JP6865045B2 - Search device, search method and search program - Google Patents

Description

The present invention relates to a search device, a search method, and a search program.

In recent years, with the rapid spread of the Internet, shopping services, auction services, and the like have been actively provided via websites and applications. In such websites and applications, so-called recommendations are made to provide products according to the interests of users who have accessed the service as recommended products.

As a technique related to such a recommendation, there is known a technique of delivering and notifying the user of auction recommendation information based on the history of the user's auction transaction.

Japanese Unexamined Patent Publication No. 2010-21160

However, in the above-mentioned conventional technique, it is not always possible to make a recommendation according to various behavior histories of the user. Specifically, the above-mentioned prior art distributes auction recommendation information based on the auction transaction history, but the behavior of the user on the network is more diverse. For example, a user takes various actions such as browsing a website, searching, and purchasing via a network. For this reason, in the past, products recommended by users on a certain website may not reflect various user behaviors other than the website.

The present application has been made in view of the above, and an object of the present application is to provide a search device, a search method, and a search program capable of making recommendations according to various behavior histories of users.

The search device according to the present application corresponds to the user from an acquisition unit that acquires an action history for each service used by the user and an action history acquired by the acquisition unit, which is an action history on the user's network. An extraction unit that extracts the query to be executed, and a search unit that searches for information content recommended to the user by using query information that is information obtained by giving weights for each service to the query extracted by the extraction unit. It is characterized by having.

According to one aspect of the embodiment, there is an effect that the recommendation can be made according to various behavior histories of the user.

FIG. 1 is a diagram showing an example of a search process according to an embodiment. FIG. 2 is a diagram showing a configuration example of a search system according to an embodiment. FIG. 3 is a diagram showing a configuration example of the search device according to the embodiment. FIG. 4 is a diagram showing an example of the action history storage unit according to the embodiment. FIG. 5 is a diagram showing an example of a service table according to the embodiment. FIG. 6 is a diagram showing an example of a query table according to the embodiment. FIG. 7 is a diagram showing an example of the recommendation information storage unit according to the embodiment. FIG. 8 is a diagram showing a configuration example of the web server according to the embodiment. FIG. 9 is a flowchart (1) showing a processing procedure according to the embodiment. FIG. 10 is a flowchart (2) showing a processing procedure according to the embodiment. FIG. 11 is a flowchart (3) showing a processing procedure according to the embodiment. FIG. 12 is a diagram showing an example of a query table according to a modified example. FIG. 13 is a hardware configuration diagram showing an example of a computer that realizes the function of the search device.

Hereinafter, a search device, a search method, and a mode for carrying out the search program (hereinafter, referred to as “the embodiment”) according to the present application will be described in detail with reference to the drawings. The search device, search method, and search program according to the present application are not limited by this embodiment. In addition, each embodiment can be appropriately combined as long as the processing contents do not contradict each other. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[1. An example of search processing]
First, an example of the search process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of a search process according to an embodiment. FIG. 1 shows an example in which the search device 100 according to the present application performs a process of searching for information content according to a user who has accessed a predetermined service page. In the embodiment, a web page will be described as an example of the service page. Further, as an example of the information content, a predetermined product recommendation (hereinafter, simply referred to as “recommendation”) will be described as an example.

The search device 100 shown in FIG. 1 is a server device that holds information about recommendations. The search device 100 searches for a recommendation suitable for the user from a database (in the embodiment, the recommendation information storage unit 125 (see FIG. 3)) that stores the recommendation when the user accesses a predetermined web page. .. Then, the search device 100 delivers the searched recommendation to the user.

The user terminal 10 shown in FIG. 1 is an information processing terminal used by the user U01. For example, the user terminal 10 is a smartphone or tablet type terminal. The user terminal 10 accesses the web server 30 (see FIG. 2) according to the operation by the user U01, and acquires the web page provided by the web server 30. The user U01 uses various services provided as a web page via the user terminal 10. In this specification, the user terminal 10 and the user U01 using the user terminal 10 may be equated with each other. For example, "sending a web page to user U01" may actually mean "sending a web page to a user terminal 10 used by user U01".

When the search device 100 includes a frame for displaying recommendations (hereinafter referred to as "recommendation frame") on the web page acquired by the user terminal 10, the search device 100 distributes the recommendation for displaying in the frame to the user terminal 10. To do. The user U01, for example, clicks on a recommendation to acquire product information or purchases a recommended product. As a result, the person who provides the recommendation (for example, the business operator who bids on the recommendation or the service business operator who sells the recommended product) benefits. That is, it is desirable that the search device 100 delivers as a recommendation an object of interest to the user U01, such as the user U01 clicking or purchasing a recommendation.

Generally, the query information possessed by the user U01 is used for the distribution of such recommendations. The query information is information generated based on the behavior history of the user U01 on the network, the attribute information of the user U01, and the like, and is information including a plurality of queries used to search for recommendations for the user U01. ..

For example, it is assumed that the user U01 purchases drinking water at a predetermined shopping site. In this case, words such as the name of the purchased drinking water, the product category such as "drinking water", and the name of the shopping site are added to the query information of the user U01. Specifically, the title and description given to the product are morphologically analyzed, and the decomposed words are extracted as a query and added to the query information of the user U01. Then, when an opportunity to search for a recommendation occurs for the user U01, the recommendation is searched using the query information.

The queries that make up the query information are ranked according to the behavior of the user U01. For example, if the user U01 takes an action of purchasing the same drinking water multiple times, the query related to the drinking water is ranked higher by that amount. Specifically, the queries are ranked according to the tf value (Term Frequency) of the queries extracted according to the action history of the user U01. In other words, the queries in the query information are ranked according to the number of times they appear in the behavior of user U01.

Then, the device for searching for the recommendation preferentially uses the higher-level query of the user U01 to search for the recommendation. For example, the device for searching the recommendation searches the query to be delivered to the user U01 by inputting the top 20 queries included in the query information corresponding to the user U01 into the search engine. As a result, recommendations according to the past actions of user U01 are searched, and the searched recommendations are delivered to user U01. The query information may include words including user attribute information (gender and age).

In this way, by delivering the recommendation according to the past behavior of the user U01, for example, the user U01 can increase the chances of selecting (clicking) the recommendation or purchasing the recommended product. Is expected to be possible. That is, if the query information used to search for recommendations is query information that accurately reflects the behavior of user U01, in other words, the interests of user U01, it is possible to search for recommendations that are more appealing to user U01. is assumed.

However, in the conventional method as described above, there is a possibility that the query information that accurately indicates the behavior of the user U01 may not be extracted. For example, the user U01 is assumed to take various actions such as browsing a website, searching, and purchasing through the network, like most users who use the network. Here, the user who uses the network is a concept including a website such as a search service (in the embodiment, a search site that provides the search service) rather than taking an action related to a certain target (for example, a product). It tends to be easy to take actions related to frequently used services such as shopping services. That is, a user who uses the network may access the network in order to use a certain service, instead of using the service in order to obtain information about a certain object.

