JP6917428B2 - Information processing equipment, information processing methods and information processing programs - Google Patents

Description

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

In recent years, with the rapid spread of networks such as the Internet, advertisement distribution via networks has been actively carried out.

By the way, in a state where there is an advertisement database that stores a plurality of advertisement contents, an advertisement content corresponding to the user information output from the user information providing device is extracted from the advertisement database, and the extracted advertisement content corresponds to the business operator. There is a known targeting advertisement that outputs to a wireless terminal that has entered the content.

JP 2015-165424

However, in the above-mentioned prior art, it is not always possible to realize information provision targeting a user in a predetermined context with high accuracy. For example, in the above-mentioned prior art, when a user of a specific business operator enters a place corresponding to the business operator, the advertising content of the business operator is delivered to the user. For this reason, in the higher-level conventional technology, the advertisement is delivered only at the timing when the relationship (for example, the positional relationship) between the user related to the specific business operator and the specific business operator is enhanced, and the advertisement is delivered only with respect to the user. We do not provide information focusing on various contexts. Therefore, in the above-mentioned prior art, it is not always possible to realize information provision targeting a user in a predetermined context with high accuracy.

The present application has been made in view of the above, and provides an information processing device, an information processing method, and an information processing program capable of realizing information provision targeting a user in a predetermined context with high accuracy. The purpose.

The information processing apparatus according to the present application is a database having a relationship between an acquisition unit that acquires pattern information indicating a user's context pattern and the context corresponding to a predetermined pattern information among the pattern information. It is characterized by having a selection unit that selects a database as an extraction destination from which a user segment, which is a user group according to a context, is extracted from a plurality of candidate databases.

According to one aspect of the embodiment, it is possible to realize information provision targeting a user in a predetermined context with high accuracy.

FIG. 1 is a diagram showing an example of pretreatment according to the embodiment. FIG. 2 is a diagram showing an example of the main process according to the embodiment. FIG. 3 is a diagram showing an example of information providing processing according to the embodiment. FIG. 4 is a diagram showing an example of variations of information providing processing according to the embodiment. FIG. 5 is a diagram showing a configuration example of the information processing system according to the embodiment. FIG. 6 is a diagram showing a configuration example of the information processing device according to the embodiment. FIG. 7 is a diagram showing an example of the content storage unit according to the embodiment. FIG. 8 is a diagram showing an example of the candidate DB storage unit according to the embodiment. FIG. 9 is a diagram showing an example of the segment information storage unit according to the embodiment. FIG. 10 is a flowchart showing an information processing procedure according to the embodiment. FIG. 11 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device.

Hereinafter, an information processing apparatus, an information processing method, and a mode for carrying out an information processing program (hereinafter, referred to as “the embodiment”) according to the present application will be described with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited by this embodiment. Further, in the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[1. Information processing overview]
An example of information processing according to the embodiment will be described with reference to FIGS. 1 to 4. FIG. 1 describes preprocessing for the main information processing among the information processing according to the embodiment. FIG. 2 describes the main information processing (main processing) among the information processing according to the embodiment. In FIGS. 3 and 4, information provision (information provision processing) that follows the main information processing will be described. Further, the pre-processing, the main processing, and the information providing processing according to the embodiment are performed by the information processing apparatus 100 shown in FIG. The information processing device 100 is, for example, a server device.

Further, prior to the description of FIGS. 1 to 4, the information processing system according to the embodiment will be described with reference to FIG. FIG. 5 is a diagram showing a configuration example of the information processing system 1 according to the embodiment. As shown in FIG. 5, the information processing system 1 according to the embodiment includes a user device 10, a trafficking device 30, and an information processing device 100. The user device 10, the submitter device 30, and the information processing device 100 are connected to each other via a network N so as to be able to communicate by wire or wirelessly. The information processing system 1 shown in FIG. 5 may include a plurality of user devices 10, a plurality of submitter devices 30, and a plurality of information processing devices 100.

The user device 10 is an information processing terminal used by an editor (an example of a user) who edits contents when distributing various contents such as article contents and advertisement contents to end users. The user device 10 is, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. For example, the user device 10 accesses the information processing device 100 according to the operation of the editor. As an example, the user device 10 transmits the keyword input by the editor to the information processing device 100.

The trafficking device 30 is an information processing terminal used by a trafficking person who uploads content (article content or advertising content), that is, a content provider (CP). The uploader device 30 is, for example, a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, or the like. For example, the uploader device 30 accesses the information processing device 100 according to the operation of the uploader. As an example, the uploader device 30 transmits (submits) the content input by the uploader to the information processing device 100.

Here, the premise for performing information processing according to the embodiment will be described. For example, in the field of marketing, by segmenting an unspecified number of users in the market, they may be grouped (segmented) into groups having the same needs and characteristics. For example, users may be segmented by age, gender, family structure, income, profession, education level, generation, nationality, social class, and so on. Such segmentation is said to be effective in targeting users who are involved in the distribution of article content and advertising content. However, it may be difficult to accurately target (extract) the users who are in contact with each service such as media service, search service, shopping service, and travel service.

Taking a media service as an example, an editor belonging to a media service, for example, segments users who are interested in a specific target from a group of users stored in various databases, thereby segmenting a group of users (that is, users). We want to target the segment) and provide content related to a specific target. However, databases exist for each service, for example, and since each database stores user information corresponding to a huge number of users, all databases are comprehensively segmented. It is difficult. For this reason, if you know the database that stores logs related to users in the context of being interested in a specific target among various databases, it is efficient to target the users included in this database. At the same time, the user can be segmented with high accuracy. Further, as a result, for example, it becomes possible to realize information provision targeting a user in a predetermined context desired by an editor on the service side with high accuracy.

Therefore, based on such a premise, the information processing apparatus 100 according to the embodiment performs the information processing according to the embodiment. Specifically, the information processing apparatus 100 performs the following information processing as the main processing according to the embodiment among the information processing according to the embodiment. For example, the information processing apparatus 100 acquires pattern information indicating a pattern of a user's context, and is a database having a relationship with a context corresponding to a predetermined pattern information among the acquired pattern information according to the context. Select the database to be the extraction destination from which the user segment, which is the user group, is extracted from a plurality of candidate databases. For example, the information processing apparatus 100 selects a database in which historical information about user behavior related to the context is stored as a database having a context from a plurality of candidate databases. As an example, the information processing apparatus 100 selects from a plurality of candidate databases a database in which historical information regarding actions according to the user's intention based on the state indicated by the user is stored.

Further, the information processing apparatus 100 has a plurality of databases having a relation to the context indicated by combining a predetermined keyword with respect to the pattern of the context indicated by the predetermined pattern information as the context corresponding to the predetermined pattern information. Select from a candidate database. The predetermined keyword may be dynamically generated by the information processing apparatus 100 side or may be arbitrarily specified by the user. In FIG. 1 described below, a generation process in which the information processing apparatus 100 dynamically generates a keyword is described as a pre-process according to an embodiment.

Further, when the information processing apparatus 100 selects a database to be extracted from which a user segment is extracted from a plurality of candidate databases, the information processing apparatus 100 selects the database from the selected database based on a predetermined keyword. Extract the user segment, which is a group of users according to the context used for the selection of.

