product ID". The attribute information indicating the attribute of the user ranked first in terms of the above-mentioned product and the above-mentioned score are stored in the item of "related user ranking". According to the user list L2-2 shown in FIG. 2, the user U who ranks first (highest degree of relevance and matches) from "product X1", "product X2", and "product X3" attribute can be specified.

In addition, the information processing apparatus 100 may weight the scores of users who have performed predetermined conversions on products or users who are similar to this user, and may include a predetermined number of users in the user list in descending order of scores. . Thereby, the information processing apparatus 100 can reflect the predetermined conversion result in the user list.

Further, the information processing apparatus 100 uses the user lists L2-1 and L2-2 shown in FIG. For example, the information processing apparatus 100 can rank products in consideration of user scores defined in user lists L2-1 and L2-2, as will be described later.

The information processing apparatus 100 can also provide information based on the user list. For example, based on the user list, information processing apparatus 100 identifies candidate users to whom content is provided for each product. Then, the information processing apparatus 100 provides the candidate user with the content listing the corresponding product. As a result, the information processing apparatus 100 can provide information to users with a high degree of relevance when viewed from the product.

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

The information processing device 100 searches for content listing products corresponding to the user U1 (step S11). In FIG. 3, content C1 listing product Y1, content C2 listing product Y2, content C3 listing product Y3, and the like are shown as content retrieved by information processing apparatus 100. In FIG. ing.

Subsequently, the information processing apparatus 100 calculates the product score published in the retrieved content (step S12). In FIG. 3, the score α1 is the score of product Y1 published in content C1, the score α2 is the score of product Y2 published in content C2, and the score α3 is the score of product Y3 published in content C3. etc. are shown.

Subsequently, the information processing apparatus 100 narrows down the products listed in the searched content based on the product score, ranks the products listed in the narrowed down content, and generates search results ( step S13). FIG. 3 shows a search result L3-1 including the first-ranked product Y1, the second-ranked product Y2, and the third-ranked product Y3.

In the background of product scoring, the information processing apparatus 100 also calculates the score of the user U1 in terms of the product listed in the retrieved content (step S14). In FIG. 3, the score β1 of user U1 viewed from product Y1 published in content C1, the score β2 of user U1 viewed from product Y2 published in content C2, and the score β2 of user U1 viewed from product Y3 published in content C3 are shown. The score β3 of the viewing user U1 and the like are shown.

Subsequently, the information processing apparatus 100 ranks again the products included in the search results based on the sum of the product score calculated in step S12 and the score of the user U1 calculated in step S14 (list ranking) to correct the search result based on the product score (step S15). In the search result L3-2 shown in FIG. 3, the order of the products is changed due to the correction of the search result L3-1. According to the search result L3-2 shown in FIG. 3, the product Y1 is replaced with the product Y2, the second product Y2 is replaced with the product Y3, and the third product Y3 is replaced with the product Y1.

In this way, the information processing apparatus 100 corrects (reranks) the search results corresponding to the user U1 using the score of the user U1 in terms of products, thereby increasing the possibility of providing various information. can be enhanced. For example, by pre-scoring the users U who can serve as delivery destinations of the content from the perspective of the product, information on products with low inventory, such as auction items, can be pinpointed to users U who strongly desire to purchase such products. It is possible to increase the possibility of being offered with points. Similarly, it is possible to increase the possibility that information such as job positions with limited hiring slots will be pinpointed to users U who have conditions and aptitudes for job positions. In addition, it is possible to increase the possibility that a user who has searched for a predetermined product will be provided with not only content with a hot-selling product, but also content with other products that match the user of the distribution destination. can. In addition, even with information such as news content, which has unlimited resources, it is possible to increase the possibility that news that matches only a specific user will be provided to the specific user.

[2. Configuration of information processing device]
The information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram illustrating a configuration example of an information processing apparatus according to the embodiment; As shown in FIG. 4, the information processing apparatus 100 has a communication section 110, a storage section 120, and a control section .