Here, when the query is extracted according to the behavior of the user U01 and the query is ranked based on the tf value to generate the query information, the information about the service used by the user U01 is lost. That is, the query information in which the queries are extracted according to the behavior of the user U01 and the queries are ranked according to the number of times the queries are extracted does not reflect the information about the service used by the user, so that the user's interests can be accurately expressed. May not be. Therefore, for example, there is a possibility that a recommendation of a product handled by a service that the user does not use often is delivered to the user, or a recommendation different from the tendency of the user's interest is delivered. As a result, there is a risk that the appealing effect of the recommendation may be reduced, such as the recommendation not being clicked or the probability of reaching conversion being reduced.

Therefore, the search device 100 according to the embodiment acquires the action history for each service used by the user U01, and gives a weight for each service used by the user U01 to the query extracted from those actions. Then, the search device 100 searches for the recommendation to be delivered to the user U01 by using the query information which is the information in which the weight for each service is added to the query. By such a method, the search device 100 can accurately search for a recommendation according to the behavior of the user U01. Hereinafter, an example of the search process performed by the search device 100 will be described along the flow with reference to FIG.

In FIG. 1, the user U01 shall use various services on a daily basis via the user terminal 10 (step S11). In the embodiment, the user U01 uses, for example, the search service A01, the shopping service A02, the auction service A03, the news service A04, and the like.

Here, the search device 100 acquires the action history related to the service used by the user U01 (step S12). For example, the search device 100 acquires an action history in which the user U01 uses the service via each web server 30 accessed by the user terminal 10.

Specifically, the search device 100 uses the search service A01 to perform a search (for example, the number of searches in a predetermined period), the type and number of queries sent to the search service A01, and the search service A01. Get the number of accesses to. In addition, the search device 100 acquires the frequency with which the user U01 uses the shopping service A02, information on the browsed product and the purchased product, the number of purchases, the usage amount, and the like. In addition, the search device 100 acquires the usage amount and the like, such as the frequency of using the auction service A03, the number of bids or successful bids, and information on the bid or successful bid product. In addition, the search device 100 acquires the frequency of using the news service A04, the number of articles browsed, the title of the browsed article, the keywords included in the browsed article, the browsing time, and the like.

The action history acquired by the search device 100 mentioned above is an example, and the search device 100 may acquire all the information stored as the action history (log) of the user U01 for each service.

Then, the search device 100 extracts a query based on the action history of various services (step S13). For example, the search device 100 extracts a word specified from the action history used by the user U01 as a query.

The search device 100 extracts, for example, a search query sent by the user U01 to the search service A01 as a query. Further, the search device 100 extracts a query from the information about the page clicked by the user U01 (that is, the link destination of the search result) with respect to the search result obtained by the user U01 from the search service A01. For example, the search device 100 morphologically analyzes the words included in the linked page and extracts the obtained words as a query. Further, the search device 100 extracts the name of the product selected by the user U01 in the shopping service A02 and the auction service A03 and the word included in the title of the product as a query. Further, the search device 100 extracts a word included in the title of the article selected by the user U01 in the news service A04 as a query.

Specifically, when the user U01 has transmitted the search query "water" to the search service A01, the search device 100 extracts "water" as the query. Further, when the user U01 is browsing the product "television" on the shopping service A02, the search device 100 extracts the "television" as a query. In this case, the search device 100 may extract "beverages", which is a category including the word "water", "home appliances", which is a category including the word "television", and the like as queries. ..

The query extracted by the search device 100 mentioned above is an example, and the search device 100 may extract various words extracted from the action history of the user U01 as queries. In addition, the search device 100 may utilize various known methods for extracting queries. Further, the search device 100 extracts words that can be a query by using, for example, tf-idf (Term Frequency, Inverse Document Frequency) in a document to be extracted (product title, article title, etc.). You may do so. For example, the search device 100 calculates a value such as tf-idf for a word that has been morphologically analyzed in a predetermined document, and extracts the words in order from the top of the calculated value. Thereby, the search device 100 can exclude, for example, commonly used words from the extracted query.

Subsequently, the search device 100 calculates the weight for each service used by the user U01 and generates the query information Q01 of the user U01 (step S14). For example, the search device 100 calculates the weight for each service related to the user U01 according to the frequency of use of the service of the user U01. Specifically, the search device 100 calculates the weight for each service based on the frequency with which the user U01 accesses the service.

Further, as will be described in detail later, the search device 100 may calculate the weight for each service based on the reaction to the recommendation delivered to the user U01. For example, the recommendation delivered by the search device 100 may be a product handled by the shopping service A02 or a product handled by the auction service A03. Then, when the user U01 clicks on the delivered recommendation or when the user U01 converts to the recommendation, the search device 100 identifies the service corresponding to the recommendation. Then, the search device 100 calculates the weight so that the weight of the service corresponding to the recommendation is not heavy for the user U01.

For example, it is assumed that the search device 100 calculates that the service having the heaviest weight for the user U01 is the search service A01. In this case, the search device 100 calculates the score for each query by multiplying, for example, the frequency of queries extracted from the behavior history of the user U01 (the number of times extracted) by the weight for each service.

A specific example will be described. For example, the query "water" is extracted "10" times from the behavior history of the search service A01 of the user U01, the query "water" is extracted "10" times from the behavior history of the shopping service A02, and the behavior history of the auction service A03. It is assumed that the query "water" is extracted "10" times from the above, and the query "water" is extracted "10" times from the action history of the news service A04. The weight of the search service A01 in the user U01 is "6", the weight of the shopping service A02 is "3", the weight of the auction service A03 is "1", and the weight of the news service A04 is "1". Suppose that

At this time, the search device 100 according to the embodiment does not simply calculate "10 + 10 + 10 + 10 = 40" as the score of "water" by using the number of occurrences (number of extractions), but multiplies the weight of each service. It is calculated as "10 * 6 + 10 * 3 + 10 * 1 + 10 * 1 = 110". In this way, the search device 100 calculates the score in consideration of not only the number of times the query is extracted but also the weight of the service of the user U01. As a result, the search device 100 can calculate the query score according to the service usage frequency of the user U01 and the interests corresponding to the service, so that the query information Q01 showing the characteristics of the behavior of the user U01 can be calculated. Can be generated. In this way, the search device 100 generates the query information Q01 corresponding to the user U01, including the plurality of queries to which the scores are given.

Although the calculation method is simplified for the sake of explanation above, the search device 100 may actually calculate the score by using various known methods such as normalization.

The search device 100 associates the generated query information Q01 with the user U01 and stores it in a predetermined storage unit (step S15). The process described so far is the query extraction process (extraction phase) for the user U01 in the search device 100.

