JP7387974B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

Application of Article 30, Paragraph 2 of the Patent Act Published on November 9, 2021 Address: https://topics. shopping. yahoo. co. jp/notice/archives/202111102021. html Published on November 19, 2021 Address https://store-info. yahoo. co. jp/shopping/topics/tool2021/test/211119-3. html Posted on December 3, 2021 and public address https://appstoreconnect. apple. com/apps/446016180/appstore/reviewsubmissions/details/e9ae2241-e0f9-4960-9cf0-94d64f0527bf https://apps. apple. com/jp/app/yahoo-%E3%82%B7%E3%83%A7%E3%83%83%E3%83%94%E3%83%B3%E3%82%B0/id446016180 Reiwa 4 January 6th post address https://play. google. com/console/u/0/developers/9059031076674808747/app/4972974430624390735/tracks/4698240759174279260/releases/278/details

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

Conventionally, techniques for providing various information to users are known. For example, a technique is known that provides users with ranking information using transaction objects such as product information corresponding to a search query as ranking factors (for example, Patent Document 1).

Patent No. 6776072

However, there is room for improvement in the above-mentioned conventional technology. For example, with the above-mentioned conventional technology, it is possible to provide users with ranking information in which ranking elements corresponding to a search query are ranked, but there is room for improvement in providing multiple pieces of ranking information corresponding to a search query. .

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 more appropriately provide multiple pieces of ranking information corresponding to a search query. shall be.

The information processing device according to the present application includes a receiving section, an estimating section, a determining section, and a providing section. The reception unit receives search queries. The estimation unit estimates the intention of the search query received by the reception unit. The determining unit determines the order in which the plurality of ranking information items are arranged based on the intent of the search query estimated by the estimating unit. The providing unit provides a plurality of pieces of ranking information arranged in the order determined by the determining unit.

According to one aspect of the embodiment, it is possible to more appropriately provide a plurality of pieces of ranking information corresponding to a search query.

FIG. 1 is a diagram for explaining an information processing method performed by an information processing apparatus according to an embodiment. FIG. 2 is a diagram illustrating an example of content provided to a user from the information processing apparatus according to the embodiment. FIG. 3 is a diagram illustrating an example of classification of scores indicating the degree of relevance of a search query to each of a category and a brand in the information processing apparatus according to the embodiment. FIG. 4 is a diagram illustrating an example of case classification determination information included in the information processing apparatus according to the embodiment. FIG. 5 is a diagram illustrating an example of ranking information determination information included in the information processing apparatus according to the embodiment. FIG. 6 is a diagram illustrating an example of ranking of transaction targets from a plurality of perspectives in the information processing apparatus according to the embodiment. FIG. 7 is a diagram illustrating an example of search results and ranking information provided by the information processing device according to the embodiment. FIG. 8 is a diagram illustrating another example of ranking information provided by the information processing device according to the embodiment. FIG. 9 is a diagram illustrating a configuration example of an information processing device according to an embodiment. FIG. 10 is a diagram illustrating an example of a user information table stored in the user information storage unit according to the embodiment. FIG. 11 is a diagram illustrating an example of a transaction target information table stored in the transaction target information storage unit according to the embodiment. FIG. 12 is a diagram illustrating an example of a content table stored in the content storage unit according to the embodiment. FIG. 13 is a flowchart illustrating an example of the flow of information processing executed by the information processing device. FIG. 14 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to the embodiment.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Below, an information processing apparatus, an information processing method, and a form for implementing an information processing program (hereinafter referred to as an "embodiment") 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 this embodiment. Moreover, each embodiment can be combined as appropriate within the range that does not conflict with the processing contents. Further, in each of the embodiments below, the same parts are given the same reference numerals, and redundant explanations will be omitted.

[1. An example of information processing]
[1.1. Overview of information processing]
First, with reference to FIG. 1, an information processing method performed by an information processing apparatus according to an embodiment will be described. FIG. 1 is a diagram for explaining an information processing method performed by an information processing apparatus according to an embodiment.

The information processing device 1 executes information processing regarding a transaction object traded in an electronic commerce (EC) service. Here, the transaction object is the use of a product or service. Note that the transaction objects traded in the electronic commerce service include the transaction objects traded in various modes such as an electronic shopping mall (online mall), an online shopping site, an auction site, and a flea market site. FIG. 1 shows an example of information processing for transaction objects traded in an online shopping mall.

In FIG. 1, an example will be described in which the information processing device 1 functions as a search device that provides search results to a terminal device 2 used by a user U who inputs a search query. The search query is input by inputting a search keyword, and the search query including the search keyword is transmitted from the terminal device 2 to the information processing device 1 . Note that the input of the search query is not limited to input using the keyboard displayed on the terminal device 2, but may also be input by specifying keyword candidates displayed on the terminal device 2. In the following description, the search query will be described as including a search keyword, but it may also include a search image instead of or in addition to the search keyword. Further, although only one terminal device 2 is illustrated in FIG. 1, the information processing device 1 can process content including search results and the like according to search queries transmitted from each of the plurality of terminal devices 2. The information is provided to each of the terminal devices 2.

The information processing device 1 has, for example, a function as a search engine that executes search processing for transaction objects traded in an online shopping mall. For example, the information processing device 1 has a database (also referred to as a "transaction object database") in which transaction objects that are the targets of search processing using a search query are indexed and stored, and information on the transaction object database is stored. Execute search processing as the target. For example, information on the transaction target database is stored in the storage unit 11 (see FIG. 9).

In this way, although FIG. 1 describes a case where the information processing device 1 also functions as a search device, that is, the information processing device 1 and the search device are integrated, the information processing device 1 and the search device are separate entities. There may be. In this case, the information processing system 100 (see FIG. 9) includes a search device that provides a search service that executes search processing for a search query and provides search results. For example, the information processing device 1 transmits a search query including a search keyword input by the user U to the search device, receives search results from the search device, and provides content generated using the search results to the user U. Send to terminal device 2.

For example, when the external device 3 is a search device, the information processing device 1 transmits a search query including the search keyword input by the user U to the external device 3, receives the search results from the external device 3, and searches the The content generated using the results is transmitted to the terminal device 2 used by the user U. Note that the above system configuration is merely an example, and the information processing system 100 may have any device configuration as long as it can provide desired information to the user U who inputs the search keyword.

First, the information processing device 1 acquires user information that is information regarding the user U from the external device 3 (step S1). The external device 3 transmits user information to the information processing device 1. For example, the external device 3 transmits user information including attribute information of the user U to the information processing device 1. The attribute information includes various information such as information indicating demographic attributes such as age, gender, area of residence, and occupation, and information indicating psychographic attributes such as interests and lifestyle. Note that the attribute information is only an example, and the user information may include any information as long as it is related to the user U. For example, the user information may include a history of user U's actions such as actions on the Internet. For example, the user information may include the behavior history of the user U, such as the viewing history and purchase history of information regarding transaction targets in an electronic commerce service such as an electronic shopping mall.

Further, the information processing device 1 acquires information regarding the transaction object (also referred to as "transaction object information") from the external device 3 (step S2). For example, the information processing device 1 acquires transaction object information of a transaction object traded in an online shopping mall from the external device 3. For example, the information processing device 1 acquires, from the external device 3, transaction object information of a transaction object that is being sold (exhibited) at an online shopping mall. For example, the information processing device 1 acquires transaction object information of a transaction object from the external device 3 every predetermined period.

Here, the transaction object information includes various information regarding the transaction object. For example, the transaction object information includes various information used to provide information about the transaction object. For example, the transaction object information includes a sales source, a sales price, an image of a transaction object, a category, a title, a description, a payment method, a sales period, the number of items sold, and the like.

Further, for example, the transaction object information includes the sales history of the transaction object. For example, the transaction object information includes information such as the number of reservations, the number of orders, the number of sales, and the order amount (sales) of the transaction object. For example, the transaction object information includes the period of time that has passed since the date and time when the transaction object was sold, the number of views of information indicating the transaction object (PV (Page View) number), the number of reviews for the transaction object, the evaluation of the transaction object, etc. Contains information.

Further, the transaction object information may include information on external factors related to the transaction object. For example, the transaction object information may include information posted regarding the transaction object on an SNS (Social Networking Service). For example, the transaction target information may include posted information posted by user U on SNS. For example, the posted information may be text information posted by user U on Twitter (registered trademark), Facebook (registered trademark), Instagram (registered trademark), YouTube (registered trademark), etc., or image information such as images or videos. It may be. For example, the transaction object information may include information on the number of searches regarding the transaction object.

Further, the transaction object information may include information on internal factors related to the transaction object. For example, the transaction object information may include information on incentives for the transaction object. For example, the transaction object information may include information on incentives given to the user U for the transaction object. For example, the transaction object information may include information about a coupon targeted at the transaction object. For example, the transaction object information may include price reduction information regarding the transaction object. Note that the above is just an example, and the transaction object information may include any information as long as it is information related to the transaction object.

In the above example, the information processing device 1 performs the acquisition process separately in step S1 and step S2, but the information processing device 1 acquires user information and transaction object from the external device 3. The information may also be acquired at the same time.

The information processing device 1 also receives a search query input by the user U from the terminal device 2 (step S3). For example, when the user U inputs a search keyword, the terminal device 2 transmits a search query including the search keyword input by the user U to the information processing device 1. Thereby, the information processing device 1 acquires the search query input by the user U.

For example, when the user U inputs "sneakers" as a search keyword into the terminal device 2, the terminal device 2 transmits a search query including the search keyword "sneakers" input by the user U to the information processing device 1. . For example, the user U inputs "sneakers" as a search keyword into an input field such as a search box BX1 in FIG. 2, which will be described later.

