JP2017211786A - Classification device, classification method and classification program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To further properly classify users.SOLUTION: A classification device according to the present invention has: a calculation unit that, for each behavior of users, calculates an index value based on a possibility resulting in a prescribed behavior to be taken by the user taking the behavior; and a classification unit that classifies the user on the basis of the index value calculated for the behavior taken by the user targeted for classification. For example, the classification device according to the present invention is configured to, as the behavior of the user, calculate an index value based on a possibility resulting in the prescribed behavior to be taken by a user inputting a retrieval query for each retrieval query input by the user and classify the user on the basis of the calculated index value for the retrieval query input by the user targeted for classification.SELECTED DRAWING: Figure 1

Description

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

  In recent years, with the rapid spread of the Internet, information distribution via the Internet has been actively performed. As an example of such information distribution, a technique for distributing various types of guidance information for guiding a user to predetermined content such as an advertisement or purchasing a product, such as an advertisement, is known. For example, a technique is known in which users are classified into a plurality of groups according to attribute information, and guidance information is distributed to users classified into a predetermined group.

JP 2008-299542 A Japanese Patent No. 4808207

  However, in the above-described conventional technology, there are cases where users cannot be classified appropriately.

  For example, in the above-described conventional technology, each user is merely classified according to the association between preset attribute information and a group. For this reason, when the guidance information should be distributed to a certain user, but the attribute information and the group are not associated with each other so as to classify the user into a predetermined group, Users cannot be classified into a given group. As a result, the guidance information cannot be distributed to the user and cannot be guided to the guidance destination.

  The present application has been made in view of the above, and aims to classify users more appropriately.

  The classification device according to the present application includes, for each user action, a calculation unit that calculates an index value based on a possibility that the user who has performed the action reaches a predetermined action, and an action performed by the user to be classified And a classifying unit for classifying the user based on the index value calculated for.

  According to one aspect of the embodiment, users can be classified more appropriately.

FIG. 1 is a diagram illustrating an example of classification processing executed by the classification device according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the classification device according to the embodiment. FIG. 3 is a diagram illustrating an example of information registered in the query log database according to the embodiment. FIG. 4 is a diagram illustrating an example of information registered in the reaching query database according to the embodiment. FIG. 5 is a diagram illustrating an example of information registered in the group database according to the embodiment. FIG. 6 is a diagram illustrating an example of information registered in the user database according to the embodiment. FIG. 7 is a diagram illustrating an example of information registered in the content database according to the embodiment. FIG. 8 is a diagram illustrating the concept of classification processing executed by the classification device according to the embodiment. FIG. 9 is a flowchart illustrating an example of a process flow for calculating an index value among the classification processes executed by the classification apparatus according to the embodiment. FIG. 10 is a flowchart illustrating an example of a flow of a process of classifying users according to an index value of an input query input by a user to be classified among the classification processes executed by the classification apparatus according to the embodiment. is there. FIG. 11 is a diagram illustrating an example of a hardware configuration.

  Hereinafter, a classification device, a classification method, and a classification program (hereinafter referred to as “embodiment”) according to the present application will be described in detail with reference to the drawings. Note that the classification device, the classification method, and the classification 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.

[Embodiment]
[1-1. Example of classification device)
First, an example of classification processing executed by the classification device will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of classification processing executed by the classification device according to the embodiment. In FIG. 1, the classification device 10 can communicate with a user terminal 101 used by a user U01 and a user terminal 102 used by a user U02 via a predetermined network N such as the Internet.

  User terminals 101 and 102 (hereinafter may be collectively referred to as “user terminal 100”) are smart devices such as smartphones and tablets, and are wireless such as 3G (3rd Generation) and LTE (Long Term Evolution). This is a mobile terminal device that can communicate with an arbitrary server device via a communication network. Note that the user terminal 100 may be not only a smart device but also an information processing apparatus such as a desktop PC or a notebook PC.

  The classification device 10 is a classification device that classifies the users U01 and U02, and is realized by, for example, a server device or a cloud system. For example, the classification device 10 groups the users U01 and U02 based on the possibility of performing a predetermined action. Then, the classification device 10 selects content to be distributed to the users U01 and U02 according to the group into which the users U01 and U02 are classified, and distributes the selected content.

