JP2019053525A - Generation device, generation method, and generation program - Google Patents

Abstract

To enable understanding the characteristics of users in a highly accurate manner.SOLUTION: A generation device according to an embodiment includes a calculation section and a generation section. The calculation section calculates a first degree of association among retrieval queries based on a retrieval query group inputted by users belonging to a first group, and a second degree of association among retrieval queries based on a retrieval query group inputted by users belonging to a second group different from the first group. The generation section generates, based on the first degree of association and the second degree of association calculated by the calculation section, indexes indicating the characteristics of users belonging to the second group.SELECTED DRAWING: Figure 3

Description

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

  In recent years, with the rapid spread of the Internet, information distribution based on information acquired via a network is actively performed. For example, attribute distribution indicating the attribute of a user who is a distribution destination of information is registered in advance as distribution destination information, and targeted distribution that selectively distributes an advertisement corresponding to the attribute information of the user as a distribution destination is performed. It has been broken.

  In addition, as a technique for grasping the attribute information of the user to whom the advertisement is distributed, for example, the apparent degree of association between the advertisement and the attribute information, and the average relation between the plurality of advertisements and the attribute information A technique for calculating a true relevance between an advertisement and attribute information based on the degree of the above is known.

Japanese Patent Laid-Open No. 2015-1956

  However, with the above-described conventional technology, it is not always possible to accurately grasp the characteristics of the user. For example, in the above-described conventional technology, as user attribute information, data based on qualitative classification such as information on a user's sex and hobbies is only acquired, so that the characteristics of the user can be accurately grasped. However, there was room for improvement.

  The present application has been made in view of the above, and an object of the present invention is to provide a generation device, a generation method, and a generation program that make it possible to accurately grasp user characteristics.

  The generating apparatus according to the present application includes a first relevance level between search queries based on a search query group input by a user belonging to a first group, and a search query group input by a user belonging to a second group different from the first group. An index indicating characteristics of users belonging to the second group based on the first relevance level and the second relevance level calculated by the calculation unit; And a generating unit that generates

  According to one aspect of the embodiment, it is possible to accurately grasp the characteristics of the user.

FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the generation system according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the generation apparatus according to the embodiment. FIG. 4 is a diagram illustrating an example of the association degree information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of the index information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the degree of association and the index value. FIG. 7 is a diagram illustrating an example of an index. FIG. 8 is a flowchart illustrating an example of a generation processing procedure according to the embodiment. FIG. 9 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the generation apparatus.

  Hereinafter, a generation apparatus, a generation method, and a mode for executing a generation program (hereinafter referred to as “embodiment”) according to the present application will be described in detail with reference to the drawings. The generation device, the generation method, and the generation program according to the present application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

[1. Generation process]
First, an example of the generation process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. In the example illustrated in FIG. 1, the generation device 100 indicates the degree of association between the search query “luxury brand A” and each of the other search queries “luxury brand B”, “luxury brand C”, and “popular brand D”. The case of calculating is shown. Here, in the embodiment, the luxury brands A to C indicate brands that handle products whose unit price is higher than the brand D for the public.

  In the example illustrated in FIG. 1, the generation apparatus 100 calculates the relevance calculated based on the search query group input by the user belonging to the group U1 and the search query group input by the user belonging to the group U2. A case where an index indicating the characteristics of users belonging to the group U2 is generated based on the relevance level is shown. Here, in the embodiment, the group U1 indicates the entire users of a predetermined search service provided by the search device 20 described later, and the group U2 indicates users who tend to prefer the luxury brand A compared to the group U1. For example, the generating apparatus 100 may determine that a user whose number of inputs of the search query “luxury brand A” is equal to or greater than a predetermined threshold is a user belonging to the group U2.

[Configuration of generation system]
Prior to the description of FIG. 1, the configuration of the generation system 1 will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of the generation system 1 according to the embodiment. As illustrated in FIG. 2, the generation system 1 according to the embodiment includes a terminal device 10, a search device 20, and a generation device 100. The terminal device 10, the search device 20, and the generation device 100 are connected via a network N so that they can communicate with each other by wire or wirelessly. The network N is, for example, a WAN (Wide Area Network) such as the Internet. The generation system 1 illustrated in FIG. 2 may include a plurality of terminal devices 10, a plurality of search devices 20, and a plurality of generation devices 100.

  The terminal device 10 is an information processing device used by a user. The terminal device 10 is realized by, 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. The terminal device 10 displays content provided by the search device 20 using a web browser or an application.

  The search device 20 is an information processing device that provides a predetermined search service (for example, a web page) in response to a request from the terminal device 10. For example, the search device 20 acquires a search query from the terminal device 10 used by the user, and provides a search result corresponding to the search query to the terminal device 10. In addition, the search device 20 collects search queries input by each user on the page distributed to the terminal device 10 and stores them in the storage unit of the search device 20. Note that the search device 20 may be integrated with the generation device 100. The search device 20 may provide a service for receiving a search query from the terminal device 10. For example, the search device 20 may provide a portal site, news site, auction site, weather forecast site, shopping site, finance (stock price) site, route search site, You may distribute each web page regarding a map provision site, a travel site, a restaurant introduction site, a web blog, etc.