In addition, the information processing device 100 presents information about the user segment to the user. For example, the information processing apparatus 100 presents, as information on a user segment, list information that is listed and displayed in a state in which the user segment and the content related to the user included in the user segment are combined. The information provision process related to such information provision will be described later with reference to FIGS. 3 and 4.

By the way, in the following, an example of these processes will be described in the order of the pre-process, the main process, and the information providing process according to the embodiment.

[2. An example of information processing]
[2-1. Example of pretreatment according to the embodiment]
First, an example of the pretreatment according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of pretreatment according to the embodiment. As described above, in the example of FIG. 1, as a preprocessing according to the embodiment, an example of a generation process in which the information processing apparatus 100 dynamically generates a keyword is shown. It should be noted that such a keyword is combined with respect to the pattern of the context indicated by the pattern information, and the details thereof will be described in the main process of FIG. Further, in the present embodiment, it is assumed that the following target push service is provided to the user. Specifically, in the present embodiment, it is assumed that the service for targeting the user (user segment) of the notification destination for notifying the content (for example, push notification) is provided to the user. Further, in the present embodiment, the content is the article content, but the type of the content is not limited. For example, the content may be advertising content. Further, in the present embodiment, the user is assumed to be an editor who edits the article content when distributing the article content to the end user. In the following embodiment, the editor AD1 will be taken as an example of the editor.

Further, since the article content is appropriately submitted by the content provider (hereinafter, may be referred to as "CP"), the information processing device 100 is the article content submitted from the CP contributor device 30. Is stored in the content storage unit 121. FIG. 7 shows an example of the content storage unit 121 according to the embodiment. As shown in FIG. 7, the content storage unit 121 has items such as “submissionr ID”, “content ID”, and “content”. The "trader ID" indicates identification information that identifies the CP that is the trafficker. The "content ID" indicates identification information that identifies the article content. “Content” refers to the article content itself, that is, the data of the article content. For example, "content" is text data that serves as an article.

That is, in the example of FIG. 7, the information processing device 100 is identified by the content ID "CN1" from the uploader (trader CP1) identified by the trafficking source ID "CP1" (article content). An example of accepting the submission of CN1) is shown.

In such a state, the information processing apparatus 100 extracts the article content of the processing target, which is the article content of the target for which the keyword is generated, from the content storage unit 121 (step S11). In the example of FIG. 1, the information processing apparatus 100 extracts the article content CN1 as the article content to be processed. In the following, the description will be focused on the article content CN1, but the information processing device 100 performs the same processing on all the article contents stored in the content storage unit 121. Next, the information processing device 100 understands the meaning of the article included in the article content CN1 (step S12). The information processing device 100 can understand the meaning by using, for example, any conventional technique. Hereinafter, the notation of article content CN1 also refers to articles included in article content CN1.

Then, the information processing apparatus 100 extracts a feature word, which is a word indicating the feature of the article content CN1, from the article content CN1 based on the meaning understood in step S12 (step S13). In the example of FIG. 1, it is assumed that the information processing apparatus 100 extracts the feature word WD1 as such a feature word. Next, the information processing apparatus 100 also acquires related words related to the feature word WD1 based on the feature word WD1 (step S14). For example, when the feature word WD1 has an abbreviation or is written in katakana, the information processing apparatus 100 can acquire the abbreviation or katakana notation as a related word. The information processing device 100 may also acquire synonyms for the feature word WD1 as related words. In the example of FIG. 1, it is assumed that the information processing apparatus 100 extracts the related word WD11 as such a related word.

Next, the information processing apparatus 100 generates a keyword to be processed, which is a keyword to be combined with respect to the pattern of the context indicated by the pattern information, based on the feature word W1 and the related word W11 (step S15). As a simple example, the information processing apparatus 100 can define both the feature word W1 and the related word W11 as keywords to be processed. Further, the information processing apparatus 100 may generate one keyword to be processed by understanding the meaning of both the feature word W1 and the related word W11. In the example of FIG. 1, it is assumed that the information processing apparatus 100 generates the keyword "baseball" as the keyword to be processed.

Next, the information processing apparatus 100 acquires the keyword to be processed as the first step of the main process according to the embodiment (step S21). Hereinafter, the description of an example of the main process according to the embodiment will be started.

[2-2. An example of the main process according to the embodiment]
From here, an example of the main process according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing an example of the main process according to the embodiment. The main process according to the embodiment is composed of a selection process of selecting a database to be an extraction destination from which a user segment is extracted from a plurality of candidate databases, and an extraction procedure of extracting a user segment from the selected database. ..

First, the information processing device 100 acquires the keyword to be processed (step S21). When the information processing apparatus 100 generates the keyword to be processed in the preprocessing, the information processing apparatus 100 acquires the generated keyword to be processed. On the other hand, the information processing apparatus 100 can also acquire the keyword specified by the editor AD1 as the keyword to be processed by causing the editor AD1 to specify the keyword. For example, the information processing apparatus 100 may acquire a keyword arbitrarily specified by the editor AD1 as a keyword to be processed, or present the keyword generated in the preprocessing to the editor AD1 as a candidate for the keyword to be processed. By doing so, the keyword specified from the candidates may be acquired as the keyword to be processed. In the example of FIG. 2, it is assumed that the information processing apparatus 100 has acquired the keyword "baseball" generated in the preprocessing as the keyword to be processed.

Here, the pattern information indicating the pattern of the user's context will be described. The user referred to here is an end user of the delivery destination to which the article content is delivered, and indicates various contexts according to his / her intention. For example, the user takes various actions (an example of the context) according to his / her intention as such a context. The pattern information according to the embodiment is information indicating that various contexts are roughly patterned according to the tendency of the context. For example, various contexts such as "a situation where you are likely to use XX", "a situation where you are likely to go to △△", "a situation where you are likely to purchase XX", "a situation where you like (interest) ●●", It can be patterned into 6 contexts such as "a situation where you are doing XX" and "a situation where you are likely to watch □□". The information processing apparatus 100 prepares pattern information indicating such a context pattern (hereinafter, may be referred to as "context pattern") in advance, and uses the information processing apparatus 100 for the main processing. The pattern information may be dynamically generated by the information processing apparatus 100 or may be manually generated.

Further, in the example of FIG. 2, the information processing apparatus 100 holds pattern information in the pattern information storage unit 122. The pattern information storage unit 122 shown in FIG. 2 stores pattern information indicating the above six context patterns. In the example of FIG. 2, the pattern information storage unit 122 has items such as "pattern ID" and "pattern information". The "pattern ID" is identification information that identifies pattern information indicating a context pattern. "Pattern information" is pattern information indicating a context pattern.

That is, in the example of the pattern information storage unit 122 shown in FIG. 2, the pattern information (pattern information PT1) identified by the pattern ID "PT1" is pattern information indicating a context pattern such as "a user who is likely to use XX". Here is an example. More specifically, in the example of the pattern information storage unit 122 shown in FIG. 2, the information processing apparatus 100 has six pattern information as pattern information indicating a context pattern corresponding to the predetermined service for each predetermined service. Here is an example of acquiring. For example, the information processing device 100 has acquired the pattern information PT2 indicating "a user who is likely to go to Δ△", which is a context pattern corresponding to the travel service. Further, for example, the information processing apparatus 100 has acquired the pattern information PT3 indicating "a user who is likely to purchase XX", which is a context pattern corresponding to the shopping service. Further, for example, the information processing apparatus 100 has acquired the pattern information PT4 indicating "a user who likes ●●", which is a context pattern corresponding to the media service.