Subsequently, a process (search phase) in which the search device 100 searches for recommendations to be delivered to the user U01 based on the query information Q01 will be described.

As shown in FIG. 1, the user terminal 10 accesses a predetermined service page (for example, a web page) according to the operation of the user U01 (step S21). It is assumed that the service page accessed by the user terminal 10 includes three recommendation frames. In this case, the user terminal 10 transmits a recommendation distribution request to the search device 100 in accordance with an instruction (script) included in the service page.

The search device 100 that has received the delivery request searches for the recommendation corresponding to the user U01 based on the query information Q01 stored in advance (step S22). As described above, a predetermined score calculated based on the weight for each service is given to the query included in the query information Q01. Then, in the query information Q01, it is assumed that each query is ranked based on the score.

Then, the search device 100 matches the query information Q01 with the plurality of recommendations to be held. For example, the recommendation held by the search device 100 is tagged with a corresponding query in advance, and the search device 100 matches the query information Q01 with the query tagged with the recommendation.

For example, it is assumed that the query information Q01 includes "water", "beverages", "television", "home appliances", etc. as queries having a relatively high score. Further, for example, it is assumed that the recommendation P01 and the recommendation P02 include "water" and "beverage" as the tagged query. Further, it is assumed that the recommendation P03 includes "television" and "home appliances" as tagged queries. Then, the search device 100 matches the query included in the query information Q01 with the query tagged with each recommendation, and searches for any of the recommendations. A known inverted index method or the like may be appropriately applied to such a search process. That is, the search device 100 may adopt a method such as multiplying the score given to the query by the score of the query tagged to the recommendation and preferentially selecting the recommendation having the highest score.

It is assumed that the search device 100 has searched for the recommendation P01, the recommendation P02, and the recommendation P03 as the recommendations to be delivered to the user U01 by the above search process. In this case, the search device 100 delivers the searched recommendation P01, recommendation P02, and recommendation P03 to the user terminal 10 (step S23).

As described with reference to FIG. 1, the search device 100 according to the embodiment acquires the action history of the user U01 on the network for each service used by the user U01. Then, the search device 100 extracts the query corresponding to the user U01 from the acquired action history. Further, the search device 100 searches for the information content (that is, the recommendation) recommended to the user U01 by using the query information which is the information obtained by giving the extracted query a weight for each service.

In this way, the search device 100 can search for a recommendation that more reflects the behavior of the user U01 by performing a search using a query weighted for each service used by the user U01. Therefore, according to the search device 100, it is possible to search for recommendations having a so-called highly appealing effect, which are easily clicked by the user or have a high possibility of leading to conversion. That is, the search device 100 can make recommendations according to various behavior histories of the user U01 according to the behavior of the user U01 who uses the network.

Note that FIG. 1 shows an example in which the search device 100 acquires the action history for each service used by the user U01 in step S11. In this case, the search device 100 may acquire user behavior information by using a notification function realized by a web beacon or the like.

That is, a function for notifying information about a user (hereinafter referred to as "user information") realized by a web beacon or the like may be embedded in a web page on which a recommendation is displayed. For example, a web beacon has a function of allowing a user terminal 10 that has accessed a web page to access a transparent image or a very small image (sometimes referred to as "clear GIF") stored in the search device 100. As a result, the search device 100 can receive and acquire user information from the user terminal 10. For example, the search device 100 uses a function realized by a web beacon to indicate that the user U01 clicks on a recommendation, makes a purchasing action, or makes a recommendation link destination page (landing page) on the user terminal 10. You can receive information such as browsing.

Hereinafter, the configuration of the search device 100 that performs the processing described with reference to FIG. 1 and the search system 1 including the search device 100 will be described in detail.

[2. Search system configuration]
The configuration of the search system 1 including the search device 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of the search system 1 according to the embodiment. As illustrated in FIG. 2, the search system 1 according to the embodiment includes a user terminal 10, a web server 30, and a search device 100. These various devices are communicably connected via a network N (for example, the Internet) by wire or wirelessly. The search system 1 shown in FIG. 2 may include a plurality of user terminals 10 and a plurality of web servers 30.

The user terminal 10 is, for example, an information processing device such as a smartphone, a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), or a wearable device (Wearable Device). Is. The user terminal 10 acquires a web page from the website provided by the web server 30 by accessing the web server 30 according to the operation by the user. Then, the user terminal 10 displays the acquired web page on a display device (for example, a liquid crystal display).

The web server 30 is a server device that provides various services when accessed from the user terminal 10. In the embodiment, the web server 30 shall provide various websites as a service. For example, the web server 30 relates to a web search site, a shopping site, an auction site, a news site, a weather forecast site, a finance (stock) site, a route search site, a map providing site, a travel site, a restaurant introduction site, a web blog, and the like. Provide various web pages.

For example, the search service A01 given as an example in FIG. 1 corresponds to a predetermined web search site, route search site, map providing site, or the like. In addition, the shopping service A02 corresponds to a predetermined shopping site, travel site, or the like. Further, the auction service A03 corresponds to a predetermined auction site. In addition, the news service A04 corresponds to a predetermined news site, weather forecast site, finance site, web blog, and the like.

The web page distributed by the web server 30 includes a recommendation frame and an advertising space for displaying the recommendation and the advertising content. Then, the web page including the recommendation frame and the advertising space includes an acquisition command for acquiring the recommendation and the advertising content to be displayed in the frame. For example, in an HTML (HyperText Markup Language) file or the like that forms a web page, the URL or the like of the search device 100 is described as an acquisition command. In this case, the user terminal 10 receives the recommendation and the advertisement content from the search device 100 by accessing the URL described in the HTML file or the like.

The search device 100 extracts a query corresponding to the user from the action history of each service used by the user, and uses query information which is information obtained by giving a weight for each service to the extracted query to the user. It is a server device that searches for recommendations to be delivered.

As described above, the search device 100 identifies the user terminal 10 and identifies the user terminal 10 that distributes the recommendation when the recommendation is distributed. For example, the user can be identified by including the user identification information in a cookie exchanged between the web browser of the user terminal 10 and the search device 100. However, the method for identifying the user is not limited to the above. For example, a dedicated program may be set in the user terminal 10 and the user identification information may be transmitted to the search device 100 from the dedicated program. Further, the search device 100 collates the user information (for example, the attribute information of the user) registered in each website with the cookie of the user terminal 10 that has sent the advertisement distribution request, so that the query information of each user is displayed. May be obtained.

[3. Search device configuration]
Next, the configuration of the search device 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing a configuration example of the search device 100 according to the embodiment. As shown in FIG. 3, the search device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The search device 100 includes an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from an administrator or the like who uses the search device 100, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. You may have.

(About communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the user terminal 10 and the web server 30 via the network N.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. The storage unit 120 includes an action history storage unit 121, a query storage unit 122, and a recommendation information storage unit 125.