  The web page information distributed by the search device 20 includes, for example, a file described in a markup language. The markup language is, for example, HTML (Hyper Text Markup Language) or XML (Extensible Markup Language). In the following description, it is assumed that the file described in the markup language is an HTML file. However, the file described in the markup language may be an XML file or other files.

  The generation apparatus 100 is an information processing apparatus that acquires the number of users who input different search queries and performs a predetermined process based on the acquired number of users. The user who has input different search queries (referred to as search query X and search query Y) indicates a user who has input search query X and search query Y in a predetermined period. For example, a user who inputs a search query X at a certain point in time and inputs a search query Y within a predetermined period (for example, 1 hour, 24 hours, 1 week, etc.) from that point in time is a different search query (search query X And the search query Y). Note that the user who inputs both the search query X and the search query Y at one time may be a user who inputs a different search query (search query X and search query Y).

  Hereinafter, returning to FIG. 1, an example of the generation process will be described. It is assumed that the generation apparatus 100 has acquired the number of users who input different search queries from a storage unit of the search apparatus 20 in a predetermined search service provided by the search apparatus 20. Specifically, the generation apparatus 100 determines the number of users who input both the search queries “luxury brand A” and “luxury brand B”, and both the search queries “luxury brand A” and “luxury brand C”. The number of input users and the number of users who input both the search queries “luxury brand A” and “popular brand D” are acquired.

  First, the generation device 100 calculates the degree of association between search queries (step S11). Specifically, the generation device 100 calculates the degree of association between search queries based on the number of users who have input different search queries. More specifically, the generation device 100 calculates a higher degree of association between different search queries as the number of users who input different search queries increases.

  In the example illustrated in FIG. 1, the generation device 100 calculates the degree of association between the search query “luxury brand A” and other search queries for the users belonging to the group U1. For example, the generation apparatus 100 determines the search query “luxury brand A” and the search query “luxury brand B” based on the number of users who input both the search query “luxury brand A” and the search query “luxury brand B”. The degree of association with is calculated. Similarly, the generation apparatus 100 uses the search query “luxury brand A” and the search query “luxury brand C” based on the number of users who input both the search query “luxury brand A” and the search query “luxury brand C”. And the search query “luxury brand A” and the search query “popular” based on the number of users who input both the search query “luxury brand A” and the search query “popular brand D”. The degree of association with “brand D” is calculated. In the example of FIG. 1, the number of users who input both the search query “luxury brand A” and the search query “luxury brand B” are both the search query “luxury brand A” and the search query “luxury brand C”. The number of users who input both the search query “luxury brand A” and the search query “luxury brand C” is larger than the number of users who have entered the search query “luxury brand A” and the search query “popular brand”. D ”is an example that is larger than the number of users who input both. In the example of FIG. 1, the generation apparatus 100 calculates the degree of association “4.0” between the search query “luxury brand A” and the search query “luxury brand B”, and searches the search query “luxury brand A”. The degree of association “2.5” with the query “luxury brand C” is calculated, and the degree of association “2.0” between the search query “luxury brand A” and the search query “popular brand D” is calculated. Similarly, the generation apparatus 100 determines the degree of association between the search query “luxury brand A” and each of the other search queries based on the number of users who have entered different search queries among the users belonging to the group U2. calculate.

  Subsequently, the generation apparatus 100 generates an index indicating the characteristics of users belonging to the group U2 based on the relevance calculated in step S11 (step S12). Specifically, when the relevance degree calculated in the group U2 is higher than the relevance degree calculated in the group U1, the generation apparatus 100 searches for the search query corresponding to the relevance degree of the user belonging to the group U2. An index is generated to indicate that the feature is related to. On the other hand, when the relevance calculated in the group U2 is lower than the relevance calculated in the group U1, the generation apparatus 100 relates to the search query corresponding to the relevance of the user belonging to the group U2. An index indicating that no feature is present is generated.