(Regarding communication unit 110)
Communication unit 110 is implemented by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the 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. FIG.

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

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

As shown in FIG. 5, the product information stored in the product information storage unit 121 has an item of "product ID" and an item of "product information". These items of product information are associated with each other. In addition, in FIG. 5, the information stored in the item of "merchandise information" is simplified and expressed as an abstract concept.

Identification information for identifying products to be traded on the online shopping mall is stored in the item of “merchandise ID”. Various information related to the product is stored in the item of “product information”. For example, the information stored in the item of "product information" includes product distributors, sales prices, product images, categories, titles, descriptions, payment methods, sales periods, sales Various information used to provide product information such as quantity may be included. The information stored in the item of "merchandise information" may include the sales history of the merchandise, such as the number of reservations, the number of orders, the number of sales, and the order amount (sales) of the merchandise. For example, the information about the product may include information such as the time elapsed since the date and time when the product was sold, the number of views of information indicating the product, the number of reviews of the product, and the evaluation of the product. The information on the product may include information on external factors related to the product, such as information posted on an SNS (Social Networking Service).

According to FIG. 5, it is shown that the product information of the product identified by product ID: "product #1" is "product information #1".

(User information storage unit 122)
The user information storage unit 122 stores user information regarding users U who use the online shopping mall. FIG. 6 is a diagram illustrating an example of user information according to the embodiment; Note that FIG. 6 shows an example of user information according to the embodiment, and information other than that shown in FIG. 6 may be included.

As shown in FIG. 6, the user information stored in the user information storage unit 122 includes a "user ID" item, a "personal information" item, a "search history" item, and a "purchase history" item. , and a plurality of items such as a "post history" item. These items of user information are associated with each other. Note that in FIG. 6, the information stored in the "personal information" item, the "search history" item, the "purchase history" item, the "posting history" item, etc. is simplified and abstract concepts are used. is expressed as

Identification information for identifying the user U is stored in the “user ID” item. Personal information belonging to the user U is stored in the “personal information” item. The personal information may include information such as name, gender, age, family structure, residence type, annual income, and interests.

A history of search queries input by the user U is stored in the item “search history”. A purchase history, which is a history of purchases made by the user U, is stored in the "purchase history" item. A posting history, which is a history of postings by the user U, is stored in the “posting history” item.

According to FIG. 6, user U identified by user ID: "U#1" is identified by "personal information": "personal information #1" and stored in search history: "search history #1". It is indicated that a search using a search query is performed, purchases indicated in purchase history: "purchase history #1" are performed, and posts indicated in posting history: "post history #1" are performed.

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

As shown in FIG. 7, the information of the user list stored in the user list storage unit 123 has an item of "product ID" and an item of "related user ranking". These items included in the user list information are associated with each other.

Identification information for identifying products to be traded on the online shopping mall is stored in the item of “merchandise ID”. The identification information stored in the "product ID" item may be the same as the identification information stored in the "product ID" item of the product information described above.

The item of “related user ranking” has a plurality of items for storing user ID and score information for each user's rank in terms of products. FIG. 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, the user U identified by the user ID: "U#3" is the sole first place in terms of the product identified by the product ID: "product #1". It is shown that the score indicating the degree of relevance of the user U identified by is "score SC-1". In addition, the user U identified by the user ID "U#4" and the user U identified by the user ID "U#11" have the same ratio in terms of the product identified by the product ID "product #1". It is shown that the score indicating the degree of relevance of each of the users U who are ranked second and identified by "U#4" and "U#11" is "score SC-2". In addition, from the point of view of the product identified by product ID: "product #1", user U identified by user ID: "U#5" is the sole third ranked user and is identified by "U#5". It is shown that the score indicating the degree of relevance of user U is "score SC-3".

(Weight information storage unit 124)
The weight information storage unit 124 stores weight information for determining how to use the user list. FIG. 8 is a diagram illustrating an example of weight information according to the embodiment. Note that FIG. 8 shows an example of weight information according to the embodiment, and information other than that shown in FIG. 8 may be included.