(About the action history storage unit 121)
The action history storage unit 121 stores the action history for each service of the user. Here, FIG. 4 shows an example of the action history storage unit 121 according to the embodiment. FIG. 4 is a diagram showing an example of the action history storage unit 121 according to the embodiment. In the example shown in FIG. 4, the action history storage unit 121 has items such as “user ID” and “action log”. In addition, the item of "behavior log" has sub-items such as "service", "behavior", and "query".

The "user ID" indicates identification information for identifying the user or the user terminal 10. In this specification, the identification information as shown in FIG. 4 may be used as a reference code. For example, the user identified by the user ID "U01" may be referred to as "user U01".

The "action log" indicates a log recorded when the user uses each service. "Service" indicates the name of the service used by the user. "Behavior" indicates an action taken by the user in the service or an action related to the service. “Query” indicates an example of a query extracted in the user's behavior.

That is, an example of the data shown in FIG. 4 shows that the user U01 identified by the user ID "U01" performed a search action using "water" as a search query in the "search service A01". .. In addition, the query extracted by the action indicates that it is "water", "product PR01", "shop E01", or the like.

The action history storage unit 121 may store not only the actions performed by the user accessing the service but also the user actions related to each service. For example, an example of the data shown in FIG. 4 indicates that the user U01 clicks on the “recommendation P01” delivered from the “search service A01”.

The recommendation delivered from the service means, for example, a recommendation searched based on a query extracted by using the service. Further, for example, the recommendation delivered from the service indicates the recommendation corresponding to the product handled by the service. For example, the "recommendation P02" delivered from the "shopping service A02" is a recommendation searched based on a query extracted from a log in which the user uses the shopping service A02, or the shopping service. Indicates that the recommendation corresponds to the product handled in A02. In any case, when the user performs an action such as clicking on the recommendation delivered from the service, the action is stored as a log and a query is extracted from the action.

Although not shown in FIG. 4, the action history storage unit 121 may store information such as the date and time when the user performed an action, and statistics on the number of times and frequency of use of a predetermined service.

(About query storage 122)
The query storage unit 122 stores information about the query. In the embodiment, the query storage unit 122 has a service table 123 and a data table called the query table 124.

(About service table 123)
The service table 123 stores information regarding the services used by the user and the weights of each service in the query information. Here, FIG. 5 shows an example of the service table 123 according to the embodiment. FIG. 5 is a diagram showing an example of the service table 123 according to the embodiment. In the example shown in FIG. 5, the service table 123 has items such as "user ID", "service", "usage information", "reaction information", and "weight".

The "user ID" and "service" correspond to the same items shown in FIG. "Usage information" indicates behavior information when a user uses a service. "Reaction information" indicates information about the user's reaction to the recommendation related to the service.

In the example shown in FIG. 5, "usage information" and "reaction information" are shown by concepts such as "F01" and "G01", but in reality, the user used the service for the usage information. Includes statistical information such as frequency and activity content used (including staying time, number of clicks, usage amount, etc.). Further, in reality, the reaction information includes statistical information such as the number of times and frequency of clicking the recommendation derived from the service, the number of times and frequency of conversion to the recommendation, and the like.

The search device 100 may represent usage information and reaction information with a predetermined score. For example, the search device 100 may calculate a score related to usage information according to the number of times the service is used, the frequency of use, and the like. Further, the search device 100 may calculate a score related to the reaction information according to the number of clicks to the recommendation, the number of conversions, the rate, and the like. Then, the search device 100 may calculate the weight for each service based on the scores of the usage information and the reaction information.

"Weight" indicates the weight for each service in the user's query information. As described above, the query extracted from the behavior in the heavy service is calculated with a relatively high score in the user's query information.

That is, in the example shown in FIG. 5, the usage information of the search service A01 of the user U01 is "F01", the reaction information is "G01", and the weight of the search service A01 obtained from these information is "6". It shows that.

(About query table 124)
The query table 124 stores information about the query included in the query information. Here, FIG. 6 shows an example of the query table 124 according to the embodiment. FIG. 6 is a diagram showing an example of the query table 124 according to the embodiment. In the example shown in FIG. 6, the query table 124 has items such as "user ID", "query information ID", "query", "service information", and "total score". In addition, the item of "service information" has small items such as "service", "score by service", and "weight".

The "user ID" corresponds to the same item shown in FIG. The "query information ID" indicates identification information that identifies the query information. The "query" is a query extracted from the user's behavior history, and indicates a query included in the user's query information. "Service information" indicates information about a query for each service.

“Service” corresponds to the same item shown in FIG. "Score by service" indicates the score related to the query extracted by service. For example, the service-specific score indicates a score according to the number of times extracted from the behavior history in the service. The "weight" corresponds to the same item shown in FIG. The "total score" indicates the score of the query included in the query information, including the weight for each service. For example, the total score is calculated by adding the product of the service-specific score and the weight for all services.

That is, in the example shown in FIG. 6, in the query information Q01 of the user U01, the query "water" has a service-specific score of "7" in the "search service A01", and the weight of the search service A01 is "6". It shows that. In addition, the query "water" has a service-specific score of "8" in "shopping service A02", a service-specific score of "7" in "auction service A03", and a service-specific score in "news service A04". It indicates that it is "4". Then, in the example shown in FIG. 6, the total score of the query "water" is "7 * 6 + 8 * 3 + 7 * 1 + 4 * 1 = 77".

(About the recommendation information storage unit 125)
The recommendation information storage unit 125 stores information related to the recommendation. Here, FIG. 7 shows an example of the recommendation information storage unit 125 according to the embodiment. FIG. 7 is a diagram showing an example of the recommendation information storage unit 125 according to the embodiment. In the example shown in FIG. 7, the recommendation information storage unit 125 has items such as "recommendation ID", "product ID", "corresponding service", "product category", and "corresponding query".

The "recommendation ID" indicates identification information that identifies the recommendation. The "product ID" indicates identification information that identifies the product corresponding to the recommendation. "Corresponding service" indicates a service in which the recommended product is handled. "Product category" indicates the category to which the recommended product belongs. A "corresponding query" is a query used to search for recommendations, and indicates a query tagged with a recommendation.

That is, in the example shown in FIG. 7, the recommendation P01 identified by the recommendation ID “P01” is a recommendation related to the product PR01 identified by the product ID “PR01”. In addition, the service corresponding to the recommendation P01 is "shopping service A02", the product category is "beverages", and the corresponding query is "water, cheap, product PR01, food and drink, health, ..." and the like. It is shown that.

The query corresponding to the recommendation (tagged) may be given a predetermined ranking or score. For example, the recommendation P01 may be ranked such that it is easier to search when it matches the query "water" than when it matches the query "health".