  Hereinafter, an example of the index generated by the generation apparatus 100 will be described. The generation device 100 calculates, as an index value, a numerical value obtained by subtracting the degree of association of the corresponding group U1 from the degree of association between the search query “luxury brand A” in the group U2 and each other search query. In the example of FIG. 1, the generation apparatus 100 determines the search query “luxury brand A” in the group U1 based on the degree of association “6.0” between the search query “luxury brand A” and the search query “luxury brand B” in the group U2. The index value “2.0” is calculated by subtracting the degree of association “4.0” between the search query “luxury brand B”. This indicates that users belonging to the group U2 who tend to prefer the luxury brand A are more likely to input the luxury brand B than users belonging to the group U1. That is, it can be said that the user who belongs to the group U2 has a strong tendency to like the luxury brand B than the user who belongs to the group U1. Similarly, the generation device 100 calculates an index value that is a difference between the degrees of association between the group U1 and the group U2. Then, as in the example illustrated in FIG. 1, the generation device 100 includes each search query that is a calculation target of the degree of association with the search query “luxury brand A” in the vertical axis direction, and a value that indicates the index value in the horizontal axis direction. Is generated. Here, the generation device 100 indicates the central axis “0” by a dotted line, sets the right region from the central axis as a positive region, and sets the left region from the central axis as a negative region, and graph G1 according to the calculated index value. Map with a circle. For example, the relevance between the search query “luxury brand A” and the search query “luxury brand B” in the group U1 is subtracted from the relevance between the search query “luxury brand A” and the search query “luxury brand B” in the group U2. Since the index value is a positive value, the generation device 100 maps the positive region of the vertical axis “luxury brand B” in the graph G1 with a circle. Similarly, the generation device 100 performs mapping for each search query set on the vertical axis of the graph G1 according to the calculated index value.

  In this way, the generation apparatus 100 can generate an index indicating the characteristics of the group U2 with respect to the group U1.

  As described above, the generating apparatus 100 according to the embodiment generates the characteristics of a group specified by a predetermined attribute or the like based on the number of users who input a search query. For example, in the example of FIG. 1, a user who likes the luxury brand A, that is, a user who has a luxury taste, is considered not to be interested in the popular brand D, that is, a low-priced product. A user who likes the luxury brand A is highly interested in both the luxury brand B and the luxury brand C, but is considered to be particularly interested in the luxury brand B among the luxury brands. That is, the generation apparatus 100 according to the embodiment makes it possible to accurately grasp the user's characteristics.

[2. Configuration of generator]
Next, the configuration of the generation apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the generation apparatus 100 according to the embodiment. As illustrated in FIG. 3, the generation device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The generation device 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator of the generation device 100 and a display unit (for example, a liquid crystal display) for displaying various types of information. May be.

(About the communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network N in a wired or wireless manner, and transmits / receives information to / from the generation device 100, the terminal device 10, the search device 20, and the like.

(About the storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 3, the storage unit 120 according to the embodiment includes a relevance information storage unit 121 and an index information storage unit 122.

(Regarding Relevance Information Storage Unit 121)
The degree-of-association information stored in the degree-of-association information storage unit 121 is a user group (“group U1” and “group U2” in the example of FIG. 1) representing various types of information about the degree of association between search queries calculated by the calculation unit 132 described later. Is equivalent to each other).

  Here, an example of the relevance information stored in the relevance information storage unit 121 will be described with reference to FIG. FIG. 4 is a diagram illustrating an example of the association degree information storage unit 121 according to the embodiment. As illustrated in FIG. 4, the relevance information storage unit 121 includes information belonging to items such as “user group ID”, “search query”, and “relevance”.

  “User group ID” indicates information for identifying a group to which the user belongs. For example, in the example of FIG. 4, the “user group ID” includes information such as “U1” for identifying the group U1 and “U2” for identifying the group U2. “Search query” indicates a different search query input by the user. For example, in the example of FIG. 4, the “search query” includes information on both the search query “luxury brand A” and each of the other search queries. “Relevance” indicates information related to the relevance between search queries stored in the item “search query”. For example, in the example of FIG. 4, the “relevance” stores the relevance between the search query “luxury brand A” and each of the other search queries.

(About the index information storage unit 122)
The index information stored in the index information storage unit 122 is information generated by the generation unit 133 to be described later, and indicates the characteristics of users belonging to a specific user group (corresponding to “group U2” in the example of FIG. 1). This information includes various information related to the index.

  Here, an example of the index information stored in the index information storage unit 122 will be described with reference to FIG. FIG. 5 is a diagram illustrating an example of the index information storage unit 122 according to the embodiment. As shown in FIG. 5, the index information storage unit 122 includes information belonging to items such as “user group ID”, “search query”, and “index value”. The “user group ID” indicates information for identifying a user group that is an index generation target. For example, in the example of FIG. 5, “user group ID” includes information such as “U2” for identifying the group U2.

  “Search query” indicates a different search query input by the user. For example, in the example of FIG. 5, the “search query” includes information on both the search query “luxury brand A” and other search queries. The “index value” indicates a value calculated based on the “relevance level” stored in the relevance level information storage unit 121. Specifically, it is a value indicating whether or not the user group identified from the “user group ID” has a feature related to the search query corresponding to the “relevance”. For example, in the example of FIG. 5, a numerical value obtained by subtracting the degree of association of the corresponding group U1 from the degree of association between the search query “luxury brand A” in the group U2 and each other search query is used as the index value. Here, when the index value is a positive value, it indicates that the user belonging to the group U2 has a feature related to the search query corresponding to the related degree. For example, it shows that the user who belongs to the group U2 has the characteristic that the tendency which inputs the search query corresponding to this relevance is higher than the user who belongs to the group U1. Further, when the index value is a negative value, it indicates that the user belonging to the group U2 does not have a feature related to the search query corresponding to the related degree. For example, it shows that the user who belongs to the group U2 has the characteristic that the tendency which inputs the search query corresponding to this degree of association is lower than the user who belongs to the group U1. In addition, when the index value is 0, it indicates that the users belonging to the group U1 and the users belonging to the group U2 have the same tendency to input a search query corresponding to the degree of association.