Here, the symbol parts "○○", "△△", "XX", "●●", "○ ×", and "□□" included in the context pattern will be described. The keyword to be processed is input in this symbol part. Therefore, the symbol part is a variable part according to the keyword to be processed. The information processing apparatus 100 combines the keywords to be processed with respect to the context pattern indicated by the pattern information, that is, inputs the keywords to be processed with respect to the variable portion (symbol portion) of the context pattern indicated by the pattern information. Recognize one context. For example, taking the keyword "baseball" which is the keyword to be processed and the pattern information PT4 as an example, the information processing apparatus 100 can combine the keyword "baseball" and the pattern information PT4 to "like baseball". Recognize the context of "user". More specifically, the information processing device 100 recognizes the context of "a situation in which baseball is liked". Further, in such an example, the context of "a situation in which baseball is liked" can be said to be a context corresponding to the pattern information PT4.

Returning to the description of FIG. The information processing apparatus 100 specifies pattern information of a usage target used in a selection process for selecting a database to be an extraction destination from which a user segment is extracted from a plurality of candidate databases (step S22). In the example of FIG. 2, the information processing apparatus 100 identifies the pattern information to be used from the pattern information stored in the pattern information storage unit 122. For example, the information processing apparatus 100 specifies pattern information to be used based on a keyword to be processed (in the example of FIG. 2, the keyword "baseball"). For example, when the keyword "baseball" is input to the context pattern indicated by the pattern information PT1, a meaningless context such as "a user who is likely to use baseball" is obtained. Therefore, when the keyword of the processing target is input, the information processing apparatus 100 specifies the pattern information that is a meaningful context as the pattern information of the usage target. On the other hand, the information processing apparatus 100 may specify the pattern information specified by the editor AD1 as the pattern information to be used by causing the editor AD1 to specify the pattern information. For example, the information processing apparatus 100 presents the pattern information stored in the pattern information storage unit 122 to the editor AD1 as a candidate for the pattern information to be used, so that the pattern information specified from the candidates can be used as the pattern to be used. Identify as information. In the example of FIG. 2, it is assumed that the information processing apparatus 100 specifies the pattern information PT4 as the pattern information to be used.

Next, the information processing apparatus 100 identifies a category corresponding to the keyword to be processed based on the keyword to be processed (in the example of FIG. 2, the keyword "baseball") (step S23). In the example of FIG. 2, it is assumed that the information processing apparatus 100 specifies the category CT1 as the category corresponding to the keyword to be processed. Category CT1 is actually a category such as "sports" or "baseball".

Next, the information processing apparatus 100 recognizes the context of the usage target (the context corresponding to the pattern information PT4) used in the selection process for selecting the extraction destination database from which the user segment is extracted (step S24). .. For example, as shown in FIG. 2, the information processing apparatus 100 combines the context pattern (user who likes ●●) indicated by the pattern information PT4 with the keyword “baseball” which is the keyword to be processed. That is, the information processing device 100 recognizes one context by inputting the keyword "baseball" for the variable portion "●●" of the context pattern indicated by the pattern information PT4. In such an example, the information processing device 100 recognizes the context CO11 of "a user who likes baseball". More specifically, the information processing apparatus 100 recognizes the context CO11 of "a situation in which baseball is liked".

Next, the information processing apparatus 100 may refer to a database as an extraction destination from which user segments corresponding to the context CO11 are extracted based on the context CO11 recognized in step S24 (hereinafter, referred to as "extraction destination database"). ) Is selected from a plurality of candidate databases (step S25). In the example of FIG. 2, as a plurality of candidate databases, a database DB1 corresponding to the media service (service SV1), a database DB2 corresponding to the credit card service (service SV2), and a database corresponding to the search and shopping service (service SV3). There are four databases called DB3 and database DB4 corresponding to other services (service SV4). For example, the database DB1 stores the action logs collected from the end users in the media service in a form associated with the user ID. Further, in the database DB2, an action log (purchase log) collected from an end user who has purchased a product by using a credit card is stored in a form associated with a user ID. Further, in the database DB3, the action log (search log) collected from the end user who searched using the predetermined search service and the end user who purchased the product using the predetermined shopping service are collected. The action log (purchase log) is stored in a form associated with the user ID.

In the example of FIG. 2, the above four databases are given as an example of a plurality of candidate databases, but the number and types of databases are not limited. Further, in the example of FIG. 2, the information processing device 100 has a candidate database in its own device, but the candidate database does not necessarily have to exist in the information processing device 100. For example, the candidate database may be owned by each server device that provides each service. Therefore, the information processing apparatus 100 can access each database as long as it has location information indicating the location (for example, URL) of the candidate database. Therefore, for example, as shown in FIG. 8, the information processing apparatus 100 indicates the “database ID” which is the identification information for identifying the candidate database and the location of the database identified by the “database ID”. It has a candidate DB storage unit 123 that is stored in association with "location information". FIG. 8 is a diagram showing an example of the candidate DB storage unit 123 according to the embodiment.

Return to the description of step S25. The information processing apparatus 100 determines, for example, a database having a relationship with the context CO11 from the candidate databases based on the context CO11, and selects the database determined to have the relationship as the extraction destination database. More specifically, the information processing apparatus 100 analyzes the user's intention based on the state of the user in the context CO11, and relates a database in which the action log of the action according to the intention indicated by the analysis result is stored to the context CO11. It is judged that the database has sex, and the judged database is selected as the extraction destination database.

Context CO11 is a context of "a situation where you like baseball", but as "users who like baseball", users who play baseball on a daily basis, or who are interested in baseball or watch baseball as a hobby. Can be a user. Then, "users who like baseball" can watch baseball games using "media service" with the intention of watching baseball because they like baseball, or "search service" with the intention of wanting to know more about baseball because they like baseball. It is expected to search for baseball using. Based on the analysis result predicted in this way, the information processing apparatus 100 has a database DB1 corresponding to the media service as an extraction destination database from which a user segment, which is a user group corresponding to the context CO11, is extracted, and a search and shopping. Select the database DB3 corresponding to the service.

In addition, "users who like baseball" may be divided into users who only search for baseball but do not purchase baseball-related products, and users who search for baseball and then purchase baseball-related products. And the latter user may have different action logs. For example, the former user mainly uses the search log, while the latter user mainly uses the purchase log. Therefore, when the database corresponding to the search service and the database corresponding to the shopping service exist separately, the information processing apparatus 100 weights both databases based on the context CO11, and the weight value is higher. Select the database of the above as the extraction destination database.

To reiterate, context CO11 is a context of "a situation where you like baseball", and "users who like baseball" are users who play baseball on a daily basis, who are interested in baseball or watch baseball games. It can be divided into users who have a hobby. Here, it is considered that most of the "users who like baseball" are users who are interested in baseball or have a hobby of watching baseball games, rather than playing baseball on a daily basis. For example, a user who plays baseball on a daily basis may purchase baseball-related products, but a user who is interested in baseball or has a hobby of watching baseball games may purchase baseball-related products rather than purchasing them. It can be said that there are more searches for baseball. Therefore, in such a situation, the information processing apparatus 100 assigns a higher weight value to the database corresponding to the search service than the database corresponding to the shopping service, so that the database corresponding to the search service is the extraction destination database. Control to be selected as.