Further, the recommendation data (image data, etc.) actually delivered to the user terminal 10 may be stored in a predetermined storage server provided separately from the search device 100. In this case, the search device 100 identifies the recommendation stored in the external storage server based on the recommendation ID stored in the recommendation information storage unit 125. Then, the search device 100 controls the storage server to deliver the specified recommendation to the user terminal 10.

(About control unit 130)
The control unit 130 is a controller, and for example, various programs (as an example of a search program) stored in a storage device inside the search device 100 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. (Equivalent) is realized by executing RAM as a work area. Further, the control unit 130 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. 3, the control unit 130 includes an acquisition unit 131, an extraction unit 132, a generation unit 133, a reception unit 134, a search unit 135, and a distribution unit 136, and the information described below. Realize or execute the function or action of processing. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3, and may be another configuration as long as it is a configuration for performing information processing described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship shown in FIG. 3, and may be another connection relationship.

(About acquisition unit 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires the action history of each service used by the user, which is the action history of the user on the network.

For example, the acquisition unit 131 provides information such as the number and frequency of times the user has used the service, the length of time the user has used the service, the amount charged for the service (for example, the purchase amount of goods in the service), or the date and time when the service has been used. Acquire the action history (log) including.

Specifically, the acquisition unit 131 acquires the user's action history in at least one of the search service A01, the shopping service A02, the auction service A03, and the news service A04 as the service used by the user. In this way, the acquisition unit 131 acquires the behavior history of various services, so that the search unit 135, which will be described later, can search for recommendations that more reflect the user's behavior.

Further, the acquisition unit 131 may acquire the user's reaction to the recommendation when the recommendation is actually delivered to the user terminal 10. For example, in the acquisition unit 131, as the user's reaction to the recommendation, the number or rate of recommendations selected (clicked or touched) by the user, the number or rate of conversions related to the recommendations achieved, or the recommendations were viewed. Get at least one of the number or the length of time. That is, the acquisition unit 131 may acquire index values indicating an appealing effect such as CTR (Click Through Rate) and CVR (Conversion Rate).

In addition, the acquisition unit 131 acquires information about the service that is the recommendation searched by the search unit 135 and is the cause of the recommendation being searched for, or the service related to the recommendation. The service that caused the recommendation to be searched corresponds to, for example, the service that has the most influence when the query score is calculated. That is, the acquisition unit 131 acquires information such as what kind of service the recommendation that the user responded to is derived from.

The acquisition unit 131 stores the acquired information in each storage unit in the storage unit 120. For example, the acquisition unit 131 stores the acquired user's action history in the action history storage unit 121. In addition, the acquisition unit 131 stores the usage information and reaction information derived from the acquired user's behavior history in the service table 123.

(About extraction unit 132)
The extraction unit 132 extracts a query corresponding to the user from the action history acquired by the acquisition unit 131. For example, the extraction unit 132 extracts a word included in the action history as a query.

For example, the extraction unit 132 extracts the search query transmitted by the user in the search service A01 as a query used for the search process. In addition, the extraction unit 132 extracts a query from the title of the product clicked in each service used by the user, the description of the product, the title of the article, the text data included in the article, and the like. For example, the extraction unit 132 morphologically analyzes text data constituting a product title or the like based on the user's behavior history. Then, the extraction unit 132 extracts the morphologically analyzed word as a query. For example, the extraction unit 132 preferentially extracts words used in the search process as words having a large number of achievements used as queries in the past.

The extraction unit 132 may extract words that can be queries by using weight values such as tf-idf. For example, the extraction unit 132 may refer to a word that has been frequently used as a query in the past but is determined to be a word that is widely and generally used and is not useful for the recommendation search process. It may not be extracted as a query.

The extraction unit 132 associates the extracted query with the service that is the extraction destination and stores the extracted query in the query storage unit 122.

(About generator 133)
The generation unit 133 generates query information for each user based on the query extracted by the extraction unit 132. For example, the generation unit 133 generates query information which is information to which weights are given for each service to the query extracted based on the user's action history.

For example, as shown in FIG. 6, the generation unit 133 generates query information in which the query type extracted from the user's behavior history, the score for each service of the query, and the weight for each service are associated with each other. ..

The generation unit 133 calculates the weight for each service corresponding to each user based on, for example, the usage information and the reaction information shown in FIG. For example, the generation unit 133 calculates the weight so that the service that is used more frequently by the user has a heavier weight. Further, the generation unit 133 calculates the weight as the reaction information so that the service corresponding to the recommendation having the higher CTR of the user has a heavier weight.

In addition to the above, the generation unit 133 may calculate the weight by variously combining the information acquired by the acquisition unit 131. For example, the generation unit 133 not only the number of times the user has used the service, but also the frequency with which the user uses the service in a predetermined period, the length of time the user has used the service, the amount charged for the service, or the date and time when the service has been used (for example,). , The newer the date and time when the service is used, the heavier the weight, etc.), etc., may be used to calculate the weight.

Then, the generation unit 133 generates the query information in which the queries are ranked based on the total score calculated by adding the weight for each service. The generation unit 133 stores the generated query information in the query table 124 of the query storage unit 122.

(About receiver 134)
The receiving unit 134 receives the recommendation delivery request from the user. Specifically, the receiving unit 134 receives a request transmitted from the user terminal 10 that displays the web page and is related to the distribution of the recommendation displayed in the recommendation frame included in the web page. The receiving unit 134 sends the received delivery request to the search unit 135.

The receiving unit 134 may receive the distribution request transmitted from the user terminal 10 and also receive the information for identifying the user terminal 10. For example, the receiving unit 134 receives a cookie transmitted from the user terminal 10.

(About search unit 135)
The search unit 135 searches for information content (recommendation) recommended to the user by using the query information which is the information obtained by giving the weight for each service to the query extracted by the extraction unit 132. Specifically, the search unit 135 searches for recommendations that match the query included in the query information, based on the query information generated by the generation unit 133.

For example, the search unit 135 is given a weight calculated based on at least one of the number of times the user has used the service, the length of time the user has used the service, the amount charged for the service, or the date and time when the service has been used. Search for recommendations using the query information.

Further, the search unit 135 may search for the recommendation using the query information whose weight is updated based on the reaction of the user to the recommendation delivered to the user. For example, the search unit 135 searches for recommendations using query information whose weights are calculated according to the number and rate of clicks by the user, conversions to recommendations, and the like.

In this case, the search unit 135 identifies the service that caused the recommendation to be searched for, or information about the service related to the recommendation, that is, the service from which the recommendation is searched. Then, the search unit 135 searches for the recommendation using the query information whose weight is updated based on the information about the specified service.

Specifically, the search unit 135 is a recommendation that the user clicks on a product that is handled by the shopping service A02, or a recommendation that is searched mainly by a query extracted from the behavior history of the shopping service A02. Suppose that it is specified that it is. In this case, in the next recommendation search opportunity, the search unit 135 searches for the recommendation using the heavily updated query information regarding the shopping service A02 based on the information regarding the specified service. The weight is calculated by, for example, the generation unit 133.