Then, the information processing device 1 that has received the search query generates a search result corresponding to the search query by a search process using the search query as a process for providing information to the user U (step S4). For example, when the search keyword included in the search query is "sneakers", the information processing device 1 generates a search result corresponding to "sneakers" through a search process using "sneakers". In the following, a search query that includes "sneakers" as a search keyword may be referred to as a search query "sneakers."

The information processing device 1 uses information in the transaction object database to extract transaction object information corresponding to the search query "sneakers." For example, the information processing device 1 performs a search process on the transaction object database using the search query "sneakers" and extracts transaction object information corresponding to the search query "sneakers." For example, the information processing device 1 extracts transaction object information in which information such as a character string corresponding to the search query "sneakers" is included in the transaction object information.

Note that extraction of information corresponding to a search query is performed using a conventional technique, and any process may be used as long as the transaction target can be specified, and a detailed explanation will be omitted. Moreover, when a device (search device) other than the information processing device 1 performs the search process, the information processing device 1 transmits a search query to the search device and receives the search result of the search query from the search device. The information processing device 1 generates a search result for the search query using transaction target information extracted as information corresponding to the search query. For example, the information processing device 1 generates transaction target list information of the extracted transaction target information as a search result for a search query.

Further, the information processing device 1 estimates the intention (hereinafter, sometimes referred to as query intention) of the search query received in step S3 (step S5). For example, the information processing device 1 estimates the degree of relevance of the search query to each of the plurality of intention candidates as the intention of the search query. Intent candidates include, for example, the category of the transaction object, the brand of the transaction object, the usage scene of the transaction object, the specifications of the transaction object, the price range of the transaction object, or the usage group of the transaction object.

The information processing device 1 calculates a score indicating the degree of relevance of the search query to each of the plurality of intention candidates based on the search query, and treats these scores or information according to the score as the intention of the search query. In the following, an example will be mainly described in which the plurality of intention candidates are a transaction target category and a transaction target brand, but the intention candidates are not limited to categories or brands.

For example, the information processing device 1 uses an estimation model for each intention candidate to calculate a score indicating the degree of relevance of a search query to each intention candidate, and estimates these scores or information according to the score as the query intention. I can do it. The estimated model is a trained model generated by machine learning, inputs a search keyword included in a search query, and outputs a score indicating the degree of relevance of the search query to the intention candidate.

The estimation model for each intention candidate is generated by machine learning using a neural network such as a convolutional neural network or a regression neural network, but is not limited to this example. For example, the estimation model for each intention candidate may be generated using machine learning using a learning algorithm such as linear regression or logistic regression instead of using a neural network. Furthermore, instead of an estimation model for each intention candidate, the information processing device 1 uses one estimation model that receives a search keyword included in a search query as an input and outputs a score indicating the degree of relevance of the search query to a plurality of intention candidates. It can also be used.

Next, the information processing device 1 generates a plurality of ranking information according to the query intention estimated in step S5 (step S6). For example, the information processing device 1 determines the type and order of a plurality of ranking information to be provided to the user U based on the query intention, and provides the information to the user U based on the determined type and order of the ranking information. Generate multiple ranking information. The type of ranking information is defined by, for example, the perspective of ranking and the display format of ranking information.

The key to ranking is the viewpoint of the transaction target. For example, the perspective on a transaction object includes the category, brand, usage scene, specifications (product specifications and functions) to which the transaction object falls, issues that can be solved by the transaction object, and people who can solve the transaction object. It includes various angles (perspectives) that correspond to the subject of transaction, such as concerns.

Furthermore, the display format of the ranking information is the arrangement format of a plurality of ranking elements constituting the ranking information, and includes a list format (an example of a first display format), a grid format (an example of a second display format), and the like. The list format is a display format in which multiple ranking elements that constitute ranking information are arranged in a line, and the grid format is a display format in which multiple ranking elements are arranged in a matrix of n rows and m columns. . n and m are integers of 2 or more.

Note that the display format of the ranking information may include a display format in which a plurality of ranking elements are arranged in one line instead of or in addition to the second display format. Furthermore, the display format of the ranking information may be divided into a display format that includes a photo of the transaction target and a display format that does not include the transaction target photo.

For example, the information processing device 1 determines the types of ranking information to be provided to the user U based on the query intention, and sets a plurality of rankings in which the ranking information that is more relevant to the query intention is given higher priority. The ranking information is determined as the order of ranking information.

For example, the information processing device 1 calculates a score indicating the degree of relevance of the search query to a category that is a further classification of the category specified by the search query, and a degree of relevance of the search query to the brand to be traded in the category specified by the search query. Based on this, the types and order of the plurality of ranking information are determined.

The information processing device 1 generates a plurality of ranking information based on the determined type of the plurality of ranking information (for example, the cut and display format; hereinafter, may be referred to as the determined type) and the order of the plurality of ranking information. do.

The information processing device 1 extracts or determines transaction objects that are ranking factors from the perspective indicated by the determined type, and performs a process of calculating a score for each extracted or determined transaction object for each determined type. The information processing device 1 uses the calculated scores to rank the transaction objects for each determination type, and generates ranking information for each determination type in which a plurality of ranking elements are arranged in a display format indicated by the determination type. For example, the information processing device 1 generates ranking information by assigning higher ranks to ranking elements in descending order of scores, and arranging a plurality of ranking elements up to a preset upper rank in descending order.

For example, the information processing device 1 calculates, for each determination type, the score of the transaction object extracted or determined as a ranking element from the perspective indicated by the determination type, based on the transaction object information regarding the transaction object. The information processing device 1 calculates the score of the transaction object using a score function that is a function that receives transaction object information of the transaction object and outputs the score of the transaction object. The information processing device 1 calculates the score of the transaction target using a score function that outputs a larger value as multiple factors such as the number of orders, order amount, and number of views (PV number) of the transaction target increase. You can.

For example, the information processing device 1 generates a value (hereinafter referred to as a "partial score") obtained by multiplying each of multiple elements such as the number of orders to be traded, the order amount, the number of views (number of PV), and the weight (coefficient) of each element. ) is used to calculate the score of the transaction object. The information processing device 1 may calculate the sum of the partial scores of each of the plurality of elements of the transaction object as the score of the transaction object. The information processing device 1 may calculate the average of the partial scores of each of the plurality of elements of the transaction object as the score of the transaction object.

In addition, the information processing device 1 calculates the score of the transaction target using the aggregated values compiled for each predetermined period for each of multiple elements such as the number of orders, order amount, and number of views (PV number) of the transaction target. You may. The information processing device 1 may calculate the score of the transaction object using a total value calculated for each date for each of the plurality of elements of the transaction object. In this case, the information processing device 1 calculates the score of the transaction object using the period score, which is the value obtained by multiplying the aggregate value of the plurality of elements of the transaction object compiled for each predetermined period by the weight (coefficient) of each element. It may be calculated. The information processing device 1 may calculate the score of the transaction object 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. The information processing device 1 may calculate the score of the transaction object using a value obtained by multiplying the period score of each period by an attenuation coefficient whose value decreases as the period passes in the past.

Note that the above is just an example, and the information processing device 1 may use any information to calculate the score of the transaction object. The information processing device 1 may correct the score of the transaction object by using a coefficient based on the evaluation of the sales agency (store) that sells the transaction object to the calculated score of the transaction object. The information processing device 1 may correct the score of the transaction object by multiplying the calculated score of the transaction object by a coefficient based on the evaluation of the sales agency that sells the transaction object.

Then, the information processing device 1 generates content to be provided to the user U using the search result corresponding to the search query and the plurality of ranking information corresponding to the search query (step S7). In addition to the search results corresponding to the search query and the ranking information corresponding to the search query, the information processing device 1 includes a first tab for displaying the search results corresponding to the search query and ranking information corresponding to the search query. and a second tab for displaying the content.

Then, the information processing device 1 transmits content including search results corresponding to the search query and ranking information corresponding to the search query to the terminal device 2 of the user U who has input the search keyword included in the search query ( Step S8). When there is a plurality of ranking information corresponding to a search query, the information processing device 1 transmits a portion of the plurality of ranking information to the terminal device 2, and then selects the remaining rankings according to the display state of the ranking information on the terminal device 2. Although part or all of the information is transmitted to the terminal device 2, the present invention is not limited to this example. For example, the information processing device 1 can also transmit a plurality of pieces of ranking information to the terminal device 2 at once.

Here, an example of content provided to the terminal device 2 will be explained using FIG. 2. FIG. 2 is a diagram showing an example of content provided to the user U from the information processing device 1 according to the embodiment. In FIG. 2, content C provided from the information processing device 1 to the terminal device 2 and displayed on the terminal device 2 includes a search box BX1, a first tab TB1, a second tab TB2, and a second tab content C2. . In the search box BX1 shown in FIG. 2, "sneakers" is shown as a search keyword input by the user U. Content C also includes first tab content C1 (see FIG. 7), which will be described later.

The first tab TB1 shown in FIG. 2 is a GUI (Graphical User Interface) selected for displaying the first tab content C1 (see FIG. 7) to be described later on the terminal device 2, and the second tab TB1 shown in FIG. TB2 is a GUI selected to display the second tab content C2 on the terminal device 2. The first tab content C1 and the second tab content C2 are selectively displayed in the content C display area AR by operating the first tab TB1 or the second tab TB2.

In FIG. 2, when the first tab TB1 is selected by the user U, the first tab content C1 in which the search results for the search query "sneakers" are arranged is displayed in the display area AR. Further, when the second tab TB2 is selected by the user U, the second tab content C2 in which a plurality of ranking information of transaction objects corresponding to the search query "sneakers" is arranged is displayed in the display area AR.

FIG. 2 shows a state where the second tab TB2 is selected, and the terminal device 2 displays the second tab content C2 in which ranking information of the transaction object corresponding to the search query "sneakers" is arranged in the display area AR. Specifically, in the display area AR of content C, ranking information in which multiple transaction objects corresponding to the search query "sneakers" are arranged as ranking elements in descending order of scores is displayed as second tab content C2. Ru.