As shown in FIG. 8, the weight information stored in the weight information storage unit 124 includes a "user ID" item, a "product score weight" item, and a "user score (product→user) weight". items and These items of weight information are associated with each other.

Identification information for identifying the user U is stored in the “user ID” item. The identification information stored in the "user ID" item is the same as the identification information stored in the "user ID" item of the user information described above.

In the item "weight of product score", information of a weight by which the product score is multiplied when correcting the search result of the product is stored. The weight information stored in the item "product score weight" corresponds to the value of "n" shown in the above equation (1). The item "weight of user score" stores information on the weight by which the user score (score defined in the user list) as viewed from the product is multiplied when correcting the search result of the product. The weight information stored in the item "user score weight" corresponds to the value "1-n" shown in the above equation (1).

According to FIG. 8, the weight to be multiplied by the product score is "0.8" when correcting the search result of the product corresponding to the user U identified by the user ID "U#1". It is shown that the score weight to be multiplied by the viewed user score is "0.2".

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

The control unit 130 shown in FIG. 4 includes 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 each of these units performs operations described below. implement or perform information processing functions or operations that Note that the control unit 130 may have a plurality of divided internal configurations for each processing unit that realizes or executes the information processing functions and actions described below. The configuration is not limited to that shown in FIG. 4, and other configurations may be used as long as they are configured to perform information processing, which will be described later.

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

Also, the search unit 131 obtains a search result 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 sent the search query, and ranks the narrowed-down products. Generate a ranking for each product by doing so. Specifically, based on the user information, the information processing apparatus 100 calculates a score (an example of “first score information”) obtained by evaluating the product posted in each content, and based on the calculated score, the product to narrow down. For example, the information processing device 100 extracts products whose scores are equal to or greater than a predetermined value. Then, the information processing apparatus 100 ranks the narrowed down products based on the scores corresponding to the products. For example, the information processing apparatus 100 assigns higher ranks to products with higher scores.

(Generating unit 132)
The generating unit 132 calculates a score (an example of “second score information”) that evaluates the degree of relevance to the product for each of the products listed in the content, for each of a plurality of candidate users who can be the content recipient. . Then, the generation unit 132 generates a user list by specifying the user U for each product based on the calculated score.

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

In addition, the generation unit 132 may generate, for each product, a user list indicating attributes of candidate users to whom content on which the product is posted is provided. Specifically, the generation unit 132 identifies a predetermined number of users in descending order of score for each product, and associates attribute information and scores associated with the identified users with rankings based on the scores in a user list. to generate For example, when generating a user list indicating users ranked first in terms of products posted in content, the generation unit 132 identifies the user with the highest score for each product, and assigns the identified user A user list is generated by associating the associated identification information with the score. In addition, when there are a plurality of 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.

(Specifying unit 133)
The identifying unit 133 identifies candidate users to whom the content is provided based on the information in the user list stored in the user list storage unit 123, for each product listed in the content. For example, when an advertiser who wishes to distribute an advertisement inputs advertisement data, the specifying unit 133 can refer to a user list associated with a product corresponding to the advertisement and specify a candidate user.

(Determination unit 134)
The determination unit 134 determines a product score (an example of “first score information”) obtained by evaluating a product based on user information about the user, and the degree of relevance to the product for each of a plurality of users who may be recipients of product information. Products to be provided to the user are determined by ranking the products based on user scores (an example of “second score information”) evaluated in advance for each product.

First, the determination unit 134 reranks (corrects) the search results generated by the search unit 131 based on the user list. Specifically, the determining unit 134 reranks the products included in the search results corresponding to the user (reranking do). That is, the determination unit 134 modifies the search results based on the product score by adding the user score for each product.

Also, for example, the determining unit 134 selects one of the product score and the user score based on the comparison result of the product score and the user score, and based on the selected score, determines the search result corresponding to the user. The included products may be re-ranked (re-ranked).