As described above, the search unit 135 searches for recommendations related to products and services handled by the service as information content to be displayed on the user terminal 10. For example, the search unit 135 searches for recommendations based on the matching between the query information and the recommendations stored in the recommendation information storage unit 125. For the process of matching the query included in the query information with the query tagged with the recommendation, for example, a known search method may be appropriately used.

Specifically, the search unit 135 ranks the recommendations in the order of the scores output as the search results. Then, the search unit 135 arranges the recommendations as the search results so that the recommendations with the highest rank are displayed as the search results in order. That is, the recommendation determined by the search unit 135 to be more matched with the query information is treated as a higher-ranked recommendation in the search result.

(About distribution unit 136)
The distribution unit 136 distributes various types of information. For example, the distribution unit 136 distributes the recommendation to the user who has sent the recommendation distribution request. Specifically, the distribution unit 136 distributes the recommendation searched by the search unit 135 to the user terminal 10.

When the recommendations searched by the search unit 135 are ranked, the distribution unit 136 preferentially distributes the recommendations having the higher rank. Further, when the web page displayed by the user terminal 10 has a plurality of recommendation frames, the distribution unit 136 distributes a number of recommendations corresponding to the recommendation frames.

[4. Web server configuration]
Next, the configuration of the web server 30 according to the embodiment will be described with reference to FIG. FIG. 8 is a diagram showing a configuration example of the web server 30 according to the embodiment. As shown in FIG. 8, the web server 30 includes a communication unit 31, a content storage unit 32, and a control unit 33.

The communication unit 31 is realized by, for example, a NIC or the like. Then, the communication unit 31 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the user terminal 10 and the search device 100.

The content storage unit 32 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. Then, the content storage unit 32 stores information about the content (web page in the embodiment). For example, the content storage unit 32 stores an HTML file forming a web page, and a still image or a moving image displayed on the web page. The web page stored in the content storage unit 32 may include an ad space for displaying the advertisement content and a recommendation frame for displaying the recommendation.

The control unit 33 is realized by, for example, a CPU, an MPU, or the like executing various programs stored in a storage device inside the web server 30 using the RAM as a work area. Further, the control unit 33 is realized by, for example, an integrated circuit such as an ASIC or FPGA.

As shown in FIG. 8, the control unit 33 has a reception unit 34 and a distribution unit 35, and realizes or executes an information processing function or operation described below. The internal configuration of the control unit 33 is not limited to the configuration shown in FIG. 8, and may be another configuration as long as it is a configuration for performing information processing described later. Further, the connection relationship of each processing unit included in the control unit 33 is not limited to the connection relationship shown in FIG. 8, and may be another connection relationship.

The reception unit 34 receives a web page acquisition request from the user terminal 10. For example, the reception unit 34 accepts an HTTP request as a request for acquiring a web page.

The distribution unit 35 distributes the web page to the user terminal 10 when the reception unit 34 receives the request for acquiring the web page. Specifically, the distribution unit 35 acquires the acquisition request target web page from the content storage unit 32, and distributes the acquired web page to the user terminal 10. Further, the distribution unit 35 may transmit information regarding the action performed by the user terminal 10 on the web page (that is, the action log in the service) to the search device 100.

[5. Processing procedure]
Next, the procedure of processing by the search device 100 according to the embodiment will be described with reference to FIGS. 9, 10 and 11. First, the procedure of the process in which the search device 100 generates the query information will be described with reference to FIG. FIG. 9 is a flowchart (1) showing a processing procedure according to the embodiment.

As shown in FIG. 9, the search device 100 acquires the action history for each service used by the user (step S101). Then, the search device 100 extracts a query from the acquired action history (step S102).

Here, the search device 100 calculates the weight for each service based on the acquired action history for each service (step S103). Then, the search device 100 generates query information corresponding to each user, including the query and the weight for each service (step S104).

Next, the procedure of the process in which the search device 100 searches for recommendations will be described with reference to FIG. FIG. 10 is a flowchart (2) showing a processing procedure according to the embodiment.

As shown in FIG. 10, the search device 100 determines whether or not a recommendation distribution request has been received from the user terminal 10 (step S201). If the delivery request has not been received (step S201; No), the search device 100 waits until the delivery request is received.

On the other hand, when the delivery request is received (step S201; Yes), the search device 100 searches for the recommendation based on the query information corresponding to the user who sent the delivery request (step S202). Then, the search device 100 distributes the searched recommendation to the user who has transmitted the distribution request (step S203).

Next, a procedure related to the process of updating the weight for each service will be described with reference to FIG. FIG. 11 is a flowchart (3) showing a processing procedure according to the embodiment.

As shown in FIG. 11, the search device 100 determines whether or not a response to the recommendation has been obtained from the user (step S301). When the search device 100 has not received the reaction (step S301; No), the search device 100 waits until it receives the reaction.

In the embodiment, "the reaction is not accepted" means a state in which the user does not perform an operation on the recommendation while the recommendation is displayed on the user terminal 10. Therefore, for example, when the user leaves the web page including the recommendation displayed on the user terminal 10, or when the browser software is terminated, the state of "accepting the reaction from the user" is included. In this case, the search device 100 determines that an unfavorable (non-click or conversion) reaction has been obtained from the user, and reflects the reaction in the reaction information.

When the response is received (step S301; Yes), the search device 100 identifies the service related to the recommendation from the user (step S302). Then, the search device 100 updates the reaction information regarding the specified service (step S303).

Then, the search device 100 updates the weight of the service based on the updated reaction information. For example, when the response from the user is a click, a conversion, or the like that the recommendation exerts an appealing effect, the search device 100 updates the service so that the weight of the service related to the recommendation becomes heavier. On the other hand, when the recommendation from the user does not exert an appealing effect such as withdrawal from the web page, the search device 100 updates the service so that the weight of the service related to the recommendation becomes low. By repeating the flow of the distribution process and the update process as described above, the search device 100 can optimize the weight set by the user.

[6. Modification example]
The search device 100 described above may be implemented in various different forms other than the above-described embodiment. Therefore, another embodiment of the search device 100 will be described below.

[6-1. Query by service]
In the above embodiment, as shown in FIG. 6, the search device 100 shows an example of calculating a total score by adding the product of the weight and the score for each service to the query included in the query information. .. Here, the search device 100 may calculate the score for each service with respect to the score of the query. This point will be described with reference to FIG.

FIG. 12 is a diagram showing an example of the query table 224 according to the modified example. In the example shown in FIG. 12, the query table 224 has items such as "user ID", "query information ID", "query", "service", "number of extractions", "weight", and "score". The items already mentioned in FIG. 6 will not be described.