In this way, the information processing device 1 switches between the first tab content C1 and the second tab content C2 according to the user U's selection, and displays the content displayed in the display area AR on the user U's terminal device 2. provide. As a result, if the user U using the terminal device 2 receiving the content C wants to simply view the search results, the user U displays the first tab content C1 on the terminal device 2, and if the user U uses the terminal device 2 to view the ranking information. causes the terminal device 2 to display the second tab content C2. In the case of content C that displays information by switching in this way, the user U using the terminal device 2 can switch the display and display it on the terminal device 2 according to the content he/she wants to see, and check the content. can do. Therefore, the information processing device 1 can provide appropriate content.

[1.2. Details of various processing]
The details of various processes will be explained based on the information processing described above. Note that descriptions of points similar to those described above will be omitted as appropriate. Further, the various processes described below may be combined as appropriate. Note that the above is just an example, and the various types of processing may be combined in any manner as long as the combined processing is possible.

[1.2.1. Estimation of query intent]
The information processing device 1 can also estimate the query intention by dividing the score indicating the degree of relevance of the search query to each of the plurality of intention candidates into a plurality of ranges. For example, the information processing device 1 classifies scores indicating the degree of relevance of a search query to each category and brand into M levels. M is an integer of 2 or more.

FIG. 3 is a diagram illustrating an example of classification of scores indicating the degree of relevance of a search query to each of a category and a brand in the information processing device 1 according to the embodiment. In the example shown in FIG. 3, the information processing device 1 classifies the scores indicating the degree of relevance of the search query to each of the categories and brands into three levels: a first range, a second range, and a third range.

The first range is a range in which the score indicating the degree of association is less than the first threshold Th1, and indicates, for example, that there is no degree of association with the intention candidate. The second range is a range in which the score indicating the degree of relevance is from the first threshold Th1 to the second threshold Th2 (>Th1), for example, there is a degree of relevance to the intention candidate, but the intention candidate is narrowed down to one specific range. Indicates that it cannot be cut. The third range is a range in which the score indicating the degree of association exceeds the second threshold Th2, and indicates, for example, that the intention candidates are narrowed down to one specific range. The first threshold Th1 and the second threshold Th2 are, for example, Th1=0.1 and Th2=0.9, but are not limited to this example. Further, the first threshold Th1 and the second threshold Th2 may be set for each intention candidate.

In the example shown in FIG. 3, the first range is expressed as "no intention," the second range is expressed as "N strong," and the third range is expressed as "1 strong." Below, when the same description is given, There is. Furthermore, below, the degree of relevance of a search query to a brand may be referred to as category intent, and the degree of relevance of a search query to a brand may be referred to as brand intent.

Categories are defined, for example, in a tree-like hierarchy. In this case, the category intention is more than 1 if one of the categories at the bottom of the tree-like hierarchy can be narrowed down. In addition, the category intention is N-strong in a case where two or more bottom-layer categories (or a predetermined number of bottom-layer categories) can be narrowed down from a plurality of bottom-layer categories. The two or more lowest-level categories are, for example, lowest-level categories that are the same or similar to the higher-level categories in the tree-like hierarchy, but are not limited to this example. In addition, there is no category intention when one of two or more bottom-layer categories cannot be narrowed down from multiple bottom-layer categories that have the same category immediately above the tree-like hierarchy. . Note that the category intention may be, for example, a case where the category specified by the search query is a category higher than the lowest level.

For example, the category "sneakers" is a medium category that is a classification of the major category "shoes." The subcategories of the intermediate category "sneakers" include the category "ladies' sneakers," the category "men's sneakers," the category "ladies' slip-ons," the category "children's sneakers," and the like. Although women's slip-ons are not sneakers, they are frequently searched for or selected along with sneakers. The subcategory into which the category "sneakers" is classified is an example of the lowest category in the tree-like hierarchy.

In this case, if the category intent can be narrowed down to one subcategory (lowest level category), the category intent is "one strong", and two or more of the multiple subcategories (lowest level categories) If it can be narrowed down to (less than four categories), it is "N strong". Further, if it is not possible to narrow down to two or more categories (less than four categories) among the plurality of subcategories (lowest level categories), the category intention is "no intention".

In addition, for example, if the brand intention cannot be narrowed down to two or more brands (or a specified number of brands or less) out of the plurality of brands, it is "no intention", and two or more brands out of the plurality of brands ( If the search results can be narrowed down to brands of a specified number or less, the result is "N-strong", and if the search can be narrowed down to brands in one subcategory, the result is "1-strong".

Note that the score indicating the degree of relevance of the search query to each of the plurality of intention candidates may be divided into two stages instead of three stages, or four stages or more. The result of dividing the score indicating the degree of relevance of the search query to each of the plurality of intention candidates is an example of information indicating the degree of relevance of the search query to each of the plurality of intention candidates. Further, the information processing device 1 can also use scores indicating the degree of relevance of a search query to each of a plurality of intention candidates without classifying them. In this case, the score indicating the degree of relevance of the search query to each of the plurality of intention candidates is an example of information indicating the degree of relevance of the search query to each of the plurality of intention candidates.

[1.2.2. Determining the type and display format of ranking information]
The information processing device 1 determines the type and order of ranking information to be provided to the user U based on the query intention. The type of ranking information is defined by, for example, the perspective of ranking and the display format of ranking information, but is not limited to such examples.

In addition to the query intention, the information processing device 1 can also determine the type and order of ranking information to be provided to the user U using a search keyword included in the search query. In this case, the information processing device 1 determines whether the search keyword included in the search query specifies one lowest category. The information processing device 1 also determines whether the search keyword included in the search query specifies one brand.

In the following, when a search keyword specifies the lowest category, it may be written as "category specified," otherwise, it may be written as "no category specified." Furthermore, if the search keyword specifies one brand, it may be written as "brand specified," and otherwise, it may be written as "no brand specified." Further, the result of determining whether a category and brand are specified may be referred to as a "query specification determination result."

The information processing device 1 determines the type and order of ranking information to be provided to the user U based on the query intention and the query designation determination result. For example, the information processing device 1 determines the type and order of ranking information to be provided to the user U based on a combination of the query designation determination result, the category intention, and the brand intention.

The information processing device 1 has case classification determination information that associates the types and order of a plurality of ranking information to be provided to the user U for each combination of category designation, category intent, brand designation, and brand intent. . The information processing device 1 determines which case of the case classification determination information the combination of the determined category designation, category intent, brand designation, and brand intent corresponds to.

FIG. 4 is a diagram illustrating an example of case classification determination information included in the information processing apparatus according to the embodiment. In the case classification determination information shown in FIG. 4, case K1 is applied, for example, when there is a category designation or the category intention is one or more, and there is no brand designation and the brand intention is no intention. Further, case K2 is applied when there is a category designation or the category intention is over 1, and there is no brand designation and the brand intention is over N. Further, case K3 is applied when there is a category designation or the category intention is more than 1, and when there is a brand designation or the brand intention is more than 1.

Further, case K4 is applied when there is no category designation and the category intention is N strong, and there is no brand designation and the brand intention is no intention. Further, case K5 is applied when there is no category designation and the category intention is N strong, and there is no brand designation and the brand intent is N strong. Further, case K6 is applied when there is no category designation and the category intention is over N, and there is a brand designation or the brand intention is over 1.

Further, case K7 is applied when there is no category designation and the category intention is "no intention", and when there is no brand designation and the brand intention is "no intention". Further, case K8 is applied when there is no category designation and the category intention is "no intention", and when there is no brand designation and the brand intention is N strong. Further, case K9 is applied when there is no category designation and the category intention is "no intention", and there is a brand designation or the brand intention is more than 1.

The information processing device 1 determines the types and order of ranking information to be provided to the user U based on the information on the types and order of ranking information associated with the determined cases. The information processing device 1 has, for example, information for determining ranking information in which information on the type and order of ranking information is defined for each case, and provides information to the user U using such information for determining ranking information. Determine the type and order of the plurality of ranking information.

FIG. 5 is a diagram illustrating an example of ranking information determination information that the information processing device 1 according to the embodiment has. In the ranking information determining information shown in FIG. 5, the type and order of ranking information are defined for each of cases K1 to K9.

In case K1, "1 category comprehensive" and "list format" are defined as the types of the first ranking information (ranking cut and display format), and "query comprehensive" and "grid format" are defined as the types of the second ranking information. Format” is specified. "1 category overall" indicates that the ranking is a method for ranking multiple transaction objects included in one lowest category specified by category designation or category intent, without any brand limitation. "Query Comprehensive" indicates that it is a way of ranking multiple transaction targets narrowed down by a search using search keywords included in a search query, without category or brand limitations.

If the case determined based on the query intention and the query specification determination result is case K1, the information processing device 1 determines the type of the first ranking information as "1 category comprehensive" and "list format", and determines the type of the second ranking information as "1 category comprehensive" and "list format". The type of information is determined as "query general" and "grid format".

In case K2, "1 category overall" and "grid format" are defined as the first ranking information type (ranking cutoff and display format), and "multi-brand" and "grid format" are defined as the second ranking information type. "Query Comprehensive" and "Grid Format" are defined as the third ranking information type. "Multi-brand" indicates a group of criteria including a plurality of criteria for ranking, by brand, multiple transaction targets included in one lowest category specified by category designation or category intent.

Here, it is assumed that the case determined based on the query intention and the query designation determination result is case K2, and the brands are brands #1 to #3. In this case, the information processing device 1 determines the type of the first ranking information as "1 category overall" and "grid format", and determines the type of the second to fourth ranking information as "1 category brand #1". ” and “grid format,” “1 category brand #2” and “grid format,” and “1 category brand #3” and “grid format.”