(About the control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller and is stored in a storage device inside the generation apparatus 100 by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Various programs (corresponding to an example of a determination program) are implemented by using the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). As illustrated in FIG. 3, the control unit 130 according to the embodiment includes an acquisition unit 131, a calculation unit 132, and a generation unit 133, and implements or executes information processing functions and operations described below.

(About the acquisition unit 131)
The acquisition unit 131 acquires the number of users who input different search queries. For example, in the example of FIG. 1, the acquisition unit 131 acquires the number of users who input different search queries in a predetermined search service provided by the search device 20 from the storage unit of the search device 20. In the following description, one of the different search queries is described as “first search query” (corresponding to the search query “luxury brand A” in the example of FIG. 1). The search query for which the degree of relevance for one search query is calculated is “second search query” (search query “luxury brand B”, “luxury brand C” or “popular brand D” in the example of FIG. 1). Equivalent)).

  The acquisition unit 131 acquires the number of users who input either the first search query or the second search query, and acquires the number of users who input both the first search query and the second search query. Also good.

(About the calculation unit 132)
The calculation unit 132 includes a first relevance between search queries based on a search query group input by a user belonging to the first group (corresponding to “group U1” in the example of FIG. 1), and a second group different from the first group. A second degree of association between search queries based on a search query group input by a user belonging to (corresponding to “group U2” in the example of FIG. 1) is calculated. Specifically, the calculation unit 132 calculates the degree of association between different search queries based on the number of users who input different search queries among the users belonging to the first group as the first degree of association, As the relevance, the relevance between different search queries is calculated based on the number of users who input different search queries among the users belonging to the second group. More specifically, the calculation unit 132, as the first relevance, the number of users who input the first search query and the second search query different from the first search query among the users belonging to the first group. Based on the above, the relevance of the second search query to the first search query is calculated, and the user who inputs the first search query and the second search query among the users belonging to the second group as the second relevance The degree of relevance of the second search query to the first search query is calculated based on the number of. For example, in the example of FIG. 1, the calculation unit 132 calculates the degree of association between the first search query “luxury brand A” and each of the other second search queries. Specifically, in the example of FIG. 1, the calculation unit 132, among the users belonging to the group U1, inputs both the first search query “luxury brand A” and the second search query “luxury brand B”. The degree of relevance (first degree of relevance) of the second search query “luxury brand B” with respect to the first search query “luxury brand A” is calculated. Similarly, the calculation unit 132 selects the first search query “luxury brand A” and the other search queries based on the number of users who input different search queries among the users belonging to the group U2. The degree of association (second degree of association) with each search query is calculated.

  The calculation unit 132 adds the number of users belonging to the first group that input either the first search query or the second search query and the first group that inputs both the first search query and the second search query. The first relevance is calculated based on the number of users belonging, and the number of users belonging to the second group to which either the first search query or the second search query is input, the first search query, and the second search query The second association degree may be calculated based on the number of users belonging to the second group both of which are input. For example, based on the following formula (1), the calculation unit 132 calculates the first search query (“search query A” in formula (1)) and the second search query (“search query B” in formula (1)). ) Of the first relevance and the second relevance.

  In the above formula (1), for example, when calculating the first degree of association, “Score (A, B)” indicates the numerical value of the first degree of association between the search query A and the search query B. “Auser” indicates the number of users who input the search query A among the users belonging to the first group. “Buser” indicates the number of users who input the search query B among the users belonging to the first group. “ALLuser” indicates the number of users belonging to the first group. “Auser∧Buser” indicates the number of users who input both the search query A and the search query B among the users belonging to the first group.

  The calculation part 132 calculates the 1st relevance degree of the search query input from the user group which belongs to a 1st group using said Formula (1). For example, the calculation unit 132 aggregates the search query B searched by the user who has input the search query A that is the first search query among the users belonging to the first group. And the calculation part 132 calculates a 1st relevance degree using said Formula (1) with respect to all the 2nd search queries with respect to a 1st search query.

  In the above formula (1), for example, when calculating the second relevance, “Score (A, B)” indicates the numerical value of the second relevance between the search query A and the search query B. “Auser” indicates the number of users who input the search query A among the users belonging to the second group. “Buser” indicates the number of users who input the search query B among the users belonging to the second group. “ALLuser” indicates the number of users belonging to the second group. “Auser∧Buser” indicates the number of users who input both the search query A and the search query B among the users belonging to the second group.