Then, the determining unit 134 determines the offer products to be included in the search results to be provided to the user U based on the corrected search results. For example, the determination unit 134 determines a predetermined number of products to be provided products in descending order of score among the corrected search results.

Also, for example, when receiving a search query from a new user, the determination unit 134 uses the product score obtained by evaluating the product based on the information of similar users similar to the new user, and the user score information related to this product to perform a search. You may rerank the results. In addition, when a new product is searched, the information processing device 100 uses the product scores corresponding to other products similar to the new product and the user scores related to the other products to rerank the search results. may By doing so, the information processing apparatus 100 can cope with the cold start problem.

(Providing unit 135)
The providing unit 135 provides the user U who has input the query with content listing the products determined by the determining unit 134 . Further, the providing unit 135 provides the candidate user identified by the identifying unit 133 with content in which the corresponding product is posted.

(Update unit 136)
The updating unit 136 updates the usage mode of the user list. For example, the updating unit 136 may obtain a product score obtained by evaluating a product corresponding to the user U, and a user score for each product obtained by pre-evaluating the degree of relevance to the product for each of a plurality of users who may serve as content recipients of content posting information about the product. Among the contents provided in the order based on the score, the contents for which the user U performed a predetermined action are identified. Then, the update unit 136 is a user list that is linked to the product listed in the specified content, and that individually indicates users specified from among a plurality of users who can be content recipients based on user scores. Then, based on the result of comparison with the user who performed the predetermined action, the combined ratio of the product score and the user score, which determines the order in which the content is provided, is updated.

Specifically, for example, if a user U who has performed a predetermined conversion is included in a user list associated with a product posted in content that has undergone a predetermined conversion, the updating unit 136 updates the user U Increase the weight of the user score corresponding to (the weight of using the user list). As a result, when providing content, the information processing apparatus 100 can provide product information that better reflects the user score (the degree of relevance of the user to the product). In addition, if the user U who has performed the predetermined conversion is not included in the user list linked to the product posted in the content that has undergone the predetermined conversion, the updating unit 136 updates the user score corresponding to the user U. Decrease the weight (the weight that uses the user list). Accordingly, when providing content, the information processing apparatus 100 can provide product information that better reflects the product score based on the user information.

Further, for example, when updating the user list linked to the product listed in the content that has undergone a predetermined conversion, the updating unit 136 updates the score corresponding to the user U who has performed a predetermined conversion and the score similar to the user U. You may raise the score corresponding to a similar user. For example, if a user U who has performed a predetermined conversion (hereinafter referred to as a “applicable user”) is included in a user list associated with a product that has undergone a predetermined conversion, the update unit 136 updates the user list. The score associated with the user may be increased by a predetermined percentage. Further, for example, if the user is similar to a user included in a user list associated with a product that has undergone a predetermined conversion, the update unit 136 associates the user with a user similar to the user in the user list. The score may be increased by a predetermined percentage. At this time, the updating unit 136 may keep the rate of increase in the score lower than when the corresponding user is included in the user list. Thus, the information processing apparatus 100 can update the user list so as to reflect the result of a predetermined conversion.

[3. Processing procedure]
(3-1. Content provision processing)
An information processing procedure executed by the information processing apparatus 100 according to the embodiment will be described below. First, an example of the procedure of content providing processing according to the embodiment will be described with reference to FIG. 9 . FIG. 9 is a flowchart illustrating an example of the procedure of 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 apparatus 100 . The processing procedure shown in FIG. 9 is repeatedly executed while the information processing apparatus 100 is in operation.

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 the product information stored in the product information storage unit 121 for content listing products corresponding to a search query specified by the user U. FIG.

Subsequently, 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 content acquired by the search process based on the user information of the user U who sent the search query, and ranks the narrowed-down products. Generate a ranking for each product by doing so.

The determination unit 134 also corrects (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 score by adding the user score for each product.