The arrangement positions of "1 category brand #1", "1 category brand #2", and "1 category brand #3" are such that the brands with the highest scores are prioritized higher. Note that the brand score is calculated, for example, by the same calculation method as the score of the transaction object. For example, a brand's score is the sum of the scores of transaction objects included in the brand among multiple transaction objects included in the non-lowest category (for example, the category "sneakers") specified by the search keyword, or It may be the total value of the scores of a preset number of transaction objects that are included in the brand and have higher scores among the plurality of transaction objects included in the non-lowest category specified by . "1 category brand #P" (P is one of 1 to 3) is a transaction target of brand #P among multiple transaction targets included in one lowest category specified by category designation or category intent. Indicates that it is a way to rank.

Similarly, when the case determined based on the query intention and the query designation determination result is one of cases K3 to K9, the information processing device 1 determines the type and order of ranking information corresponding to the determined case. Determine using the table below.

In addition, in Figure 5, "1 category & 1 brand overall" means 1 category specified by brand designation or brand intent among multiple transaction targets included in one lowest category specified by category designation or category intent. Indicates that this is a way to rank multiple transaction targets of one brand. In addition, "one brand comprehensive" is one of the multiple transaction targets included in one non-lowest category (for example, the category "sneakers") specified by category specification, which is specified by brand specification or brand intention. Indicates that this is a way to rank the business targets of two brands.

"Multi-brand (1 category)" is, for example, a category that satisfies a specific condition among multiple categories specified by category designation or category intent (for example, a category with the highest category score), or a category that is randomly selected. Indicates that this is a group of perspectives that includes multiple perspectives for ranking transaction targets in the categories listed by brand. The category score is calculated, for example, by the same calculation method as the score of the transaction object. For example, the score of a category is the average value of the scores of multiple transaction targets included in the target category, or the score of a preset number of higher transaction targets among multiple transaction targets included in the target category. It may be the total value of .

Further, "multi-category" indicates, for example, a group of perspectives that includes a plurality of perspectives for ranking a plurality of transaction targets for each category below the category specified by the search keyword. For example, if the category specified by the search keyword is "sneakers," the multiple lower categories include women's sneakers, men's sneakers, women's slip-ons, and children's sneakers.

"One brand overall" is a way to rank multiple transaction targets of one brand specified by brand designation or brand intent among multiple transaction targets included in the category specified by the search keyword. show.

Note that the method of determining the type and order of ranking information by the information processing device 1 is not limited to the example described above. For example, the ranking information determining information is not limited to the example shown in FIG. 5. Further, the ranking information determining information may be provided for each attribute of the user U. In this case, the information processing device 1 determines the type and order of ranking information using the ranking information determination information corresponding to the attribute of the user U who input the search query.

Further, the above is just an example, and the information processing device 1 may determine the type and order of ranking information using various information as appropriate in addition to or in place of the query intention. In addition to or instead of the query intention, the information processing device 1 may determine the approach according to user attributes or user U's worries. Further, the information processing device 1 may determine the approach based on the search history. For example, in addition to or instead of the query intent, the information processing device 1 may determine the approach based on interest estimated from the search history.

Further, the ranking information determining information may be provided for each non-lowest category. In this case, if the category specified by the search keyword included in the search query is a non-lowest category, the information processing device 1 corresponds to the non-lowest category specified by the search keyword included in the search query. The type and order of ranking information are determined using the ranking information determining information.

[1.2.3. Generation of ranking information from the determined perspective]
The information processing device 1 ranks a plurality of transaction objects based on each of a plurality of different angles determined as described above, and generates a plurality of ranking information. FIG. 6 is a diagram illustrating an example of ranking of transaction targets from a plurality of perspectives in the information processing device 1 according to the embodiment. Note that FIG. 6 shows a state in which the image is divided into sections for the sake of explanation.

In addition, although FIG. 6 shows abstract character strings such as cut #1, cut #2, etc., these cuts are, for example, when the case determined by the information processing device 1 is case K1. This is information indicating specific aspects such as "one category comprehensive" and "query comprehensive."

For example, the information processing device 1 stores transaction objects that correspond to each of section #1, section #2, etc. among the transaction objects included in the search results of the search process using the search query (search result transaction objects). Determine (specify). For example, the information processing device 1 uses the transaction object information of the search result transaction objects to determine the transaction objects corresponding to each of cut #1, cut #2, and so on.

The information processing device 1 generates the ranking of the cut #1 by ranking the transaction objects corresponding to the cut #1 as the ranking elements of the cut #1. For example, the information processing device 1 calculates a score for a transaction target that corresponds to cut #1, which is a ranking element, and generates a ranking for cut #1 using the calculated score. Note that the calculation of the score of the transaction object is the same as that explained in FIG. 1, so the explanation will be omitted. For example, the information processing device 1 generates ranking information for cut #1 by ranking items in descending order of score.

List information TA1 shown in FIG. 6 is information that associates the ranking of the transaction object, the transaction object ID (Identifier) which is identification information for identifying the transaction object, and the score. In the list information TA1, the transaction object ranked "1st" is the transaction object with the transaction object ID "M34" and has a score of "0.94." The transaction object ranked "2nd" is the transaction object with the transaction object ID "M7" and has a score of "0.89." The transaction object ranked "3rd" is the transaction object with the transaction object ID "M1" and has a score of "0.85." The information processing device 1 generates ranking information for section #1 using information such as that shown in the list information TA1.

Similarly, the information processing device 1 generates the ranking of the cut #2 by ranking the transaction objects corresponding to the cut #2 as the ranking elements of the cut #2. For example, the information processing device 1 calculates a score for a transaction object that corresponds to cut #2, which is a ranking element, and generates ranking information for cut #2 using the calculated score.

List information TA2 shown in FIG. 6 is information that associates the ranking of the transaction object, the transaction object ID which is identification information for identifying the transaction object, and the score. In the list information TA2, the transaction object ranked "1st" is the transaction object with the transaction object ID "M162" and has a score of "0.84." The transaction object ranked "2nd" is the transaction object with the transaction object ID "M78" and has a score of "0.74." The transaction object ranked "3rd" is the transaction object with the transaction object ID "M18" and has a score of "0.73." The information processing device 1 generates ranking information for section #2 using information such as that shown in the list information TA2.

When there are cuts other than cuts #1 and #2, the information processing device 1 generates ranking information for cuts other than cuts #1 and #2 through similar processing.

[1.2.4. Example of content including search results and multiple ranking information]
Next, an example of the search results (first tab content) and ranking information (second tab content) included in the content C provided from the information processing device 1 to the terminal device 2 will be explained using FIG. 7. FIG. 7 is a diagram illustrating an example of search results and ranking information provided by the information processing device 1 according to the embodiment.

In FIG. 7, a first tab content C1 and a second tab content C2 included in content C generated by the information processing apparatus 1 when the search query "sneakers" is transmitted from the terminal device 2 to the information processing apparatus 1 are shown. ing. The user U can display the first tab content C1 in the display area AR by selecting the first tab TB1 (see FIG. 2), and can display the first tab content C1 in the display area AR by selecting the second tab TB2 (see FIG. 2). , the second tab content C2 can be displayed in the display area AR. The switching between the first tab content C1 and the second tab content C2 may be performed by either the information processing device 1 or the terminal device 2.

The information processing device 1 determines that the number of lower categories included in the category of the search query "sneakers" obtained from the terminal device 2 is less than or equal to the specified number, and the number of brands to be traded in the category of "sneakers" is less than or equal to the specified number. Therefore, it is determined that each of the category intention and the brand intention is N strong. Further, since the search query is "sneakers", the information processing device 1 determines that each of the category designation and the brand designation is unspecified. In this case, if the case classification determination information is in the state shown in FIG. 4, the information processing device 1 determines that the case corresponds to case K5.

In this case, if the ranking information determination information is in the state shown in FIG. )" and ranking information whose cut type is "query comprehensive" are generated as second tab content C2. The plural pieces of ranking information whose cut type is "multi-category" include ranking information for ladies' sneakers, ranking information for men's sneakers, ranking information for ladies' slip-ons, ranking information for children's sneakers, and the like. Each piece of ranking information whose cut type is "multi-brand (1 category)" is ranking information that ranks multiple transaction targets classified into one category of sneakers (for example, women's sneakers) by brand. be. The "query general" type is ranking information in which transaction targets searched for "sneakers" are ranked as ranking factors.

In the second tab content C2 shown in FIG. 7, ranking information for ladies' sneakers, ranking information for men's sneakers, etc. are arranged in order. In each ranking information shown in FIG. 7, the top six transaction objects are shown, and if the user U wants to know the ranking of the transaction objects below seventh place, the user U can use the character string " By selecting "See more," the second tab content C2 containing ranking information including the ranking of the transaction objects ranked 7th or lower is transmitted from the information processing device 1 to the terminal device 2, and the terminal device 2 A second tab content C2 is displayed that includes ranking information including rankings of transaction objects.

FIG. 8 is a diagram showing another example of ranking information provided by the information processing device 1 according to the embodiment. In the example shown in FIG. 8, when the search keyword included in the search query obtained from the terminal device 2 is "sneakers ladies", the second tab included in the content C sent from the information processing device 1 to the terminal device 2 It is a figure showing an example of content C2. If the search keyword included in the search query is "sneakers for women," the information processing device 1 determines that there is a category specification or that the category intent is one or more, and also that there is no brand specification and the brand intent is no intent. It is determined that If the case classification determination information is in the state shown in FIG. 4, the information processing device 1 determines that the case corresponds to case K1.

In this case, if the ranking information determination information is in the state shown in FIG. The second tab content C2 including the information is generated. The ranking information whose cut type is "1 category overall" is ranking information about ladies' sneakers. Ranking information whose cut type is "query general" is ranking information in which transaction targets searched for with the search keyword "sneakers for ladies" are ranked as ranking factors.