  The calculation part 132 calculates the 2nd relevance degree of the search query input from the user group which belongs to a 2nd group using said Formula (1). For example, the calculation unit 132 aggregates the search query B searched by the user who has input the search query A that is the first search query among the users belonging to the second group. And the calculation part 132 calculates a 2nd relevance degree using the said Formula (1) with respect to all the 2nd search queries with respect to a 1st search query.

  Further, the calculation unit 132 may calculate the degree of association between search queries based on a search query group input by a user belonging to the second group included in the first group as the second degree of association. Specifically, the calculation unit 132 is identified based on at least one of an input history of a predetermined search query, a usage history of a predetermined service, or a predetermined attribute in the first group. The second degree of association in the group is calculated. For example, as illustrated in the example of FIG. 1, the calculation unit 132 receives the first search query “luxury brand A” from the first group indicating the entire users of a predetermined search service provided by the search device 20. A user specified by being equal to or greater than a predetermined threshold may be a user belonging to the second group, and the second association degree in the second group may be calculated. Further, the calculation unit 132 selects a user specified by a use history of a specific search service provided by the search device 20 in the example of FIG. 1 or various services provided by an external information processing device other than the search device 20. It is assumed that the user belongs to the second group, and the second association degree in the second group may be calculated. For example, the calculation unit 132 includes a portal site, news site, auction site, weather forecast site, shopping site, finance (stock price) site, route search provided by the search device 20 or an external information processing device other than the search device 20. Users belonging to the second group may be specified based on the use history in services such as sites, map providing sites, travel sites, restaurant introduction sites, and web blogs. Further, the calculation unit 132 may calculate a second relevance level in the second group by setting a user specified by a predetermined attribute such as “gender” or “age” as a user belonging to the second group.

(About the generator 133)
The generation unit 133 generates an index indicating the characteristics of the users belonging to the second group based on the first relevance level and the second relevance level calculated by the calculation unit 132. Specifically, the generation unit 133 generates an index indicating the characteristics of the users belonging to the second group based on the level relationship between the first relevance level and the second relevance level. For example, in the example of FIG. 1, the generation unit 133 obtains a numerical value obtained by subtracting the degree of association of the corresponding group U1 from the degree of association between the first search query “luxury brand A” in the group U2 and each of the other search queries. The index value indicating the characteristics of the users belonging to the group U2 is calculated.

  In addition, when the second relevance level is higher than the first relevance level, the generation unit 133 indicates that the user belonging to the second group has a characteristic related to the second search query than the user belonging to the first group. If the first relevance level is higher than the second relevance level, a user belonging to the second group does not have a feature related to the second search query than a user belonging to the first group. An index indicating is generated. For example, in the example of FIG. 1, the relevance between the first search query “luxury brand A” and the second search query “luxury brand B” in the group U2 calculated by the calculation unit 132 is “6.0”. The degree of association between the first search query “luxury brand A” and the second search query “luxury brand B” in U1 is “4.0”. That is, since the second relevance degree is higher than the first relevance degree, the generation unit 133 has an index in which a user belonging to the group U2 has a characteristic related to the second search query “luxury brand B” rather than a user belonging to the group U1. Is generated. Specifically, the generation unit 133 indicates that a user who belongs to the group U2 who has a strong tendency to prefer the luxury brand A is more likely to input the luxury brand B than a user who belongs to the group U1. An index (corresponding to “graph G1” in FIG. 1) is generated. In the example of FIG. 1, the relevance between the first search query “luxury brand A” and the second search query “popular brand D” in the group U1 calculated by the calculation unit 132 is “2.0”. The degree of association between the first search query “luxury brand A” and the second search query “popular brand D” in the group U2 is “0.5”. That is, since the first relevance level is higher than the second relevance level, the generation unit 133 has a characteristic that the user belonging to the group U2 is related to the second search query “popular brand D” more than the user belonging to the group U1. Generate an indicator that does not. Specifically, the generation unit 133 has a feature that a user belonging to the group U2 who has a strong tendency to prefer the luxury brand A is less likely to input the brand D for the public than a user belonging to the group U1. Generate indicators to show.

  Moreover, the production | generation part 133 produces | generates the parameter | index which shows whether it has the palatability to the category to which a 2nd search query belongs as a parameter | index which shows the user's characteristic which belongs to a 2nd group. Here, with reference to FIGS. 6 and 7, the relevance levels of the users belonging to each of the groups U1 and U2 calculated based on the category to which the first search query belongs and the category to which the second search query belongs are shown. An example of the index generated by the generation unit 133 based on the above will be described. FIG. 6 is a diagram illustrating an example of the degree of association and the index value.