Further, the information processing apparatus 100 can select the extraction destination database based on the algorithm defined for selection as described above. Further, in such an algorithm, the database to be selected may be defined on a rule basis according to the context in which the context pattern and the keyword are combined. In the example of FIG. 2, it is assumed that the information processing apparatus 100 selects the databases DB1 and DB3 as the extraction destination databases from which the user segments corresponding to the context CO11 are extracted.

Here, in the example of FIG. 2, four users belong to the databases DB1 and DB3, respectively. Since the database DB1 is a database corresponding to the media service, the user belonging to the database DB1 is an end user having an action log (for example, a browsing log) related to the use of the media service. Further, since the database DB3 is a database corresponding to the search and shopping services, the user belonging to the database DB3 is an end user having an action log (for example, a search log and a purchase log) related to the use of the search and shopping services. ..

Then, if the user group composed of a total of eight users belonging to the databases DB1 and DB3 is defined as the user group UG1, not all the users in the user group UG1 may be said to be users corresponding to the context CO11. In some cases, it may not be possible to say that all the users in the user group UG1 are in a "baseball-loving situation". Therefore, the information processing apparatus 100 extracts a user segment, which is a user group corresponding to the context CO11, from the eight users belonging to the user group UG1 based on the context CO11 (step S26). For example, the information processing device 100 belongs to the user group UG1 which is a user group corresponding to the context CO11 based on the keyword "baseball" to be processed combined with the pattern information PT4 corresponding to the context CO11. Extract from 8 users. As an example of this, the information processing apparatus 100 specifies a user group related to the keyword "baseball" from the user group UG1 based on the category CT1 (specified in step S23) corresponding to the keyword "baseball". Then, the information processing apparatus 100 determines that the specified user group is the user segment UG11 which is the user group corresponding to the context CO11, and extracts the user segment UG11.

For example, the information processing apparatus 100 calculates a related score indicating how much the eight users belonging to the user group UG1 are related to the category CT1 corresponding to the keyword "baseball". For example, the information processing device 100 has an action log indicating browsing of content related to baseball (for example, a video, an article, an advertisement, etc.), or a user having an action log indicating a search or purchase regarding baseball. Calculate a higher association score for. Further, the information processing device 100 may further weight the related score according to the action frequency (for example, the number of views, the number of searches, the number of purchases) indicated by the action log. Then, the information processing device 100 identifies a user group having a related score higher than a predetermined value as a user group having a relationship with the keyword "baseball". In such an example, as shown in FIG. 2, the information processing apparatus 100 specifies a user group such as user U11, user U14, user U32, and user U34 as a user group related to the keyword “baseball”. Therefore, the information processing apparatus 100 extracts the user group composed of the user U11, the user U14, the user U32, and the user U34 from the user group UG1 as the user segment UG11 which is the user group corresponding to the context CO11.

Further, the information processing apparatus 100 includes a keyword to be processed (“baseball” in the example of FIG. 2), a pattern ID for identifying pattern information to be used (“pattern information PT4” in the example of FIG. 2), and a keyword to be processed. And the context information recognized by combining the pattern information identified by the pattern ID (“context CO11” in the example of FIG. 2), and the database ID that identifies the database selected based on the context information (in the example of FIG. 2, in the example of FIG. 2). "DB1, DB3"), a user ID that identifies a user extracted from the database identified by the database ID ("U11, U14, U32, U34" in the example of FIG. 2), and a user identified by the user ID. The segment ID (“UG11” in the example of FIG. 2) that identifies the user segment, which is the user group of the above, is associated and stored in the segment information storage unit 124. FIG. 9 shows an example of the segment information storage unit 124 according to the embodiment, and the example of FIG. 9 corresponds to the above example of FIG.

Here, the user segment UG11 is a group of users according to the context CO11. Further, the context CO11 is a context recognized by combining the pattern information PT4 with the keyword "baseball" to be processed. The keyword "baseball" is a keyword generated from the article content CN1. From this, it can be said that the users belonging to the user segment UG11 are the users related to the article content CN1. For example, a user belonging to the user segment UG11 can be said to be a user who may be interested in the article content CN1. Therefore, if the article content CN1 related to the user segment UG 11 is distributed (for example, push notification) to the users belonging to the user segment UG 11, it is considered that the appealing power of the article content CN1 can be enhanced. Furthermore, the user segment UG11 can be said to be a user that can be used for the target push service for the editor AD1. Therefore, the information processing apparatus 100 provides the editor AD1 with information about the user segment UG 11 so that the editor AD1 can use the user segment UG 11 for the target push service (step S27). For example, the information processing device 100 transmits information about the user segment UG 11 to the user device 10 of the editor AD1. Hereinafter, the description will shift to an example of the information providing process according to the embodiment.

As described above with reference to FIGS. 1 and 2, the information processing apparatus 100 according to the embodiment acquires pattern information indicating a pattern of the user's context, and among the acquired pattern information, predetermined pattern information A database that is related to the context corresponding to the above and is the extraction destination database from which the user segment that is the user group corresponding to the context is extracted is selected from a plurality of candidate databases. Further, the information processing apparatus 100 selects a user segment, which is a group of users according to the context used for selecting the database, from the selected database based on the keywords to be processed combined with respect to the predetermined pattern information. Extract.

As a result, the information processing apparatus 100 according to the embodiment can accurately narrow down the database to be extracted from which the user segment is extracted. Therefore, by targeting the narrowed down database, it is efficient and highly accurate. Users can be segmented into. Further, as a result, the information processing apparatus 100 can realize, for example, information provision targeting a user in a predetermined context desired by an editor on the service side with high accuracy.

[2-3. An example of information provision processing according to the embodiment]
From here on, an example of the information providing process according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing an example of information providing processing according to the embodiment. FIG. 3 shows, as an example of the information provision process according to the embodiment, the information provision performed in step S27, which provides the information provision regarding the user segment UG11 to the editor AD1. Further, in the example of FIG. 2, an example is shown in which the article content related to the user segment UG 11 is only the article content CN1 by the main process according to the embodiment, but in the example of FIG. 3, it is related to the user segment UG 11. It is assumed that there are a plurality of article contents to be created in the article content CN1.

In such a state, the information processing apparatus 100 is a keyword included in the user segment and the context used for selecting the database of the extraction source from which the user segment is extracted, and is used as pattern information corresponding to the context. On the other hand, the combination information in which the combined keywords are combined with the acquired content of the acquisition source is generated (step S271). Taking the user segment UG11 as an example, the extraction source databases from which the user segment UG11 is extracted are the databases DB1 and DB3. Further, the keyword included in the context (context CO11) used for selecting the databases DB1 and DB3 and combined with the pattern information (pattern information PT4) corresponding to the context is the keyword "baseball". Is. Further, the content of the acquisition source from which the keyword "baseball" is acquired is the article content CN1. Therefore, the information processing apparatus 100 generates combination information in which the user segment UG 11 and the article content CN1 are combined. Further, the information processing apparatus 100 performs the same processing for each set of the user segment and the article content related to the user segment. Then, as shown in FIG. 3, the information processing apparatus 100 generates a list of combination information in which the user segment and the article content related to the user segment are combined.