The display format of the ranking information whose cut type is "1 category overall" is a list format, and in the example shown in FIG. There is. In the list format, more information regarding the ranking target is added than in the grid format, the amount of information is large, and the number of ranking elements included is also large.

For example, compared to the grid format, the list format contains brand names, product names, colors, materials, and other information (e.g., user rating value, number of user ratings, etc.), and has a large amount of information. . Therefore, the user U can understand more clearly what the ranking elements are based on the information on the ranking elements included in the ranking information. In addition, the list format includes a larger number of ranking elements than the grid format, so you don't have to select "See more" less often to get ranking information starting from the next rank. User U's convenience can be improved. Note that even in the grid format, brand names and product names may be included.

In the example shown in Figure 5, the list format is set for highly specific query intents, such as when there is an intent candidate specification or when there is more than one intent candidate. The format is set. Therefore, user U can check ranking information in a list format by using specific search keywords, or check ranking information in grid format by using abstract search keywords. can do. Note that in the example shown in FIG. 5, the second and subsequent ranking information among the plurality of ranking information is in a grid format, but it is also possible to determine a part of the ranking information to be in a list format based on the query intention. In addition, the display format of ranking information for which the cut type is "query general" is a grid format, and in the example shown in Figure 8, the transaction target searched for the search keyword "sneakers ladies" is ranked up to 6th as a ranking factor. Although the ranking elements are arranged in a ranked manner, the number of ranking elements is not limited to six.

[1-3. summary〕
Through the various processes described above, the information processing device 1 can provide a ranking-related tab in a conspicuous position in the first view to suggest a search method of selecting from content that can be a deciding factor, such as "ranking." Therefore, the information processing device 1 can reduce the possibility that the user U who was unable to select a transaction object on his own from the search results will leave. Further, the information processing device 1 can encourage the user U (light user) whose usage time is less than a predetermined time to go around.

For example, a use case can be assumed in which the user U has a large number of options (transaction targets) corresponding to the search keyword input, has little prerequisite knowledge, and is unsure of what to buy. In this case, for example, the information processing device 1 provides rankings for each category, spec, etc. As a result, even with a search query with a broad intention, the user U can easily grasp the outline of the transaction object, deepen the intention, and naturally narrow down the options.

Moreover, the information processing device 1 can make it easier for the user U to visualize purchasing the transaction object by providing content in which the transaction object is organized for each aspect. Furthermore, by providing content organized by brand or the like, the information processing device 1 can make it easier for the user U to narrow down choices based on trends, popularity, etc.

Further, the information processing device 1 can provide the user U with a plurality of pieces of ranking information in different order of arrangement determined based on the query intention. Thereby, the information processing device 1 can more appropriately provide a plurality of ranking information corresponding to a search query. For example, the information processing device 1 can provide a plurality of ranking information more appropriately by providing a plurality of ranking information in a sorted order such that ranking information with a higher degree of relevance to a query intention is given higher priority. I can do it.

Further, the information processing device 1 can provide ranking information in a display format determined based on the query intention. Thereby, the information processing device 1 can more appropriately provide ranking information corresponding to the search query. For example, the information processing device 1 provides ranking information in a list format when the specificity of the query intention is high, and otherwise provides ranking information in a grid format. Thereby, the information processing device 1 can more appropriately provide ranking information corresponding to the search query.

Hereinafter, the configuration of the information processing system 100 including the information processing device 1, the terminal device 2, and the external device 3 that performs such processing will be described in detail.

[2. Configuration of information processing system 100]
As shown in FIG. 9, the information processing system 100 includes an information processing device 1, a terminal device 2, and an external device 3. The information processing device 1, the terminal device 2, and the external device 3 are connected via a network N so that they can communicate by wire or wirelessly. Note that the information processing system 100 shown in FIG. 9 may include a plurality of information processing apparatuses 1, a plurality of terminal devices 2, and a plurality of external devices 3.

The terminal device 2 according to the embodiment is an information processing device used by a user who accesses content such as a web page displayed on a browser or content for an application. For example, the terminal device 2 is a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), or the like. Note that the terminal device 2 is not limited to the above example, and may be, for example, a smart watch or a wearable device.

The external device 3 according to the embodiment is an information processing device that provides various information, and is realized by, for example, a server device or a cloud system. For example, the external device 3 provides user information as various information. In addition, as another example, the external device 3 may be used for Internet shopping, an electronic shopping mall, a flea market site, an auction site, a reservation site for travel or restaurants, a credit card contract site, or a financial product providing site. Provide information regarding transaction targets, etc.

The information processing device 1 according to the embodiment is an information processing device that can communicate with various devices via a predetermined network N such as the Internet, and is realized by, for example, a server device or a cloud system. For example, the information processing device 1 is communicably connected to various other devices via the network N.

[3. Configuration of information processing device 1]
An example of the functional configuration of the information processing device 1 described above will be described below. FIG. 9 is a diagram showing a configuration example of the information processing device 1 according to the embodiment. As shown in FIG. 9, the information processing device 1 includes a communication section 10, a storage section 11, and a processing section 12.

[3.1. Communication department 10]
The communication unit 10 is realized by, for example, a NIC (Network Interface Card). The communication unit 10 is connected to the network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from each of the terminal device 2 and the external device 3 via the network N.

[3.2. Storage unit 11]
The storage unit 11 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 11 also includes a user information storage unit 20, a transaction target information storage unit 21, a content storage unit 22, and a ranking information storage unit 23.

[3.2.1. User information storage unit 20]
The user information storage unit 20 stores various types of user information regarding the user U. FIG. 10 is a diagram showing an example of a user information table stored in the user information storage unit 20 according to the embodiment. In the example shown in FIG. 10, the user information table stored in the user information storage unit 20 has items such as "user ID" and "user information." For example, "user information" includes items such as "attribute information,""purchasehistory," and "browsing history."

“User ID” is an identifier that identifies user U. "Attribute information" is attribute information regarding the attributes of the user U associated with the "user ID." For example, the attribute information includes user U's age, gender, telephone number, address, etc. The above-mentioned attribute information is just one example, and various information other than age and gender may be used, such as information indicating demographic attributes such as occupation, and information indicating psychographic attributes such as interest, lifestyle, etc. May be included.

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

“Browsing history” is a history of contents being viewed by the user U associated with the “user ID”. For example, the "browsing history" may be a history of content displayed on the terminal device 2 of the user U. For example, the viewing history includes information regarding the content viewed (displayed) by the user U, the type of content, the number of times the content was displayed, the date and time the content was displayed, and the like.

For example, in FIG. 10, "U1" identified by the user ID has attribute information "CH1", purchase history "PH1", and display history "WA1". Note that in the example shown in Figure 10, attribute information, etc. is expressed using an abstract code such as "CH1," but attribute information, etc. can be expressed as a specific numerical value, specific character string, or various information. It may also be a file format that includes.

Note that the user information storage unit 20 is not limited to the above, and may store various information depending on the purpose. The user information storage unit 20 may store information indicating the number of times the information has been displayed for each transaction object, for example, the number of times the information has been viewed by user U, for each user.

[3.2.2. Transaction object information storage unit 21]
The transaction object information storage unit 21 stores various transaction object information regarding transaction objects. FIG. 11 is a diagram showing an example of a transaction object information table stored in the transaction object information storage unit 21 according to the embodiment. In the example shown in FIG. 11, the transaction object information table stored in the transaction object information storage unit 21 includes "transaction object ID", "transaction object", "transaction object information", "category", and "product specific information". Includes items such as. Note that in FIG. 11, "category" and "product specific information" are explained as separate items from "transaction target information," but category information and product information are not included in transaction target information. You can.

Further, although not shown, the transaction object information storage unit 21 stores, in addition to the category, information indicating the angle to which each transaction object falls. For example, the transaction object information storage unit 21 stores information indicating multiple aspects such as the category, brand, usage scene, specifications, problems that can be solved by the transaction object, and people's problems that can be solved by the transaction object to which each transaction object corresponds. is stored in association with each transaction object.

“Transaction object ID” is an identifier that identifies a transaction object. “Transaction object” indicates a transaction object associated with “transaction object ID”. The "transaction object information" is the transaction object information of the transaction object identified by the "transaction object ID."

"Category" is information regarding the category to which the transaction object identified by the "transaction object ID" corresponds. For example, when categories are defined in a hierarchical structure (for example, a tree-like hierarchical structure), "category" is information about the lowest category to which the transaction object corresponds, or from the top category to the lowest category to which the transaction object corresponds. Contains information for each category up to the category. "Product identification information" is information regarding the product to which the transaction object identified by the "transaction object ID" corresponds.

For example, in FIG. 11, the transaction object of "M1" identified by the transaction object ID is "MA1." In the example shown in Figure 11, the transaction object is expressed as an abstract code such as "MA1," but the transaction object is a concrete character string (such as a product name) indicating the product sold by each vendor. ).

Further, in FIG. 11, the transaction object information of "M1" identified by the transaction object ID is "MD1". In the example shown in FIG. 11, the transaction object information is expressed by an abstract code such as "MD1," but the transaction object information may be in a file format containing various information regarding the transaction object.

Further, in FIG. 11, "M1" identified by the transaction object ID has the category "CT1". In the example shown in FIG. 11, the category is expressed by an abstract code such as "CT1", but the category is information indicating the category of the transaction object.

Further, in FIG. 11, "M1" identified by the transaction object ID has product identification information "PD1". In the example shown in Figure 11, the product specification information is expressed as an abstract code such as "PD1", but if there is a product to which the transaction target corresponds, the product specification information can be used to identify the product. Information (for example, JAN code). Further, when there is no product corresponding to the transaction object, the product specifying information is information indicating that there is no product corresponding to the transaction object (for example, a flag indicating that there is no corresponding product).