  In this description, it is assumed that the calculation unit 132 calculates the degree of association with each category to which each second search query belongs, assuming that the category to which the first search query belongs is a “cosmetic query group”. Here, in this description, the group U1 indicates the entire users of the predetermined search service provided by the search device 20 shown in FIG. 1, and the group U2 includes items related to the category “cosmetic query group” as compared to the group U1. Indicates a user who has a strong tendency to like. For example, the calculation unit 132 may set a user whose number of input of a search query belonging to the category “cosmetic system query group” is equal to or greater than a predetermined threshold as a user belonging to the group U2. The category “cosmetic system query group” includes search queries such as “skin lotion”, “perfume”, “lipstick”, and the like. Further, for example, the “movie query group” of the category to which the second search query belongs includes a search query such as “music video”, “short movie”, “notice movie”, and the like.

  Further, in the example illustrated in FIG. 6, the calculation unit 132 relates the relationship between one search query belonging to the category “cosmetic query group” and each search query of the category to which the second search query belongs, for users belonging to the group U1. Assume that the degree is calculated. For example, based on the number of users who input both the search query “skin lotion” and the search query “music video”, the calculation unit 132 determines the degree of association between the search query “skin lotion” and the search query “music video”. Is calculated. Similarly, based on the number of users who input both the search query “skin lotion” and the search query “short movie”, the calculation unit 132 associates the search query “skin lotion” with the search query “short movie”. The degree of relevance between the search query “skin lotion” and the search query “preliminary video” is calculated based on the number of users who input both the search query “skin lotion” and the search query “preliminary video”. To do. Similarly, the calculation unit 132 calculates the degree of association between another search query belonging to the category “cosmetic query group” and each search query of the category to which the second search query belongs. Then, the calculation unit 132 calculates the average value of the calculated relevance degrees, and uses the calculated average value as the relevance degree between the category “cosmetic query group” and the “movie query group” for the users belonging to the group U1. . In the example illustrated in FIG. 6, it is assumed that the calculation unit 132 calculates the degree of association between the category “cosmetic query group” and the “movie query group” as “4.0”. Similarly, it is assumed that the calculation unit 132 calculates the degree of association between the “cosmetic query group” and each category to which the second search query belongs.

  Similarly, it is assumed that the calculation unit 132 calculates the degree of association between the “cosmetic query group” and each category to which the second search query belongs in the users belonging to the group U2.

  The generation unit 133 calculates the index value of the user belonging to the group U2 based on the degree of association between the category to which the first search query belongs calculated by the calculation unit 132 and each category to which the second search query belongs. In the example of FIG. 6, the generation unit 133 determines the category “cosmetic query group” in the group U1 based on the degree of association “5.5” between the category “cosmetic query group” and the category “video query group” in the group U2. The index value “+1.5” is calculated by subtracting the degree of association “4.0” between the category and the “movie query group”. This is because users who belong to the group U2, who tend to prefer items related to the category “cosmetic query group”, are more likely to input search queries that belong to the category “movie query group” than users who belong to the group U1. It shows that. That is, it can be said that the user who belongs to the group U2 has a strong tendency to like the matter regarding the category “moving picture system query group” than the user who belongs to the group U1. Similarly, the generation unit 133 calculates an index value that is a difference between the degrees of association between the group U1 and the group U2.

  Then, as illustrated in FIG. 7, the generation unit 133 displays items related to each category for which the degree of association with the category “cosmetic query group” is calculated in the vertical axis direction, and values indicating index values in the horizontal axis direction. The set graph G11 is generated. FIG. 7 is a diagram illustrating an example of an index. Here, the generation unit 133 indicates the central axis “0” with a dotted line, sets the right region from the central axis as a positive region, and sets the left region from the central axis as a negative region, and graph G11 according to the calculated index value. Map with a circle. For example, the degree of association between the category “cosmetic query group” and the category “video system query group” in the group U1 is subtracted from the degree of association between the category “cosmetic system query group” and the category “video system query group” in the group U2. Since the index value is a positive value, the generation unit 133 maps the positive region of the vertical axis “moving image like” on the graph G11 with a circle. Similarly, the generation unit 133 performs mapping for each item related to the category set on the vertical axis of the graph G11 according to the calculated index value.

  Note that the generation unit 133 may generate an index based on the degree of association between the first search query calculated by the calculation unit 132 and the category to which the second search query belongs.

[3. Decision process flow]
Here, the procedure of the generation process according to the embodiment will be described with reference to FIG. FIG. 8 is a flowchart illustrating an example of a generation processing procedure according to the embodiment.

  As illustrated in FIG. 8, the generation device 100 acquires the number of users who input different search queries from the search device 20 (step S101). Subsequently, the generation device 100 calculates a first relevance level (step S102). For example, in the example illustrated in FIG. 1, the generation device 100 calculates the degree of association between the search query “high-end brand A” and each of the other search queries as the first degree of association for the users belonging to the group U1. Subsequently, the generating apparatus 100 calculates a second relevance level (step S103). In the example illustrated in FIG. 1, the degree of association between the search query “luxury brand A” and other search queries for the users belonging to the group U2 is calculated as the second degree of association.