Next, the information processing apparatus 100 performs rearrangement control for the set of the user segment and the article content related to the user segment based on the predetermined information (step S272). Specifically, in the information processing apparatus 100, in a state where the combination information is displayed in a list, the editor AD1 uses the predetermined information to form a pair of the user segment and the article content related to the user segment. Control so that it can be sorted arbitrarily. For example, predetermined information includes the title of the article content, the date of the article content (for example, the desired delivery date), the trend of the world, the demographic attribute, and various achievements related to the article content. Of course, this is just one example. Then, the information processing apparatus 100 uses the combination information based on the predetermined information so that the editor AD1 can rearrange the pair of the user segment and the article content related to the user segment according to the predetermined information. Control. For example, for convenience of explanation, it is assumed that the combination information is composed of two sets, "user segment UG11-article content CN1" (group 1) and "user segment UG12-article content CN2" (group 2). In such a case, the information processing apparatus 100 controls the set 1 and the set 2 based on the predetermined information so that the editor AD1 can rearrange the set 1 and the set 2 according to the predetermined information.

Next, the information processing apparatus 100 extracts a part of the sets included in the combination information that has been rearranged and controlled in step S272, which is the combination information generated in step S271, and presents it to the editor AD1. (Step S273). For example, the information processing apparatus 100 extracts a predetermined number of pairs specified in advance, and presents the combination information of the extracted pairs to the editor AD1.

By the way, as described above with reference to FIG. 3, the information processing apparatus 100 according to the embodiment provides the user with information regarding the user segment. For example, the information processing apparatus 100 provides list information as information about a user segment, which is displayed in a list in a state where the user segment and the content related to the user included in the user segment are combined. As a result, the information processing device 100 can provide the user segment by the user having a relationship with each content to the user (editor AD1 in the example of FIG. 3). It is possible to easily make the user understand what kind of content is effective to deliver (for example, push notification) to such a user. As a result, the information processing apparatus 100 can improve the performance of the target push service.

[2-4. Variations in information provision processing related to the embodiment]
From here on, variations of the information providing process according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram showing an example of variations of information providing processing according to the embodiment. As shown in FIG. 4, the information processing apparatus 100 provides information on the number of users of users included in the user segment as information on the user segment. FIG. 4 shows an example in which information regarding the number of users included in the user segment UG11 extracted in the main process of FIG. 2 is provided. In FIG. 4, it is assumed that the editor AD1 inputs a keyword to the information processing apparatus 100. In other words, in FIG. 4, the information processing apparatus 100 causes the editor AD1 to specify a keyword, so that the keyword specified by the editor AD1 is acquired as the keyword to be processed.

Further, the acquisition of the keyword and the provision of information are performed via the page P1 displayed on the display screen D of the user device 10 of the editor AD1. Page P1 is performed by the information processing apparatus 100 in response to access from the editor AD1, for example. As shown in FIG. 4, the page P1 includes an input field AR1 that allows the user to input a keyword. Here, for example, it is assumed that the editor AD1 inputs the keyword "baseball" in the input field AR1 and presses the "add" button. In such a case, the information processing apparatus 100 acquires the keyword "baseball" specified by the editor AD1 as the keyword to be processed.

Further, when the information processing apparatus 100 acquires the keyword "baseball" from the editor AD1, the information processing apparatus 100 uses the keyword "baseball" to perform the main processing described with reference to FIG. Then, the information processing apparatus 100 displays the numerical information J1 which is the information obtained by the main processing and is the information about the number of users of the users included in the user segment UG11 on the page P1. The numerical information J1 is, for example, as shown in FIG. 4, the keyword “baseball” specified by the editor AD1, the context CO11 “user who likes baseball” used for selecting the databases DB1 and DB3, and the databases DB1 and DB3. The ratio of users belonging to the user segment UG11 extracted from "30%", a link to jump to a confirmation destination where it is possible to confirm what kind of user is a user belonging to the user segment UG11 (its user ID), and the like. .. The ratio of users belonging to the user segment UG 11 is, for example, the ratio of the number of users belonging to the user segment UG 11 to the number of users belonging to the total user group AU shown in FIG.

Further, the information processing apparatus 100 causes the editor AD1 to specify narrowing conditions such as gender and age for users belonging to the user segment UG11, so that information J2 for narrowing down users by gender and age is displayed on page P1.

[3. Information processing device configuration]
Next, the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 6 is a diagram showing a configuration example of the information processing apparatus 100 according to the embodiment. As shown in FIG. 6, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. For example, the information processing device 100 is a server device that performs information processing described with reference to FIGS. 1 to 4.

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

(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, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes a content storage unit 121, a pattern information storage unit 122, a candidate DB storage unit 123, and a segment information storage unit 124. Since the content storage unit 121, the pattern information storage unit 122, the candidate DB storage unit 123, and the segment information storage unit 124 have already been described, the description thereof will be omitted here.

(About control unit 130)
The control unit 130 is realized by executing various programs stored in the storage device inside the information processing device 100 using the RAM as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. .. Further, the control unit 130 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. 6, the control unit 130 includes a trafficking reception unit 131, a pattern information acquisition unit 132, a generation unit 133, a keyword acquisition unit 134, a specific unit 135, a recognition unit 136, and a selection unit 137. It has an extraction unit 138 and a provision unit 139, and realizes or executes the functions and operations of information processing described below. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 6, 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. 6, and may be another connection relationship.

(About the submission reception department 131)
The submission reception unit 131 accepts submission of content from the submitter. For example, the submission reception unit 131 accepts submission of various contents such as article content, advertisement content, and video content. For example, the submission receiving unit 131 accepts the submission of content from the uploader device 30 of the uploader. also. The submission reception unit 131 stores the submitted content in the content storage unit 121.

(Pattern information acquisition unit 132)
The pattern information acquisition unit 132 acquires pattern information indicating a pattern of the user's context. For example, the pattern information acquisition unit 132 acquires pattern information indicating the pattern of the context corresponding to the predetermined service for each predetermined service. Further, the pattern information acquisition unit 132 stores the acquired pattern information in the pattern information storage unit 122. In the example of FIG. 2, the pattern information acquisition unit 132 acquires the pattern information PT1 indicating a context pattern such as “a situation (a user in) who is likely to use XX”. Further, the pattern information acquisition unit 132 has acquired the pattern information PT2 indicating the pattern of the context such as "a situation (a user in) who is likely to go to Δ△". Further, the pattern information acquisition unit 132 acquires the pattern information PT3 indicating a context pattern such as "a situation (a user in) who is likely to purchase XX". Further, the pattern information acquisition unit 132 has acquired the pattern information PT4 indicating the pattern of the context such as "a situation (a user in) who likes ●●". Further, the pattern information acquisition unit 132 has acquired the pattern information PT5 indicating the pattern of the context such as "the situation (the user in) doing XX". Further, the pattern information acquisition unit 132 acquires pattern information PT6 indicating a context pattern such as "a situation (a user in) who is likely to watch □□".

The pattern information acquisition unit 132 identifies a representative context by analyzing, for example, the tendency of the end user's context based on the end user's context. Then, the pattern information acquisition unit 132 may determine the specified representative context as the pattern of the context and acquire (generate) the pattern information indicating this pattern. Further, for example, when the pattern information manually generated is stored in a predetermined storage unit, the pattern information acquisition unit 132 acquires the pattern information from the predetermined storage unit.