"Number of extractions" indicates the number of times a query has been extracted for each service. The number of extractions does not strictly indicate the number of extractions itself, but may be a ratio of the number of extractions, a numerical value normalized to the total number, or the like.

That is, in the example shown in FIG. 12, the score of the query "water" is calculated for each service in the query information Q01 of the user U01. For example, the score of the query "water" in "search service A01" is "48", the score in "shopping service A02" is "24", the score in "auction service A03" is "8", and so on. It shows that the score in "News Service A04" is "8".

When searching using the query "water", the search device 100 according to the modified example may perform a search process based on the score for each service as described above. For example, the search device 100 treats "water" in the search service A01 and "water" in the shopping service A02 and the like as different queries. In this case, since the search device 100 has the highest score of "water" in the search service A01, it is highly likely that the search device 100 searches for recommendations related to the search service A01.

In this case, for example, the search device 100 searches for drinking water that the user has browsed through the search service A01 in the past as a recommendation, rather than drinking water as a product in the shopping service A02 as a recommendation. Alternatively, for example, the search device 100 preferentially searches for drinking water as a product in the shopping service A02 as a recommendation rather than drinking water exhibited in the auction service A03 as a recommendation.

That is, the search device 100 may set a score for each service for the query, even if the query is common as a word. As a result, the search device 100 can add a difference for each service to the recommendation that is the search result even if the search is performed using the same query "water". For example, the search device 100 uses the same query "water" for a user who uses the shopping service A02 more frequently than the auction service A03 and a user who uses the auction service A03 more frequently than the shopping service A02. Even if you do a search, you can return different search results.

In this way, the search device 100 may search for recommendations using queries having different scores for each service. As a result, the search device 100 can search for recommendations that are more in line with the user's behavior.

[6-2. Information content]
In the above embodiment, the search device 100 shows an example of searching for recommendations related to products including products and services handled by the service as information content recommended to the user. Here, the search device 100 may search for information content other than the recommendation regarding the product.

For example, the search device 100 may recommend articles such as news and columns as information content. As described above, since the search device 100 has query information weighted for each service used by the user, it can be said that the search device 100 has information related to the user's interests. Therefore, the search device 100 can accurately search for articles that are expected to be of interest to the user by searching for articles such as news and columns using the query information. In this case, the search device 100 searches for an article recommended to the user according to, for example, the degree of matching between the query included in the query information and the word included in the text data constituting the article.

In this way, the search device 100 may perform a process of searching other than the recommendation related to the product. As a result, the search device 100 can search for more diverse information contents that the user is interested in.

[6-3. Weight according to the surface]
Further, the search device 100 may search for the recommendation displayed on the surface (web page) on the user terminal 10 by using the query information to which different weights are given according to the surface (web page) on which the recommendation is displayed.

For example, when the surface on which the recommendation is displayed is a web page related to the shopping service A02, the search device 100 performs a search using the query information weighted so that the recommendation related to the shopping service A02 can be easily searched. May be good. As a result, the search device 100 can preferentially deliver recommendations that are highly relevant to the page that the user is currently viewing.

[6-4. Medium]
In the above embodiment, an example in which the search process is performed is shown by taking a web page provided by the web server 30 as an example. However, the medium for displaying information content is not limited to web pages. For example, the search device 100 may search for information content to be displayed in a banner ad space or the like displayed on a predetermined information application, game application, or the like.

[6-5. Service type]
In the above embodiment, the search device 100 shows an example of assigning a weight for each service such as the search service A01 and the shopping service A02. Here, the search device 100 may give weights not for each individual service but for each service category. For example, when one user uses the search service A01 and the search service A11 different from the search service A01, the search device 100 does not determine the search service A01 and the search service A11 as different services, but instead determines that the search service A01 and the search service A11 are different services. It may be treated as belonging to the same category of "search service".

[7. Hardware configuration]
The search device 100, the user terminal 10, and the web server 30 according to the above-described embodiment are realized by, for example, a computer 1000 having a configuration as shown in FIG. Hereinafter, the search device 100 will be described as an example. FIG. 13 is a hardware configuration diagram showing an example of a computer 1000 that realizes the function of the search device 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) Has 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via the communication network 500 (corresponding to the network N shown in FIG. 2) and sends the data to the CPU 1100, and the data generated by the CPU 1100 is transmitted to the other device via the communication network 500. Send to the device.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the data generated via the input / output interface 1600 to the output device.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or 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. And so on.

For example, when the computer 1000 functions as the search device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. Further, the data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the communication network 500.

[8. Others]
Further, among the processes described in the above-described embodiment, all or a part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed can be performed. All or part of it can be done automatically by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. Can be integrated and configured. For example, the acquisition unit 131 and the reception unit 134 shown in FIG. 3 may be integrated. Further, for example, the information stored in the storage unit 120 may be stored in a predetermined storage device provided externally via the network N.

Further, in the above embodiment, an example is shown in which the search device 100 performs, for example, an acquisition process for acquiring a user's action history, a generation process for generating query information, and a search process for searching for recommendations. However, the above-mentioned search device 100 may be separated into an acquisition device that performs acquisition processing, a generation device that performs generation processing, and a search device that performs search processing. In this case, the acquisition device has at least the acquisition unit 131. The generator has at least a generator 133. The search device has at least a search unit 135. Then, the processing by the search device 100 is realized by the search system 1 having each device of the acquisition device, the generation device, and the search device.

Further, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not contradict each other.

[9. effect〕
As described above, the search device 100 according to the embodiment includes an acquisition unit 131, an extraction unit 132, and a search unit 135. The acquisition unit 131 acquires the action history of each service used by the user, which is the action history on the user's network. The extraction unit 132 extracts a query corresponding to the user from the action history acquired by the acquisition unit 131. The search unit 135 searches for information content recommended to the user by using query information which is information obtained by giving weights for each service to the query extracted by the extraction unit 132.

As described above, the search device 100 according to the embodiment searches for the information content recommended to the user by using the query weighted for each service used by the user. As a result, the search device 100 can search for appropriate information content according to the user's various action histories.

In addition, the acquisition unit 131 acquires the user's reaction to the information content. The search unit 135 searches for information content using query information whose weights have been updated based on the user's reaction.

In this way, the search device 100 according to the embodiment gives weights according to the user's reaction to the information content. As a result, the search device 100 can use the active reaction of the user for the search process, not just browsing the service, so that it becomes easier to search the information content according to the interests of the user.

In addition, as a reaction of the user to the information content, the acquisition unit 131 viewed the number or rate of the information content selected by the user, or the number or rate of conversion of the information content achieved, or the information content was viewed. Get at least one of the number or the length of time.

In this way, the search device 100 according to the embodiment acquires the reaction of the user who is assumed to have exerted the appealing effect of the information content, and reflects the reaction in the weight. This makes it easier for the search device 100 to search for information content related to the service that the user has responded to, so that it becomes easier to search for information content that exerts an appealing effect on the user.