  Subsequently, the generation device 100 calculates an index value based on the first relevance level and the second relevance level (step S104). Subsequently, the generation device 100 generates an index based on the calculated index value (step S105), and ends the process. For example, in the example illustrated in FIG. 1, when the calculated index value is a positive value, the generation apparatus 100 maps to a positive area of a graph indicating the index. Specifically, the generation device 100 maps a circle to the right region from the central axis “0” of the graph G1. Moreover, the production | generation apparatus 100 maps to the negative area | region of the graph which shows an parameter | index, when the index value calculated based on the 1st relevance level and the 2nd relevance level is a negative value. Specifically, the generation device 100 maps a circle to the left region from the central axis “0” of the graph G1. Further, when the calculated index value is 0, the generation apparatus 100 maps the central axis “0” of the graph G1 with a circle.

[4. effect]
As described above, the generation device 100 according to the embodiment includes the calculation unit 132 and the generation unit 133. The calculation unit 132 includes a first relevance between search queries based on a search query group input by a user belonging to the first group, and a search query based on a search query group input by a user belonging to a second group different from the first group. And a second relevance level between them. The generation unit 133 generates an index indicating the characteristics of the users belonging to the second group based on the first relevance level and the second relevance level calculated by the calculation unit 132.

  Thereby, since the generation apparatus 100 according to the embodiment can generate an index indicating the user characteristics based on the search query group input by the user, that is, quantitative data, the user characteristics can be accurately grasped. Make it possible to do.

  In addition, the calculation unit 132 calculates the degree of association between different search queries based on the number of users who input different search queries among the users belonging to the first group as the first degree of association, The relevance between different search queries is calculated based on the number of users who input different search queries among the users belonging to the second group.

  Thereby, since the production | generation apparatus 100 which concerns on embodiment can produce | generate the parameter | index which shows a user's characteristic based on the relevance degree between each search query, it can grasp | ascertain the characteristic of the user who belongs to a 2nd group accurately. to enable.

  In addition, the generation unit 133 generates an index indicating the characteristics of users belonging to the second group based on the level relationship between the first relevance level and the second relevance level.

  Thereby, the production | generation apparatus 100 which concerns on embodiment can produce | generate the parameter | index which shows the characteristic of the user who belongs to the 2nd relevance degree of a 2nd group based on the relative relationship of a 1st relevance degree and a 2nd relevance degree. Therefore, it is possible to grasp the characteristics of the users of the second group with higher accuracy.

  In addition, the calculation unit 132 selects the first search query based on the number of users who input the first search query and the second search query different from the first search query among the users belonging to the first group. The first search query is calculated based on the number of users who input the first search query and the second search query among the users belonging to the second group as the second relevance level. When the second relevance level is higher than the first relevance level, the generation unit 133 determines that the user belonging to the second group is second than the user belonging to the first group. When an index indicating that the search query has characteristics related to the search query is generated and the first relevance is higher than the second relevance, the second search is more likely than the user belonging to the first group. The query Generating an indication that has no associated features.

  Thereby, the production | generation apparatus 100 which concerns on embodiment makes it possible to grasp | ascertain the characteristic of the user who belongs to a 2nd group more accurately by producing | generating a parameter | index on the basis of a 1st relevance degree.

  Moreover, the production | generation part 133 produces | generates the parameter | index which shows whether it has the palatability to the category to which a 2nd search query belongs as a parameter | index which shows the user's characteristic which belongs to a 2nd group.

  Thereby, since the production | generation apparatus 100 which concerns on embodiment produces | generates the parameter | index which shows the palatability to the category to which a search query belongs, it becomes possible to grasp | ascertain the characteristic of the user which belongs to a 2nd group with a category unit accurately. To do.

  In addition, the calculation unit 132 adds the number of users belonging to the first group to which either the first search query or the second search query is input and the first group to which both the first search query and the second search query are input. The first relevance is calculated based on the number of users belonging, and the number of users belonging to the second group to which either the first search query or the second search query is input, the first search query, and the second search query The second relevance level is calculated based on the number of users belonging to the second group both of which are input.

  Thereby, since the generation apparatus 100 according to the embodiment can calculate the degree of association between the search queries more accurately and can generate an index indicating the characteristics of the user based on the calculated degree of association, the generation apparatus 100 belongs to the second group. It is possible to accurately grasp the characteristics of users.

  Moreover, the calculation part 132 calculates the relevance degree between the search queries based on the search query group input by the user who belongs to the 2nd group contained in the 1st group as a 2nd relevance degree.

  Accordingly, the generation apparatus 100 according to the embodiment generates, for example, an index indicating the characteristics of the users belonging to the second group included in the first group for the entire user. It is possible to accurately grasp the characteristics of users having attributes and the like.

  In addition, the calculation unit 132 calculates the second relevance level in the second group specified based on at least one of a predetermined search query input history, a predetermined service usage history, and a predetermined attribute. .

  Accordingly, the generation apparatus 100 according to the embodiment generates an index indicating the characteristics of the users belonging to the second group specified by the behavior information or the attribute information, and thus the second group specified by the predetermined information. It is possible to accurately grasp the characteristics of the user to which the user belongs.