(About generator 133)
The generation unit 133 generates a keyword. For example, the generation unit 133 generates a keyword to be processed, which is a keyword to be combined with respect to the pattern of the context indicated by the pattern information. For example, the generation unit 133 generates a keyword to be processed in the preprocessing according to the embodiment described with reference to FIG.

For example, the generation unit 133 extracts one content (for example, article content) from the content storage unit 121. Then, the generation unit 133 understands the meaning of the content of the extracted content, and extracts a feature word, which is a word indicating the feature of the content, from this content based on the understood meaning. Then, the generation unit 133 acquires the related word related to the feature word based on the extracted feature word. In such a state, the generation unit 133 generates the keyword to be processed based on the feature word and the related word. As a simple example, the generation unit 133 can define both the feature word and the related word as the keyword to be processed. Further, the generation unit 133 may generate one keyword to be processed by understanding the meaning of both the feature word and the related word. In the example of FIG. 1, the generation unit 133 generates the keyword "baseball" as a keyword to be processed.

(About keyword acquisition unit 134)
The keyword acquisition unit 134 acquires a keyword to be processed, which is a keyword combined with respect to the context pattern indicated by the pattern information. For example, the keyword acquisition unit 134 acquires the generated keyword to be processed when the keyword to be processed is generated by the preprocessing by the generation unit 133. On the other hand, the keyword acquisition unit 134 may acquire the keyword specified by the editor as the keyword to be processed by having the user specify the keyword. For example, the keyword acquisition unit 134 may acquire a keyword arbitrarily specified by the user as a keyword to be processed, or presents the keyword generated in the preprocessing to the user as a candidate for the keyword to be processed. The keyword specified from the candidates may be acquired as the keyword to be processed. In the example of FIG. 2, the keyword acquisition unit 134 acquires the keyword “baseball” generated in the preprocessing as the keyword to be processed.

(About specific part 135)
The identification unit 135 specifies the pattern information of the usage target used in the selection process of selecting the database to be the extraction destination from which the user segment is extracted from a plurality of candidate databases. For example, the identification unit 135 specifies the pattern information to be used from the pattern information stored in the pattern information storage unit 122. For example, the specific unit 135 specifies the pattern information of the usage target based on the keyword of the processing target acquired by the keyword acquisition unit 134. Further, the specifying unit 135 may specify the pattern information specified by the user as the pattern information to be used by causing the user to specify the pattern information. For example, the specific unit 135 presents the pattern information stored in the pattern information storage unit 122 to the user as a candidate for the pattern information to be used, so that the pattern information specified from the candidates is used as the pattern information to be used. Identify. In the example of FIG. 2, the specifying unit 135 specifies the pattern information PT4 as the pattern information to be used.

Further, the specific unit 135 specifies a category corresponding to the keyword to be processed based on the keyword to be processed acquired by the keyword acquisition unit 134. In the example of FIG. 2, the specific unit 135 specifies the category CT1 as a category corresponding to the keyword to be processed.

(About recognition unit 136)
The recognition unit 136 recognizes the context of the usage target used in the selection process for selecting the extraction destination database from which the user segment is extracted. For example, as shown in FIG. 2, the recognition unit 136 combines the keyword "baseball", which is the keyword to be processed, with the context pattern (user who likes ●●) indicated by the pattern information PT4. That is, in the example of FIG. 2, the recognition unit 136 recognizes one context by inputting the keyword “baseball” for the variable portion “●●” of the context pattern indicated by the pattern information PT4. In such an example, the recognition unit 136 recognizes the context CO11 "a user who likes baseball". More specifically, the recognition unit 136 recognizes the context CO11 "a situation in which baseball is liked".

(About selection unit 137)
The selection unit 137 performs a selection process among the main processes according to the embodiment described with reference to FIG. Specifically, the selection unit 137 is a database having a relationship with a context corresponding to a predetermined pattern information among the pattern information acquired by the pattern information acquisition unit 132, and is a user group corresponding to the context. Select the database to be extracted from which a certain user segment is extracted from a plurality of candidate databases. For example, the selection unit 137 selects a database in which historical information regarding user behavior related to the context is stored as a database having a context from a plurality of candidate databases. Further, the selection unit 137 selects a database from a plurality of candidate databases in which historical information regarding the behavior according to the user's intention based on the state of the context is stored as the user behavior related to the context. select.

Further, the selection unit 137 determines the relationship with the context indicated by combining a predetermined keyword (keyword to be processed) with the pattern of the context indicated by the predetermined pattern information as the context corresponding to the predetermined pattern information. Select the database to have from a plurality of candidate databases. For example, the selection unit 137 selects a database having a context and relevance as a predetermined keyword by combining a keyword specified by the user with respect to the pattern from a plurality of candidate databases. Alternatively, the selection unit 137 creates a database having a context and relevance as a predetermined keyword by combining a dynamically generated keyword based on the predetermined content submitted by the uploader with respect to the pattern. Select from multiple candidate databases.

Further, the selection unit 137 may select a database having a relationship with the context based on the predetermined keyword (keyword to be processed) as the context corresponding to the predetermined pattern information from a plurality of candidate databases.

Further, the selection unit selects a database having a context and relevance corresponding to the pattern information specified based on the predetermined keyword (keyword to be processed) as the predetermined pattern information from a plurality of candidate databases. Alternatively, the selection unit 137 selects, as predetermined pattern information, a database having a context and relevance corresponding to the pattern information specified by the user from a plurality of candidate databases.

In the example of FIG. 2, the recognition unit 136 recognizes the context CO11 "a situation in which baseball is liked". In such an example, the selection unit 137 analyzes the user's intention based on the state of the user in the context CO11, and establishes a relationship with the context CO11 in a database in which the action log of the action according to the intention indicated by the analysis result is stored. It is judged that it is a database to have, and the judged database is selected as the extraction destination database. Context CO11 is a context of "a situation where you like baseball", but as "users who like baseball", users who play baseball on a daily basis, or who are interested in baseball or watch baseball as a hobby. Can be a user. Then, "users who like baseball" can watch baseball games using "media service" with the intention of watching baseball because they like baseball, or "search service" with the intention of wanting to know more about baseball because they like baseball. It is expected to search for baseball using. Based on the analysis result predicted in this way, the selection unit 137 sets the database DB1 corresponding to the media service and the search and shopping service as the extraction destination database from which the user segment, which is the user group corresponding to the context CO11, is extracted. Select the database DB3 corresponding to.

The selection unit 137 may weight each candidate database based on the recognized context and select a database having a higher weight value.

(About extraction unit 138)
The selection unit 137 performs an extraction process among the main processes according to the embodiment described with reference to FIG. Specifically, the extraction unit 138 is a user group that is a group of users according to the context used for selecting the database from the database selected by the selection unit 137 based on a predetermined keyword (keyword to be processed). Extract the segment. For example, the extraction unit 138 selects a user segment, which is a predetermined keyword included in the context and is a group of users having a relationship with the predetermined keyword combined with respect to the pattern corresponding to the context, by the selection unit. Extract from the user group included in the database.