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

Further, the providing unit 135 provides the user U with the content in which the provided product is posted (Step S105), and ends the processing procedure shown in FIG.

(3-2. User list weight update processing)
Next, with reference to FIG. 10, an example of the procedure of the user list weight update process according to the embodiment will be described. FIG. 10 is a flowchart illustrating an example of a procedure of weight update processing for a user list according to the embodiment. The processing procedure shown in FIG. 10 is executed by the control unit 130 of the information processing apparatus 100 . The processing procedure shown in FIG. 10 is repeatedly executed while the information processing apparatus 100 is in operation.

As shown in FIG. 10, the updating unit 136 identifies products for which a predetermined conversion has been performed by the user U, 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 a predetermined conversion with the user U included in the user list associated with the product identified in step S201 (step S202).

Next, the update unit 136 determines whether or not the user U who performed the predetermined conversion is included in the user list associated with the product specified in step S201 (step S203).

When the update unit 136 determines that the user U who performed the predetermined conversion is included in the user list linked to the product identified in step S201 (step S203; Yes), the weight for using the user list is increased for the user. Then (step S204), the processing procedure shown in FIG. 10 ends.

On the other hand, when the update unit 136 determines that the user U who performed the predetermined conversion is not included in the user list linked to the product identified in step S201 (step S203; No), the user list is used for the user. The weight is decreased (step S205), and the processing procedure shown in FIG. 10 ends.

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

(4-1. User list)
The user list generated by the information processing apparatus 100 is not limited to a configuration in which related user ranking information is stored in association with products, as shown in FIG. 7 described above. For example, the information processing apparatus 100 may generate a user list configured to store related product ranking information in association with the user U. FIG. FIG. 11 is a diagram showing an example of a user list according to a modification. As shown in FIG. 11, the user list according to the modification has an item of "user ID" and an item of "related product ranking", and these items are associated with each other. According to the user list according to the modified example, it is possible to execute processing using the user ID as a key, as in the search processing, so that large-scale implementation can be supported.

(4-2. Application to matching between users)
In the above embodiment, the processing executed by the information processing apparatus 100 can also be applied to matching between users. For example, if there is an influencer who introduces a certain product on an SNS or the like, it is possible to provide the influencer with information on users who can be followers of the influencer. Influencer information can also be provided to users who have a high degree of relevance to products introduced by the influencer.

(4-3. Other applications)
In the above embodiment, the information processing apparatus 100 associates each user in advance with a user list indicating other users with a high degree of relevance from the user's point of view, and when expanding the users to be processed, You can use this user list. Further, the information processing apparatus 100 associates in advance with each content a content list indicating other content that is highly related to the content, and uses this content list for recommendation of “i2i”. good.

[5. Hardware configuration]
Also, the information processing apparatus 100 according to the present embodiment described above is implemented by, for example, a computer 1000 configured as shown in FIG. FIG. 12 is a hardware configuration diagram showing an example of a computer that implements the functions of the service providing apparatus according to this embodiment.

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

Arithmetic device 1030 operates based on programs stored in primary storage device 1040 and secondary storage device 1050, programs read from input device 1020, and the like, and executes various types of processing. 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, and is implemented by a ROM (Read Only Memory), HDD, flash memory, or the like.

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 implemented 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, or a semiconductor memory. 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 according to the present embodiment, the arithmetic device 1030 of the computer 1000 executes a program (for example, an information processing program) loaded on the primary storage device 1040 to A function similar to that of the control unit 130 is realized. That is, the arithmetic device 1030 realizes the processing by the information processing device 100 according to this embodiment in cooperation with the program (for example, the information processing program) loaded on the primary storage device 1040 .

[6. others]
Of the processes described in the above embodiments, all or part of the processes described as being automatically performed can be manually performed, or all or part of the processes described as being manually performed. Part can also be done 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.

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.

Moreover, each embodiment described above can be appropriately combined within a range in which the processing contents are not inconsistent.