[5. Hardware configuration]
Further, the generation apparatus according to each embodiment described above is realized by a computer 1000 having a configuration as shown in FIG. 9, for example. Hereinafter, the generation apparatus 100 will be described as an example. FIG. 9 is a hardware configuration diagram illustrating an example of a computer 1000 that implements the functions of the generation apparatus 100. The computer 1000 includes a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and 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 unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, 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 the program, and the like. The communication interface 1500 receives data from other devices via the communication network 500 (corresponding to the network N in the embodiment) and sends the data to the CPU 1100, and the data generated by the CPU 1100 via the communication network 500 is sent to the other devices. Send to device.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and 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 it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a 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. Etc.

  For example, when the computer 1000 functions as the generation apparatus 100, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program loaded on the RAM 1200. In addition, each data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be obtained from other devices via a predetermined communication network.

[6. Others]
As described above, some of the embodiments of the present application have been described in detail with reference to the drawings. However, these are merely examples, and various modifications, including the aspects described in the disclosure section of the invention, based on the knowledge of those skilled in the art, It is possible to implement the present invention in other forms with improvements.

  Further, the generation apparatus 100 described above may be realized by a plurality of server computers, and depending on functions, an external platform or the like may be realized by calling an API (Application Programming Interface), network computing, or the like. Can be changed flexibly.

  Further, “section (module, unit)” described in the claims can be read as “means”, “circuit”, and the like. For example, the generation unit can be read as generation means or a generation circuit.

DESCRIPTION OF SYMBOLS 1 Generation system 20 Search apparatus 100 Generation apparatus 110 Communication part 120 Storage part 121 Relevance information storage part 122 Index information storage part 130 Control part 131 Acquisition part 132 Calculation part 133 Generation part

Claims (10)

A second relevance between search queries based on a search query group input by a user belonging to the first group and a search query based on a search query group input by a user belonging to a second group different from the first group. A calculation unit for calculating relevance;
A generating unit that generates an index indicating characteristics of users belonging to the second group based on the first relevance level and the second relevance level calculated by the calculation unit;
A generating apparatus comprising: The calculation unit includes:
As the first relevance, the relevance between the different search queries is calculated based on the number of users who input different search queries among the users belonging to the first group, and the second relevance is the first relevance Calculating a relevance between the different search queries based on the number of users who input the different search queries among the users belonging to two groups;
The generating apparatus according to claim 1, wherein: The generator is
Generating an index indicating characteristics of users belonging to the second group based on a height relationship between the first relevance level and the second relevance level;
The generating apparatus according to claim 1 or 2, wherein The calculation unit includes:
Based on the number of users who input the first search query and the second search query different from the first search query among the users belonging to the first group as the first relevance level, the first search The degree of relevance of the second search query to the query is calculated, and the number of users who input the first search query and the second search query among the users belonging to the second group as the second relevance degree And calculating the relevance of the second search query to the first search query,
The generator is
When the second relevance level is higher than the first relevance level, an index indicating that a user belonging to the second group has characteristics related to the second search query than a user belonging to the first group When the first relevance level is higher than the second relevance level, the user belonging to the second group has a characteristic related to the second search query than the user belonging to the first group. Generate an indicator of not
The generating apparatus according to claim 1, wherein The generator is
Generating an index indicating whether or not the user has a preference for the category to which the second search query belongs, as an index indicating characteristics of users belonging to the second group;
The generating apparatus according to claim 4. The calculation unit includes:
The number of users belonging to the first group who input either the first search query or the second search query and the first group where both the first search query and the second search query are input The first relevance is calculated based on the number of users, and the number of users belonging to the second group that input either the first search query or the second search query, the first search query, and Calculating the second relevance based on the number of users belonging to the second group both of which input the second search query.
The generating apparatus according to claim 4 or 5, wherein The calculation unit includes:
Calculating the degree of association between search queries based on a group of search queries input by a user belonging to the second group included in the first group, as the second degree of association;
The generating apparatus according to claim 1, wherein The calculation unit includes:
Calculating the second relevance level in the second group specified based on at least one of an input history of a predetermined search query, a usage history of a predetermined service, or a predetermined attribute;
The generating apparatus according to claim 1, wherein A generation method executed by a computer,
A second relevance between search queries based on a search query group input by a user belonging to the first group and a search query based on a search query group input by a user belonging to a second group different from the first group. A calculation process for calculating the relevance;
A generating step of generating an index indicating characteristics of users belonging to the second group based on the first degree of association and the second degree of association calculated by the calculating step;
A generation method comprising: A second relevance between search queries based on a search query group input by a user belonging to the first group and a search query based on a search query group input by a user belonging to a second group different from the first group. A calculation procedure for calculating relevance,
A generation procedure for generating an index indicating characteristics of users belonging to the second group based on the first relevance and the second relevance calculated by the calculation procedure;
A program for causing a computer to execute.

Images