In the example of FIG. 2, the extraction unit 138 sets the user segment, which is the user group corresponding to the context CO11, into the user group based on the keyword “baseball” to be processed combined with the pattern information PT4 corresponding to the context CO11. Extract from eight users belonging to UG1. For example, the extraction unit 138 calculates a related score indicating how much it is related to the category CT1 corresponding to the keyword "baseball" for each of the eight users belonging to the user group UG1. For example, the extraction unit 138 has an action log indicating browsing of baseball-related contents (for example, videos, articles, advertisements, etc.), or a user having an action log indicating a search or purchase regarding baseball. On the other hand, a higher association score is calculated. In addition, the extraction unit 138 may further weight the related score according to the action frequency (for example, the number of views, the number of searches, the number of purchases) indicated by the action log. Then, the extraction unit 138 identifies a user group having a related score higher than a predetermined value as a user group having a relationship with the keyword "baseball". In the example of FIG. 2, the extraction unit 138 specifies a user group such as user U11, user U14, user U32, and user U34 as a user group related to the keyword “baseball”. Therefore, the extraction unit 138 extracts the user group composed of the user U11, the user U14, the user U32, and the user U34 from the user group UG1 as the user segment UG11 which is the user group corresponding to the context CO11.

(About the provider 139)
The providing unit 139 performs the information providing processing according to the embodiment described with reference to FIGS. 3 and 4. Specifically, the providing unit 139 provides the user with information regarding the user segment. For example, the providing unit 139 provides list information that is displayed as a list in a state in which the user segment and the content related to the user included in the user segment are combined as the information regarding the user segment. Further, the providing unit 139 presents information on the number of users of the users included in the user segment as information on the user segment.

[4. Processing procedure]
Next, the procedure of information processing according to the embodiment will be described with reference to FIG. FIG. 10 is a flowchart showing an information processing procedure according to the embodiment. In the example of FIG. 10, it is assumed that the pattern information acquisition unit 132 has already acquired the pattern information indicating the pattern of the user's context.

First, the keyword acquisition unit 134 acquires a keyword to be processed, which is a keyword combined with respect to the context pattern indicated by the pattern information (step S301). For example, the keyword acquisition unit 134 acquires the generated keyword to be processed when the keyword to be processed is generated by the preprocessing by the generation unit 133. Further, when the keyword is specified by the user, the keyword acquisition unit 134 acquires the specified keyword as the keyword to be processed.

Next, the identification unit 135 specifies the pattern information of the usage target used in the selection process of selecting the database to be the extraction destination from which the user segment is extracted from the plurality of candidate databases (step S302). For example, the specific unit 135 may dynamically specify the pattern information of the usage target based on the keyword of the processing target acquired by the keyword acquisition unit 134, or cause the user to specify the pattern information. Then, the pattern information specified by the user may be specified as the pattern information to be used. Further, the identification unit 135 specifies a category corresponding to the keyword to be processed based on the keyword to be processed acquired by the keyword acquisition unit 134 (step S303).

Next, the recognition unit 136 recognizes the context of the usage target used in the selection process for selecting the extraction destination database from which the user segment is extracted (step S304). For example, the recognition unit 136 combines the keywords to be processed with respect to the context pattern indicated by the pattern information of the usage target specified by the specific unit 135. Specifically, the recognition unit 136 recognizes one context by inputting a keyword to be processed for a variable portion of the context pattern indicated by the pattern information to be used.

Next, the selection unit 137 is the context recognized by the recognition unit 136 (the context recognized by inputting the keyword to be processed with respect to the pattern indicated by the pattern information of the usage target specified by the specific unit 135). ), The database to be the extraction destination from which the user segment, which is the user group according to the context, is extracted is selected from the plurality of candidate databases (step S305). For example, the selection unit 137 is a database having a relationship with the context recognized by the recognition unit 136, and is a plurality of candidates for the database to be the extraction destination from which the user segment, which is the user group corresponding to the context, is extracted. Select from the database. As an example, the selection unit 137 selects a database from a plurality of candidate databases in which historical information regarding actions according to the user's intention based on the user being in the state of the context recognized by the recognition unit 136 is stored. select.

Next, the extraction unit 138 responds to the context used for selecting the database from the database selected by the selection unit 137 based on the keyword to be processed, that is, the context of the usage target recognized by the recognition unit 136. A user segment, which is a group of users, is extracted (step S306). For example, the extraction unit 138 extracts a user segment which is a user group having a keyword and a relationship related to the pattern corresponding to this context, that is, the pattern indicated by the pattern information of the usage target specified by the specific unit 135. do.

Then, the providing unit 139 provides the user with segment information regarding the user segment extracted by the extracting unit 138 (step S307). For example, the providing unit 139 uses what kind of user should be targeted as a distribution target for delivering a predetermined content (for example, the content stored in the content storage unit 121) in the target push service. Provide users with segment information that can be effectively grasped by the user. For example, as shown in FIG. 3, the providing unit 139 provides list information that is listed in a state in which a user segment and content related to a user included in the user segment are combined and displayed.

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

[5-1. Multiple pattern information (1)]
In the above embodiment, an example is shown in which the specific unit 135 specifies one pattern information as the pattern information to be used. However, the specific unit 135 may specify a plurality of pattern information as the pattern information to be used. Further, when a plurality of pattern information is to be processed in this way, the selection unit 137 selects a database having a combination and relevance according to the context corresponding to each of the plurality of pattern information from the plurality of candidate databases. This point will be described with reference to the example of FIG.

First, in such a modified example, it is assumed that the keyword acquisition unit 134 has acquired two keywords such as the keyword "baseball" and the keyword "ballpark" as the keywords to be processed. Both the keyword "baseball" and the keyword "ballpark" may be generated by the generation unit 133, or both may be those specified by the editor AD1. Further, either one of the keyword "baseball" and the keyword "ballpark" may be generated by the generation unit 133, and the other one may be specified by the editor AD1.

In such a state, it is assumed that the specific unit 135 specifies the pattern information PT4 as the pattern information to be used, for example, based on the keyword "baseball". In such a case, the recognition unit 136 recognizes the context CO21 "user who likes baseball" by combining the context pattern "user who likes ●●" and the keyword "baseball" corresponding to the pattern information PT4. Further, it is assumed that the specific unit 135 specifies the pattern information PT2 as the pattern information to be used, for example, based on the keyword “ballpark”. In such a case, the recognition unit 136 recognizes the context CO22 "user who is likely to go to the stadium" by combining the context pattern "user who is likely to go to the stadium" and the keyword "stadium" corresponding to the pattern information PT2. Then, in such an example, the combination of contexts CO21 and CO22 can be said to be an example of a combination of contexts corresponding to each of a plurality of pattern information (pattern information PT2 and PT4).

Then, the selection unit 137 selects a database having a relationship with the combination of contexts of contexts CO21 and CO22 from a plurality of candidate databases. For example, the selection unit 137 stores a summary context in which the contexts CO21 and CO22 are combined into one, that is, history information regarding the behavior of a "user who likes baseball and is likely to go to the stadium" and the user behavior that is related to the behavior. Select a database from multiple candidate databases. For example, the selection unit 137 analyzes the user's intention based on the fact that the user is in a situation where he / she likes baseball and is likely to go to the stadium, and acts according to the intention indicated by the analysis result (there is such an intention). The database that stores the action log of (take action) is summarized and judged to be a database that has a relationship with the context, and the judged database is selected as the extraction destination database. For the sake of simplicity, it is assumed that the selection unit 137 selects the databases DB1 and DB3 as the extraction destination databases as in the example of FIG.