[7. effect]
The information processing device 100 according to the embodiment includes a search unit 131 and a determination unit 134 . The search unit 131 searches for a target corresponding to the user. The determining unit 134 pre-evaluates the first score information that evaluates the target (for example, product) based on the user information about the user, and the degree of relevance to the target for each of the plurality of users who can be the target information recipients. Targets to be provided to the user are determined by ranking the targets based on the second score information for each target.

For example, in the information processing device 100, the determining unit 134 re-ranks the target search results corresponding to the user based on the sum of the first score information and the second score information.

Further, for example, in information processing device 100, determination unit 134 selects one of the first score information and the second score information based on the result of comparison between the first score information and the second score information. One is selected, and the target search results corresponding to the user are re-ranked based on the selected score information.

For this reason, the information processing apparatus 100 according to the embodiment can increase the possibility that various information will be provided in information distribution. For example, by pre-scoring the users U who can serve as delivery destinations of the content from the perspective of the product, information on products with low inventory, such as auction items, can be pinpointed to users U who strongly desire to purchase such products. It is possible to increase the possibility of being offered with points. Similarly, it is possible to increase the possibility that information such as job positions with limited hiring slots will be pinpointed to users U who have conditions and aptitudes for job positions. In addition, it is possible to increase the possibility that a user who has searched for a predetermined product will be provided with not only content with a hot-selling product, but also content with other products that match the user of the distribution destination. can. In addition, even with information such as news content, which has unlimited resources, it is possible to increase the possibility that news that matches only a specific user will be provided to the specific user.

Further, in the information processing apparatus 100, when the search unit 131 searches for a target corresponding to the new user, the determination unit 134 evaluates the target based on information on similar users similar to the new user, and obtains first score information. , and second score information that pre-evaluates the degree of relevance for each of the similar users, to rank the targets.

Further, in the information processing device 100, when the searching unit 131 searches for a new target, the determining unit 134 provides the first score information corresponding to other targets similar to the new target, and the score information of the plurality of users. The new subjects are ranked using the second score information, which pre-evaluates the relevance of each to the other subjects.

With these, the information processing apparatus 100 can cope with the cold start problem.

As described above, the embodiments of the present application have been described in detail based on several drawings, but these are examples, and various modifications and It is possible to carry out the invention in other forms with modifications.

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

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 Part 136 Update part

Claims (7)

a search unit for searching for a target corresponding to a user;
first score information obtained by evaluating the target based on user information about the user; and a determination unit that determines the target to be provided to the user by ranking the target based on the score information of No. 2 above. The decision unit
The information processing apparatus according to claim 1, wherein the search results of the target corresponding to the user are re-ranked based on a sum result of the first score information and the second score information. . The decision unit
Selecting one of the first score information and the second score information based on a comparison result between the first score information and the second score information, and based on the selected score information 2. The information processing apparatus according to claim 1, wherein the search results of the target corresponding to the user are ranked again. The decision unit
When the target corresponding to the new user is retrieved by the search unit, the first score information evaluated for the target based on information of similar users similar to the new user, and each of the similar users 4. The information processing apparatus according to any one of claims 1 to 3, wherein the second score information obtained by pre-evaluating the degree of association is used to rank the objects. The decision unit
When the search unit searches for the new target, the first score information corresponding to the other target similar to the new target, and the relationship of each of the plurality of users to the other target 5. The information processing apparatus according to any one of claims 1 to 4, wherein the new target is ranked using the second score information obtained by evaluating the degree in advance. A computer-executed information processing method comprising:
a search step of searching for an object corresponding to the user;
first score information obtained by evaluating the target based on user information about the user; and a determining step of determining the target to be provided to the user by ranking the target based on the score information of No. 2 above. to the computer,
a search procedure for searching for an object corresponding to a user;
first score information obtained by evaluating the target based on user information about the user; and a determination procedure for determining the target to be provided to the user by ranking the target based on the score information of No. 2 above.

Images