Note that the transaction object information storage section 21 is not limited to the above, and may store various information depending on the purpose. For example, the transaction object information storage unit 21 may record information such as a score and the number of times of display corresponding to each transaction object.

[3.2.3. Content storage unit 22]
The content storage unit 22 stores information regarding content. FIG. 12 is a diagram showing an example of a content table stored in the content storage unit 22 according to the embodiment. In the example shown in FIG. 12, the content table stored in the content storage unit 22 has items such as "content ID" and "content."

"Content ID" is an identifier that identifies content. “Content” is information regarding the content associated with “Content ID”. Specifically, the content may indicate information regarding the contents of the content.

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

Further, the content may be content related to a route search site, a map providing site, a travel site, a restaurant introduction site, a web blog site, an SNS site, etc.

For example, in FIG. 12, the content of "C1" identified by the content ID is "CO1." Note that in the example shown in Figure 12, the content etc. is expressed by an abstract code such as "CO1", but the content etc. is a file containing specific numerical values, specific character strings, and various information. It may be a format, etc.

Note that the content storage section 22 is not limited to the above, and may store various information depending on the purpose.

[3.2.4. Ranking information storage unit 23]
The ranking information storage unit 23 stores various types of information used to generate rankings. For example, the ranking information storage unit 23 stores case classification determination information shown in FIG. 4, ranking information determination information shown in FIG. Stores score calculation information used to calculate various scores of the target.

The ranking standard information is, for example, information indicating a ranking standard for ranking items in descending order of scores. The score calculation information is, for example, information such as a score function used to calculate various scores of transaction targets.

Note that the ranking information storage section 23 is not limited to the above, and may store various information depending on the purpose.

[3.3. Processing unit 12]
The processing unit 12 is a controller that executes various programs (information processing) stored in a storage device inside the information processing device 1 by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). This is realized by executing a program (an example of a program) using RAM as a work area. Further, the processing unit 12 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 9, the processing unit 12 includes an acquisition unit 30, a reception unit 31, an estimation unit 32, a determination unit 33, a generation unit 34, and a provision unit 35, and includes information as described below. Achieve or execute a processing function or action. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 9, and may be any other configuration as long as it performs information processing to be described later.

[3.3.1. Acquisition unit 30]
The acquisition unit 30 acquires various information. The acquisition unit 30 acquires various information from the storage unit 11. The acquisition unit 30 acquires various information from the user information storage unit 20, transaction object information storage unit 21, content storage unit 22, ranking information storage unit 23, and the like.

The acquisition unit 30 receives various information from an external information processing device via the communication unit 10. The acquisition unit 30 receives various information from the terminal device 2 or the external device 3. For example, the acquisition unit 30 acquires user information regarding the user U from the external device 3. In FIG. 1, the acquisition unit 30 collects, as user information, user U's attribute information, purchase history on Internet shopping, online shopping malls, auction sites, flea market sites, etc., and content display history on the external device 3. Get from. The acquisition unit 30 then stores this user information in the user information storage unit 20. For example, the acquisition unit 30 acquires user information from the external device 3 every predetermined period, and updates the user information stored in the user information storage unit 20.

Further, the acquisition unit 30 acquires information regarding the transaction object from the external device 3. For example, the acquisition unit 30 acquires from the external device 3 information regarding a transaction object traded at an auction site or a flea market site. Then, the acquisition unit 30 stores information regarding the transaction target in the transaction target information storage unit 21. For example, the acquisition unit 30 acquires information regarding the transaction object from the external device 3 every predetermined period, and updates the information regarding the transaction object stored in the transaction object information storage section 21.

The acquisition unit 30 acquires transaction object information regarding a transaction object. The acquisition unit 30 acquires transaction object information including the sales history of the transaction object. The acquisition unit 30 acquires transaction target information including the number of orders for the transaction target. The acquisition unit 30 acquires transaction object information including the period of time that has passed since the date and time when the transaction object was sold. The acquisition unit 30 acquires transaction object information including the number of sales of the transaction object. The acquisition unit 30 acquires transaction object information including the number of times the information indicating the transaction object has been viewed.

The acquisition unit 30 acquires transaction object information including the number of reviews for the transaction object. The acquisition unit 30 acquires transaction object information including evaluations of the transaction object. The acquisition unit 30 acquires transaction object information including external factors related to the transaction object. The acquisition unit 30 acquires transaction object information including posts related to transaction objects on SNS. The acquisition unit 30 acquires transaction object information including the number of searches regarding the transaction object. The acquisition unit 30 acquires transaction object information including internal factors related to the transaction object. The acquisition unit 30 acquires transaction object information including incentives for the transaction object. The acquisition unit 30 acquires transaction object information including coupons for the transaction object. The acquisition unit 30 acquires transaction object information including price reductions regarding the transaction object.

The acquisition unit 30 acquires element information regarding a plurality of elements included in the transaction target information. The acquisition unit 30 acquires element information indicating trends of a plurality of elements included in transaction target information. The acquisition unit 30 acquires scores corresponding to each of the plurality of elements.

The acquisition unit 30 acquires element information indicating trends of a plurality of elements including the number of orders to be traded. The acquisition unit 30 acquires element information indicating trends of a plurality of elements including the number of views of information indicating a transaction object. The acquisition unit 30 acquires element information indicating trends of a plurality of elements including the number of reviews for a transaction object. The acquisition unit 30 acquires element information indicating trends of a plurality of elements including the number of reservations for a transaction target.

The acquisition unit 30 acquires element information indicating trends of a plurality of elements including external factors related to the transaction target. The acquisition unit 30 acquires element information indicating trends of a plurality of elements including posts related to transaction targets on the SNS. The acquisition unit 30 acquires element information indicating trends of a plurality of elements including the number of searches related to a transaction object. The acquisition unit 30 acquires element information indicating trends of a plurality of elements including internal factors related to the transaction object. The acquisition unit 30 acquires element information indicating trends of a plurality of elements including incentives for a transaction target. The acquisition unit 30 acquires element information indicating trends of a plurality of elements including coupons targeted at transaction targets. The acquisition unit 30 acquires element information indicating trends of a plurality of elements including price reduction regarding the transaction object.

The acquisition unit 30 also acquires information indicating the number of times the transaction object is displayed (the number of times the transaction object is viewed by the user U) from the terminal device 2 . For example, the acquisition unit 30 acquires the number of times content is displayed and the number of times each transaction object is displayed from the terminal device 2 . Further, the acquisition unit 30 acquires the content together with control information provided in advance to acquire the display count. Then, the acquisition unit 30 stores the number of times of display in the transaction target information storage unit 21.

[3.3.2. Reception Department 31]
The reception unit 31 receives various requests. The reception unit 31 receives various requests from external information processing devices. The reception unit 31 receives information indicating various requests from an external information processing device via the communication unit 10. For example, the receiving unit 31 receives a request from the terminal device 2 or the external device 3. The reception unit 31 receives a search query including a search keyword input by the user U from the terminal device 2 . For example, the reception unit 31 receives a search query including a search keyword input by the user U from the terminal device 2 as a request to provide content related to the search query. Further, the receiving unit 31 receives a query including parameters from the terminal device 2 as a request for providing content.

[3.3.3. Estimation unit 32]
The estimation unit 32 executes estimation processing to estimate various information. For example, the estimation unit 32 executes estimation processing based on various information acquired by the acquisition unit 30. The estimation unit 32 executes estimation processing based on various information stored in the storage unit 11. The estimation unit 32 executes estimation processing based on the search query received from the terminal device 2 and various information received from an external information processing device.

For example, the estimating unit 32 estimates a query intention that is the intention of the search query accepted by the receiving unit 31. For example, the estimation unit 32 estimates the degree of relevance of the search query to each of the plurality of intention candidates as the query intention. Intent candidates include, for example, the category of the transaction object, the brand of the transaction object, the usage scene of the transaction object, the specifications of the transaction object, the price range of the transaction object, or the usage group of the transaction object.

The estimation unit 32 calculates a score indicating the degree of relevance of the search query to each of the plurality of intention candidates based on the search keyword included in the search query, and treats these scores or information according to the score as the query intention. For example, the estimation unit 32 may use an estimation model for each intention candidate to calculate a score indicating the degree of relevance of the search query to each intention candidate, and estimate these scores or information according to the score as the query intention. can. The estimated model is a trained model generated by machine learning, inputs a search keyword included in a search query, and outputs a score indicating the degree of relevance of the search query to the intention candidate.

The estimation model for each intention candidate is generated by machine learning using a neural network such as a convolutional neural network or a regression neural network, but is not limited to this example. For example, the estimation model for each intention candidate may be generated using machine learning using a learning algorithm such as linear regression or logistic regression instead of using a neural network.

Further, the estimating unit 32 calculates the degree of relevance of the search query to each of the plurality of intention candidates using, for example, a table for each intention candidate in which each search keyword and a score indicating the degree of relevance are associated with each other. It can also be estimated as

In addition to the search keyword included in the search query, the estimation unit 32 estimates the query intention based on the user information of the search user who is the user U who input the search keyword included in the search query. You can also do it. For example, the estimating unit 32 calculates a score indicating the degree of relevance of the search query to each of the plurality of intention candidates based on the search keyword included in the search query and the user information of the search user, and calculates these scores. Treat as the intent of the search query.

In this case as well, the estimation unit 32 uses, for example, an estimation model for each intention candidate to calculate a score indicating the degree of relevance of the search query to each intention candidate, and uses these scores or information according to the score as the query intention. It can be estimated. The estimated model is a trained model generated by machine learning, which takes as input the search keyword included in the search query and the user information of the search user, and outputs a score indicating the degree of relevance of the search query to the intention candidate. .