In such a case, the extraction unit 138 selects users who are related to both the keyword "baseball" and the keyword "ballpark" from the database DB1 or DB3 based on the keyword "baseball" and the keyword "ballpark". Identify. Then, the extraction unit 138 extracts the specified user group as a user segment according to the summary context.

As described above, when the information processing apparatus 100 according to the modified example of the embodiment targets a plurality of pattern information among the acquired pattern information, the information processing apparatus 100 is related to the combination of contexts corresponding to each of the plurality of pattern information. Select a database with sex from a plurality of candidate databases. As a result, the information processing apparatus 100 according to the modified example of the embodiment targets a user who satisfies all of the contexts corresponding to each of the plurality of pattern information with high accuracy even when a plurality of pattern information is to be processed. Information can be provided.

[5-2. Multiple pattern information (2)]
In the above modification 5-1 is shown an example in which the selection unit 137 selects a database related to the summary context in which the contexts CO21 and CO22 are combined into one. However, the selection unit 137 may select the context CO21 and CO22 and their related databases without combining the contexts CO21 and CO22 into one. That is, the selection unit 137 may individually perform selection processing such as selecting a database related to context CO21 and selecting a database related to context CO22.

For example, it is assumed that the selection unit 137 selects the database DB1 as the extraction destination database from which the user segment corresponding to the context CO21 is extracted because the database related to the context CO21 is determined to be the database DB1. Further, it is assumed that the selection unit 137 selects the databases DB1 and DB3 as the extraction destination database from which the user segment corresponding to the context CO22 is extracted because the database related to the context CO22 is determined to be the database DB3. In such a case, the database DB1 is common as the extraction destination database in the context CO21 and the context CO22. Therefore, the extraction unit 138 identifies a user who is related to both the keyword "baseball" and the keyword "ballpark" from the database DB1 based on the keyword "baseball" and the keyword "ballpark". Then, the extraction unit 138 extracts the specified user group as a user segment corresponding to both the context CO21 and the CO22.

[6. Hardware configuration]
Further, the information processing apparatus 100 according to the above embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 11 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the information processing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 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 50 and sends it to the CPU 1100, and transmits the data generated by the CPU 1100 to the other device via the communication network 50.

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 generated data to the output device via the input / output interface 1600.

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 information processing 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 50.

[7. others〕
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 the device is functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

The embodiments of the present application have been described in detail with reference to some drawings, but these are examples, and various modifications 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 practice the present invention in other improved forms.

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

1 Information processing system 10 User equipment 30 Submitter equipment 100 Information processing equipment 120 Storage unit 121 Content storage unit 122 Pattern information storage unit 123 Candidate DB storage unit 124 Segment information storage unit 130 Control unit 131 Submission reception unit 132 Pattern information Acquisition part 133 Generation part 134 Keyword acquisition part 135 Specific part 136 Recognition part 137 Selection part 138 Extraction part 139 Providing part

Claims (18)

An acquisition unit that acquires pattern information indicating a user's context pattern, and
A pattern context indicating pattern information of the pattern information caries Chi plants constant is, a database having a context and relevance to be recognized based on a predetermined keyword, the user segment is the user group in accordance with the context An information processing device characterized by having a selection unit that selects a database to be extracted from a plurality of candidate databases. The information processing device according to claim 1, wherein the acquisition unit acquires pattern information indicating a pattern of the context corresponding to the predetermined service for each predetermined service. The claim unit is characterized in that, as a database related to the context, a database in which historical information about user behavior related to the context is stored is selected from the plurality of candidate databases. Item 2. The information processing apparatus according to item 1 or 2. The selection unit selects, as a user behavior related to the context, a database in which historical information about the behavior according to the user's intention analyzed from the context is stored from the plurality of candidate databases. The information processing apparatus according to claim 3. The selection unit, out of the pattern information, when a plurality of the predetermined pattern information is processed has an association with the set fit that due to the context corresponding to each of a plurality of the predetermined pattern information The information processing apparatus according to any one of claims 1 to 4, wherein a database is selected from the plurality of candidate databases. As the context corresponding to the predetermined pattern information, the selection unit includes a plurality of databases having a relationship with the context indicated by combining a predetermined keyword with respect to the pattern of the context indicated by the predetermined pattern information. The information processing apparatus according to any one of claims 1 to 5, wherein the information processing apparatus is selected from a candidate database. The selection unit selects a database having a relationship with the context indicated by combining a keyword specified by the user with respect to the pattern as the predetermined keyword from the plurality of candidate databases. The information processing apparatus according to claim 6. The selection unit is a database having relevance to the context shown by combining a keyword dynamically generated based on a predetermined content submitted by a trafficking source as the predetermined keyword with respect to the pattern. The information processing apparatus according to claim 6 or 7, wherein the information processing apparatus is selected from the plurality of candidate databases. 6. The selection unit is characterized in that, as the context corresponding to the predetermined pattern information, a database having a relationship with the context based on the predetermined keyword is selected from the plurality of candidate databases. The information processing apparatus according to any one of 8 to 8. The selection unit is characterized in that, as the predetermined pattern information, a database having a relationship with the context corresponding to the pattern information specified based on the predetermined keyword is selected from the plurality of candidate databases. The information processing apparatus according to any one of claims 6 to 9. The claim is characterized in that the selection unit selects, as the predetermined pattern information, a database having a relationship with the context corresponding to the pattern information specified by the user from the plurality of candidate databases. The information processing apparatus according to any one of 1 to 10. A claim characterized by further having an extraction unit that extracts a user segment, which is a group of users according to the context used for selecting the database, from the database selected by the selection unit based on the predetermined keyword. Item 6. The information processing apparatus according to any one of Items 6 to 10. The extraction unit obtains a user segment which is the predetermined keyword included in the context and is a group of users having a relationship with the predetermined keyword combined with respect to the pattern corresponding to the context. The information processing apparatus according to claim 12, wherein the information processing apparatus is extracted from a group of users included in a database selected by a selection unit. The information processing apparatus according to any one of claims 1 to 13, further comprising a providing unit that provides information on the user segment to a user. The claim is characterized in that, as information about the user segment, the providing unit provides list information that is listed in a state in which the user segment and the content related to the user included in the user segment are combined. Item 14. The information processing apparatus according to item 14. The information processing apparatus according to claim 14 or 15, wherein the providing unit presents information regarding the number of users of users included in the user segment as information regarding the user segment. It is an information processing method executed by an information processing device.
The acquisition process to acquire pattern information indicating the pattern of the user's context, and
A pattern context indicating pattern information of the pattern information caries Chi plants constant is, a database having a context and relevance to be recognized based on a predetermined keyword, the user segment is the user group in accordance with the context An information processing method including a selection process of selecting a database to be extracted from a plurality of candidate databases. The acquisition procedure for acquiring pattern information indicating the pattern of the user's context, and
A pattern context indicating pattern information of the pattern information caries Chi plants constant is, a database having a context and relevance to be recognized based on a predetermined keyword, the user segment is the user group in accordance with the context An information processing program characterized by having a computer execute a selection procedure for selecting a database to be extracted from a plurality of candidate databases.

Images