In addition, the acquisition unit 131 acquires information about the information content searched by the search unit 135, which is the cause of the search for the information content, or the service related to the information content. The search unit 135 searches for information content using query information whose weights have been updated based on the information about the service acquired by the acquisition unit 131.

In this way, the search device 100 according to the embodiment identifies the service related to the information content to which the user has reacted, and updates the weight related to the service. This makes it easier for the search device 100 to search for information content related to the service that the user is expected to be interested in.

Further, the search unit 135 is given a weight calculated based on at least one of the number of times the user has used the service, the length of time the user has used the service, the amount charged for the service, or the date and time when the service has been used. Search for information content using the query information.

In this way, the search device 100 according to the embodiment gives weights according to the usage mode of the user's service. As a result, the search device 100 can perform a search process that more reflects the behavior of the user on the network.

In addition, the search unit 135 searches for recommendations related to products corresponding to the user's query information as information content.

In this way, the search device 100 according to the embodiment searches for recommendations such as products handled by the service. As a result, the search device 100 can activate the purchasing activity of the user.

In addition, the search unit 135 searches for recommendations related to articles corresponding to the user's query information as information content.

As described above, the search device 100 according to the embodiment may search for articles and the like according to the user's interests as information contents. As a result, the search device 100 can provide many opportunities to attract users to information services and the like.

In addition, the acquisition unit 131 acquires the action history of at least one of the search service, the shopping service, the auction service, and the news service as the service used by the user. The search unit 135 searches for information content using query information to which at least one of the search service, shopping service, auction service, and news service used by the user is weighted.

In this way, the search device 100 according to the embodiment acquires the action history of services belonging to various categories. As a result, the search device 100 can search for information content according to various actions of the user.

Further, the search unit 135 searches for the information content displayed on the surface by using the query information to which different weights are given according to the surface on which the information content is displayed.

As described above, the search device 100 according to the embodiment may perform the search process according to the medium of the information content. As a result, the search device 100 can search not only the past user behavior but also the information content related to the service page or the like that the user is currently browsing, so that the information content that appeals to the user can be searched more. ..

Further, the search device 100 according to the embodiment further includes a receiving unit 134 for receiving the information content distribution request from the user, and a distribution unit 136 for distributing the information content to the user who has transmitted the information content distribution request. The search unit 135 searches for the information content using the query information corresponding to the user, triggered by the reception request for the distribution of the information content by the receiving unit 134. The distribution unit 136 distributes the information content searched by the search unit 135 to the user.

In this way, the search device 100 according to the embodiment may perform a process of delivering information content. As a result, the search device 100 can deliver the information content according to the user's interests weighted for each service to the user.

The embodiments of the present application have been described in detail with reference to the drawings, but this is an example, and various modifications and improvements are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to carry out the present invention in other forms described above.

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

1 Search system 10 User terminal 30 Web server 100 Search device 110 Communication unit 120 Storage unit 121 Action history storage unit 122 Query storage unit 123 Service table 124 Query table 125 Recommendation information storage unit 130 Control unit 131 Acquisition unit 132 Extraction unit 133 Generation unit 134 Receiver 135 Search 136 Distribution

Claims (12)

An acquisition unit that acquires the behavior history of each service used by the user, which is the behavior history on the user's network.
An extraction unit that extracts a query corresponding to the user from the action history acquired by the acquisition unit, and an extraction unit.
Calculating a score based on the frequency of the query before each SL service extracted by the extraction unit, the sum of the query your capital value obtained by multiplying the calculated weight based on the usage information and response information for each of the services A search unit that searches for information content recommended to the user using query information that is information related to the calculated calculation result.
A search device characterized by being equipped with. The acquisition unit
Acquire the user's reaction to the information content and
The search unit
The information content is searched by using the query information whose weight is updated based on the reaction of the user.
The search device according to claim 1. The acquisition unit
As a user's reaction to the information content, at least the number or rate of information content selected by the user, the number or rate of conversions achieved for the information content, the number or duration of viewing of the information content. Get any one,
2. The search device according to claim 2. The acquisition unit
The information content searched by the search unit, and the service that caused the information content to be searched, or the service related to the information content is acquired.
The search unit
The information content is searched by using the query information whose weight is updated based on the information about the service acquired by the acquisition unit.
The search device according to claim 2 or 3. The search unit
Using the query information with a weight calculated based on at least one of the number of times the user has used the service, the length of time the service has been used, the amount charged for the service, or the date and time when the service has been used. To search for the information content,
The search device according to any one of claims 1 to 4. The search unit
As the information content, a recommendation regarding a product corresponding to the query information of the user is searched.
The search device according to any one of claims 1 to 5, wherein the search device is characterized. The search unit
As the information content, a recommendation regarding an article corresponding to the query information of the user is searched.
The search device according to any one of claims 1 to 5, wherein the search device is characterized. The acquisition unit
As the service used by the user, the action history of at least one of a search service, a shopping service, an auction service, and a news service is acquired, and the action history is acquired.
The search unit
The information content is searched by using the query information to which at least one of the search service, the shopping service, the auction service, and the news service used by the user is weighted.
The search device according to any one of claims 1 to 7. The search unit
Using the query information to which different weights are given according to the surface on which the information content is displayed, the information content displayed on the surface is searched.
The search device according to any one of claims 1 to 8. A receiving unit that receives a distribution request for the information content from the user, and
A distribution unit that distributes the information content to the user who has sent the information content distribution request,
With more
The search unit
When the receiving unit receives the distribution request for the information content, the information content is searched for using the query information corresponding to the user.
The distribution unit
Distribute the information content searched by the search unit to the user.
The search device according to any one of claims 1 to 9, wherein the search device is characterized. It ’s a computer-run search method.
An acquisition process that acquires the behavior history of each service used by the user, which is the behavior history on the user's network.
An extraction process that extracts a query corresponding to the user from the action history acquired by the acquisition process, and an extraction process.
A score based on the frequency of the query before each SL service extracted by the extraction step, the sum of the query your capital of user information and a value obtained by multiplying the calculated weights based on the response information for each of the services A search process for searching for information content recommended to the user using query information, which is information related to the calculated calculation result, and
A search method characterized by including. The acquisition procedure for acquiring the behavior history of each service used by the user, which is the behavior history on the user's network.
An extraction procedure for extracting a query corresponding to the user from the action history acquired by the acquisition procedure, and an extraction procedure.
A score based on the frequency of the query before each SL service extracted by the extraction procedure, the sum of the query your capital of user information and a value obtained by multiplying the calculated weights based on the response information for each of the services A search procedure for searching for information content recommended to the user using query information, which is information related to the calculated calculation result, and
A search program characterized by having a computer execute.

Images