Further, the estimating unit 32 estimates the query intention based on, for example, the search keywords included in the search queries previously accepted by the accepting unit 31 and the search keywords included in the search queries currently accepted by the accepting unit 31. It can also be estimated.

In this case as well, the estimation unit 32 uses, for example, an estimation model for each intention candidate to calculate a score indicating the degree of relevance of the search query to each intention candidate, and uses these scores or information according to the score as the query intention. It can be estimated. The estimated model is a trained model generated by machine learning, which inputs the search keywords included in the previous search query and the current search query, and outputs a score indicating the degree of relevance of the search query to the intention candidate. do. Note that instead of an estimation model for each intention candidate, one estimation model that outputs a score indicating the degree of relevance of a search query to a plurality of intention candidates may be used.

The estimation unit 32 can also estimate the query intention by dividing the score indicating the degree of relevance of the search query to each of the plurality of intention candidates into a plurality of ranges. For example, the estimating unit 32 classifies scores indicating the degree of relevance of the search query to each category and brand into M levels. M is an integer of 2 or more.

Furthermore, the estimation unit 32 can also determine the specificity of the query intention based on a score indicating the degree of relevance of the search query to each of the plurality of intention candidates. For example, the estimation unit 32 determines that the specificity of the query intention is relatively high when the intention candidate has an intention, and that the specificity of the query intention is relatively low when the intention candidate has no intention. . Further, the estimating unit 32 can also estimate that the specificity of the query intention is relatively high, for example, when the intention candidate is specified.

Note that instead of determining the specificity of the query intention in terms of high or low, the estimating unit 32 can also determine the specificity of the query intention numerically. For example, the estimating unit 32 may set the highest score among the scores indicating the degree of relevance of the search query to each of the plurality of intention candidates as the specificity of the query intention, and may set the specificity of the search query to each of the plurality of intention candidates. The average value of the scores indicating the degree of relevance can also be taken as the degree of specificity of the query intention.

[3.3.4. Determination section 33]
The determination unit 33 executes determination processing to determine various information. For example, the determining unit 33 determines the type and order of ranking information to be provided to the user U based on the query intention estimated by the estimating unit 32. The type of ranking information is defined by, for example, the perspective of ranking and the display format of ranking information. Note that the type of ranking information also defines the number of ranking candidates included in the ranking information.

For example, the determining unit 33 can determine the order in which ranking information having a higher degree of relevance to the query intention estimated by the estimating unit 32 has higher priority as the order in which the plurality of ranking information is arranged. For example, when the estimating unit 32 calculates scores indicating the degree of relevance of the search query to each of the plurality of intention candidates, the determining unit 33 determines the order of the plurality of ranking information based on these scores.

Further, when the estimation unit 32 classifies the scores indicating the degree of relevance of the search query to each of the plurality of intention candidates into a plurality of ranges, the determination unit 33 determines whether The order of ranking information is determined.

Further, when the estimation unit 32 classifies the score indicating the degree of relevance of the search query to each of the plurality of intention candidates into a plurality of ranges, the determination unit 33 determines whether or not the classification result by the estimation unit 32 and the presence or absence of category designation are determined. It is also possible to determine the order in which a plurality of pieces of ranking information are arranged based on the brand designation and the presence or absence of brand designation.

In this case, the determining unit 33 determines whether a category is specified and a brand is specified based on the search keyword included in the search query. Then, the determining unit 33 uses the case classification determination information (for example, see FIG. 4) and the ranking information determination information (for example, see FIG. 5) stored in the ranking information storage unit 23 and acquired by the acquiring unit 30. Based on the results of classification by the estimation unit 32, the order in which the plural pieces of ranking information are arranged can be determined.

The case classification determination information and ranking information determination information are based on user U's viewing history of ranking information and user U's viewing history (for example, click history, etc.) of ranking elements included in ranking information. , may be changed by the processing unit 12. Further, the determining unit 33 can also determine the type and order of ranking information using a decision model that inputs the query intention estimated by the estimating unit 32 and outputs the type and order of ranking information. Similar to the estimation model, the decision model is generated by machine learning using a neural network such as a convolutional neural network or a regression neural network, but is not limited to such examples.

Further, when each of the plurality of intention candidates is determined to have no intention, the determining unit 33 prioritizes ranking information regarding an intention candidate that is likely to be confirmed by the user U among the plurality of intention candidates. Determine the top sorting order. For example, when the category intention and the brand intention are both unintentional, the determining unit 33 determines the ranking order in which the category-specific ranking information is prioritized over the brand-specific ranking information. Note that ranking information regarding intention candidates that are likely to be confirmed by user U is, for example, ranking information that has a high possibility (e.g., viewing frequency) of ranking elements being viewed (e.g., clicked); but not limited to.

The determining unit 33 displays a plurality of display formats based on the query intention, including a first display format in which a plurality of ranking elements constituting ranking information are arranged in a line, and a second display format in which a plurality of ranking elements are arranged in a matrix. The display format of the ranking information is determined from among the display formats.

For example, the determining unit 33 determines the display format of the ranking information as the first display format when the specificity of the query intention is relatively high, and determines the display format of the ranking information when the specificity of the query intention is relatively low. is determined to be the second display format.

[3.3.5. Generation unit 34]
The generation unit 34 executes generation processing to generate various information. For example, the generation unit 34 executes generation processing based on various information acquired by the acquisition unit 30, various information stored in the storage unit 11, or various information received from an external information processing device.

The generation unit 34 generates the above-described content C including, for example, a first tab TB1, a second tab TB2, a search box BX1, a first tab content C1, and a second tab content C2.

For example, the generation unit 34 generates first tab content C1 in which search results corresponding to a search query including the search keyword input by the user U are arranged. The generation unit 34 generates first tab content C1 in which search results obtained by a search process using the search keyword input by the user U are arranged.

The search process is performed, for example, by extracting a transaction object from transaction object information that includes a search keyword. For example, when the search keyword included in the search query is "television", the generation unit 34 extracts transaction object information corresponding to the search query "television" from the transaction object information storage section 21 in the search process. Note that extraction of information corresponding to a search query is performed using a conventional technique, and any process may be used as long as the transaction target can be specified, and a detailed explanation will be omitted.

Moreover, when a device (search device) other than the information processing device 1 performs the search process, the acquisition unit 30 transmits a search query to the search device and receives the search result of the search query from the search device. The generation unit 34 generates a search result of the search query using the transaction object information extracted as information corresponding to the search query. For example, the generation unit 34 generates transaction target list information of the extracted transaction target information as a search result of the search query.

Further, the generation unit 34 executes generation processing based on the information determined by the determination unit 33. For example, the generation unit 34 executes generation processing based on the type and order of ranking information determined by the determination unit 33.

The generation unit 34 generates a plurality of pieces of ranking information based on the type and order of the ranking information determined by the determination unit 33 and transaction object information regarding the transaction object. For example, the generation unit 34 performs a process of calculating a score for each transaction object that is a ranking element from the perspective indicated by the type of ranking information determined by the determination unit 33 for each determination type.

For example, the generation unit 34 uses a function (score function) that receives as input the transaction object information of the transaction object that corresponds to the cut indicated by the type of ranking information determined by the determination section 33 and outputs the score of the transaction object. and calculate the score of the transaction target. For example, the generation unit 34 calculates the average value of the partial scores corresponding to each of the plurality of elements included in the transaction object information as the score of the transaction object. For example, the generation unit 34 calculates the score of the transaction object by adding up the partial scores corresponding to each of the plurality of elements included in the transaction object information.

The generation unit 34 uses the calculated scores to rank the transaction objects for each determination type, and generates ranking information for each determination type in which a plurality of transaction objects are arranged in the display format indicated by the determination type. For example, the generation unit 34 generates ranking information by ranking the transaction objects in descending order of their scores and arranging them in the display format determined by the determination unit 33 in descending order of the transaction objects having the highest scores. .

Then, the generation unit 34 generates second tab content C2 in which a plurality of pieces of ranking information are arranged in the order determined by the determination unit 33. For example, when the display format is a list format (an example of a first display format), the generation unit 34 generates a plurality of transaction information (rankings) compared to when the display format is a grid format (an example of a second display format). Set a large amount of information for each element.

The generation unit 34 generates a screen (content C) to be provided to the terminal device 2 by appropriately using various techniques related to image generation, image processing, and the like. For example, the generation unit 34 generates a screen (content C) to be provided to the terminal device 2 using various technologies such as Java (registered trademark). Note that the generation unit 34 may generate the screen (content C) to be provided to the terminal device 2 based on CSS, JavaScript (registered trademark), or HTML format. Further, for example, the generation unit 34 may generate the screen (content) in various formats such as JPEG (Joint Photographic Experts Group), GIF (Graphics Interchange Format), and PNG (Portable Network Graphics).

[3.3.6. Providing Department 35]
The providing unit 35 provides various information. The providing unit 35 transmits various information to an external information processing device via the communication unit 10. The providing unit 35 transmits various information to the terminal device 2 or the external device 3. The providing unit 35 transmits the content to the terminal device 2. The providing unit 35 transmits information regarding the transaction object to the terminal device 2.

For example, the providing unit 35 provides information generated by the generating unit 34. For example, the providing unit 35 provides content C generated by the generating unit 34. The content C is provided, for example, by transmitting the content C to the terminal device 2. Note that instead of the content C, the providing unit 35 can also independently provide the same content as the first tab content C1 and the same content as the second tab content C2.

The content transmitted from the providing unit 35 to the terminal device 2 is displayed on the terminal device 2. For example, the terminal device 2 can display content C provided by the providing unit 35, as shown in FIG.

[4. Processing procedure]
Next, the procedure of information processing executed by the information processing device 1 according to the embodiment will be described using FIG. 13. FIG. 13 is a flowchart illustrating an example of the flow of information processing performed by the information processing device 1.

As shown in FIG. 13, the processing unit 12 of the information processing device 1 receives a search query from the terminal device 2 via the network N and the communication unit 10 (step S10). Then, the processing unit 12 estimates the search intention based on the search query received in step S10 (step S11). For example, in the process of step S11, the processing unit 12 estimates the degree of relevance of the search query to each of the plurality of intention candidates as the intention of the search query.

Next, the processing unit 12 determines whether the intention candidate is specified (step S12). For example, the processing unit 12 determines whether or not a category is specified, and whether or not a brand is specified.

Next, the processing unit 12 determines the type and order of ranking information based on the query intention estimated in step S11 and the presence or absence of designation of the intention candidate determined in step S12 (step S13).

Next, the processing unit 12 generates content C including second tab content C2 in which the ranking information of the type determined in step S13 is arranged in the order determined in step S13 (step S14). Then, the processing unit 12 provides the content C generated in step S14 (step S15), and ends the process shown in FIG. 13.

[5. Modified example]
The information processing device 1 described above may be implemented in various different forms other than the above embodiment. Therefore, other embodiments of the information processing device 1 will be described below.

[5.1. User U]
In the above embodiment, the user U who is registered as a member of a predetermined service has been described as an example, but the present invention is not limited to the above example. For example, the user U may be any user U, such as a user U who is not registered as a member of a predetermined service.

[5.2. Transaction target]
Although the above embodiment has been described using an example of a transaction object traded in an online shopping mall, the present invention is not limited to the above example. For example, the transaction object may be any transaction object. For example, the transaction object may be a transaction object whose quantity is limited. Further, the transaction object may be a transaction object traded through Internet shopping, an auction site, a flea market site, or the like. Furthermore, the search target and ranking target based on the search query are not limited to transaction targets, and may be other than transaction targets.

[5.3. Providing information regarding the transaction object]
In the above embodiment, an example of information processing in which the information processing device 1 provides content to the terminal device 2 has been described, but the present invention is not limited to the above example. For example, an external server may provide content to the terminal device 2. In this case, the information processing device 1 may provide information regarding the transaction object to the external server.

For example, the external server provides content related to a portal site as an example of the content. In this case, the information processing device 1 may provide the external server with an image of the transaction object, information regarding the layout when arranged in the content, etc. as information regarding the transaction object.

[6. Hardware configuration]
The information processing device 1 or the terminal device 2 according to the embodiments described above is realized by, for example, a computer 80 having a configuration as shown in FIG. 14. The information processing device 1 will be described below as an example. FIG. 14 is a hardware configuration diagram showing an example of a computer 80 that implements the functions of the information processing device 1 according to the embodiment. The computer 80 includes a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, an HDD (Hard Disk Drive) 84, a communication interface (I/F) 85, an input/output interface (I/F) 86, and a media interface (I/F). )87.

The CPU 81 operates based on a program stored in the ROM 83 or HDD 84 and controls each part. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 is started, programs depending on the hardware of the computer 80, and the like.

The HDD 84 stores programs executed by the CPU 81 and data used by the programs. The communication interface 85 receives data from other devices via the network N (see FIG. 9) and sends it to the CPU 81, and sends data generated by the CPU 81 to the other devices via the network N.

The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse via an input/output interface 86. The CPU 81 obtains data from an input device via the input/output interface 86. Further, the CPU 81 outputs the generated data to an output device via the input/output interface 86.

Media interface 87 reads programs or data stored in recording medium 88 and provides them to CPU 81 via RAM 82. The CPU 81 loads this program from the recording medium 88 onto the RAM 82 via the media interface 87, and executes the loaded program. The recording medium 88 is, for example, an optical recording medium such as 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. etc.

For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 realizes the functions of the processing unit 12 by executing a program loaded onto the RAM 82. Furthermore, data in the storage unit 11 is stored in the HDD 84 . The CPU 81 of the computer 80 reads these programs from the recording medium 88 and executes them, but as another example, these programs may be acquired from another device via the network N.

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

Furthermore, each component of each device shown in the drawings is functionally conceptual, and does not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distributing and integrating each device is not limited to what is shown in the diagram, and all or part of the devices can be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured.

Furthermore, the embodiments and modifications described above can be combined as appropriate within a range that does not conflict with the processing contents. For example, part of the determination of the types and order of ranking information of the plurality of ranking information can be performed by the terminal device 2, and in this case, the information processing device 1 and a part of the terminal device 2 function as the information processing device.

[8. effect〕
As described above, the information processing device 1 according to the embodiment includes the receiving section 31, the estimating section 32, the determining section 33, and the providing section 35. The reception unit 31 receives a search query. The estimation unit 32 estimates the intention of the search query accepted by the reception unit 31. The determining unit 33 determines the order of the ranking information based on the intent of the search query estimated by the estimating unit 32. The providing unit 35 provides a plurality of pieces of ranking information arranged in the order determined by the determining unit 33. Thereby, the information processing device 1 can more appropriately provide a plurality of ranking information corresponding to a search query.

Further, the determining unit 33 determines, as the ranking order of the plurality of ranking information, the ranking information having a higher degree of relevance to the intent of the search query estimated by the estimating unit 32 is given higher priority. Thereby, the information processing device 1 can more appropriately provide a plurality of ranking information corresponding to a search query.

Furthermore, the estimation unit 32 estimates the degree of relevance of the search query to each of the plurality of intention candidates as the intention of the search query. The determining unit 33 determines the order in which the plurality of ranking information items are arranged based on the degree of relevance of the search query to each of the plurality of intention candidates. Thereby, the information processing device 1 can more accurately estimate the intention of the search query, and can more appropriately provide a plurality of ranking information corresponding to the search query.

Further, each of the plurality of ranking information includes information on two or more transaction objects among the plurality of transaction objects according to the intention of the search query. The plurality of intention candidates includes a transaction target category and a transaction target brand. Thereby, the information processing device 1 can more accurately estimate the intention of the search query for the transaction object, and can more appropriately provide a plurality of ranking information corresponding to the search query.

Further, the determining unit 33 determines the display format of each of the plurality of ranking information based on the intent of the search query estimated by the estimating unit 32. Thereby, the information processing device 1 can more appropriately provide a plurality of ranking information corresponding to a search query.

Further, the providing unit 35 provides a plurality of ranking information each including information on two or more transaction targets traded in electronic commerce. Thereby, the information processing device 1 can more appropriately provide a plurality of ranking information in which transaction objects traded in electronic commerce are ranked.

Further, the providing unit 35 transmits ranking information to the terminal device 2 of the user U. Thereby, the information processing device 1 can more appropriately provide the user U with a plurality of ranking information corresponding to the search query.

The providing unit 35 also includes a first tab TB1 that causes the terminal device 2 to display search results corresponding to the search query, and a second tab TB2 that causes the terminal device 2 to display a plurality of ranking information that corresponds to the search query. Provide content C. Thereby, the information processing device 1 can more appropriately provide the user U with a plurality of ranking information corresponding to the search query according to the user U's selection.

Although the embodiments of the present application have been described above in detail based on the drawings, this is merely an example, and various modifications and improvements can be made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. It is possible to implement the invention in other forms.

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

1 Information processing device 2 Terminal device 3 External device 10 Communication unit 11 Storage unit 12 Processing unit 20 User information storage unit 21 Transaction target information storage unit 22 Content storage unit 23 Ranking information storage unit 30 Acquisition unit 31 Reception unit 32 Estimation unit 33 determining unit 34 generating unit 35 providing unit 100 information processing system

Claims (8)

A reception department that accepts search queries,
an estimation unit that estimates the intention of the search query received by the reception unit;
a determining unit that determines the order of a plurality of ranking information based on the intent of the search query estimated by the estimating unit;
a providing unit that provides the plurality of ranking information arranged in the order determined by the determining unit,
The determining unit is
An information processing apparatus characterized in that a display format of each of the plurality of ranking information is determined based on the intention of the search query estimated by the estimation unit. The estimation unit is
Estimating the degree of relevance of the search query to each of a plurality of intention candidates as the intention of the search query,
The determining unit is
The information processing apparatus according to claim 1 , wherein the arrangement order of the plurality of ranking information is determined based on the degree of relevance of the search query to each of the plurality of intention candidates. The determining unit is
Claim 1 or 2 , characterized in that the ranking information having a higher degree of relevance to the intent of the search query estimated by the estimating unit is given higher priority and a higher ranking is determined as the ranking order of the plurality of ranking information. The information processing device described in . The provision department is
The information processing device according to any one of claims 1 to 3 , wherein the information processing device provides the plurality of ranking information each including information on two or more transaction targets traded in electronic commerce. The provision department is
The information processing device according to any one of claims 1 to 4 , wherein the plurality of ranking information is transmitted to a terminal device used by a user. The provision department is
providing content including a first tab that causes the terminal device to display search results corresponding to the search query; and a second tab that causes the terminal device to display the plurality of ranking information that corresponds to the search query. The information processing device according to claim 5 . An information processing method performed by a computer, the method comprising:
A reception process for accepting search queries;
an estimation step of estimating the intention of the search query accepted by the reception step;
a determining step of determining the order of a plurality of ranking information based on the intent of the search query estimated by the estimating step;
a providing step of providing the plurality of ranking information arranged in the order determined by the determining step,
The determining step includes:
An information processing method, comprising: determining a display format for each of the plurality of ranking information based on the intent of the search query estimated by the estimation step. A reception procedure for accepting a search query,
an estimation step for estimating the intent of the search query accepted by the reception step;
a determining step of determining the order of a plurality of ranking information based on the intent of the search query estimated by the estimating step;
causing a computer to perform a providing step of providing the plurality of ranking information arranged in the order determined by the determining step;
The determination procedure is
An information processing program characterized in that a display format of each of the plurality of ranking information is determined based on the intent of the search query estimated by the estimation procedure.

Images