  For example, the classification device 10 acts to browse predetermined content (for example, a web page), to select (for example, click or tap) the predetermined content, to purchase, bid, etc. for a predetermined product or service For example, groups having different possibilities of reaching a predetermined conversion are set in advance. To give a more specific example, the classification device 10 acquires and browses a web page related to a tour in Hawaii organized by company #A and a web page related to a tour in Hawaii organized by company #B. Is a predetermined conversion. Then, the classification device 10 classifies the users U01 and U02 into any group. For example, the classification device 10 classifies each user U01, U02 into a reverse funnel type group based on the stage until each user U01, U02 reaches a predetermined conversion, and based on the classification result, Deliver.

  Here, an act of browsing a tour application page as a predetermined conversion is considered. Users classified into groups that are likely to lead to such activities are more likely to actually view the tour application page, but for comparison, flow into the application page of competitors that conduct similar tours. The possibility to do is also increased. As a result, in a group that has a high possibility of reaching a predetermined conversion, competition between competitors occurs, and there is a possibility that the value of CVR (Conversion Rate) when an advertisement is distributed may be reduced. On the other hand, users who are classified into groups that are unlikely to browse the tour application page, as a whole, have a lower probability of actually viewing the tour application page, but conduct similar tours for comparison. Since the act of browsing the application page of the competitor is not performed, the value of CVR when the advertisement is distributed increases. For this reason, when guiding each user U01, U02 to a tour application page organized by a predetermined company, the content and distribution mode of the advertisement are switched according to the group into which each user U01, U02 is classified. It is considered better.

  However, in the prior art, since the users U01 and U02 are grouped based on the relationship between preset attribute information and groups, there are cases where appropriate grouping cannot be performed. For example, in the related art, if the attribute information of the user U01 is not associated with a group that is likely to reach a predetermined conversion, even if the user U01 is likely to reach a predetermined conversion The user U01 is classified into a group having a low possibility of reaching a predetermined conversion.

[1-2. Example of classification process)
Therefore, the classification device 10 executes the following classification process. First, for each user action, the classification device 10 calculates an index value based on the possibility that the user who performed the action will reach a predetermined action. Then, the classification device 10 classifies the users based on the index values calculated for the actions performed by the users to be classified.

[1-2-1. About action)
Here, the index value based on the possibility of reaching a predetermined action is a value based on the possibility that the user executes a preset action. As a more specific example, the classification device 10 purchases a possibility that a user browses a website in a predetermined field, a possibility that a user browses a predetermined website, and a predetermined product or service. An index value is calculated based on the possibility of selecting, browsing, purchasing, or the like, the possibility, a predetermined content such as music content or moving image content. That is, the classification device 10 calculates an index value based on the possibility that the user will reach a predetermined conversion set in advance. In addition, if the classification apparatus 10 calculates the index value based on the possibility that the user who performed the action will reach the predetermined action for each user action, the index based on the possibility of reaching the arbitrary action A value may be calculated.

  In addition, the user behavior is, for example, a user behavior that can be identified on the network. For each content of the user behavior, there is a possibility that the user who performed the behavior of the content will reach the predetermined behavior. If the index value based on is calculated, any action can be applied. For example, for each content of web search by the user, the classification device 10 calculates an index value based on the possibility that the user who performed the web search for the content reaches a predetermined action. Then, the classification device 10 may classify the user based on the index value calculated for the content of the web search performed by the user to be classified. More specifically, the classification device 10 calculates, for each search query input by the user, an index value based on the possibility that the user who has input the search query will reach a predetermined action, and is used as a classification target. The user may be classified based on the index value calculated for the search query input by the user.

  In addition, for example, the classification device 10 performs a browsing act or a selection act of the contents for each browsing act or selection act by the user, such as an act of browsing the content or an act of selecting a link to the content. An index value is calculated based on the possibility that the user will reach a predetermined action. Then, the classification device 10 may classify the user based on the index value calculated for the contents of the browsing action or selection action performed by the user to be classified. More specifically, the classification device 10 calculates an index value based on the possibility that the user who browsed or selected the content will reach a predetermined action for each content browsed or selected by the user. The user may be classified based on the index value calculated for the content viewed or selected by the user.

[1-2-2. (About index values based on possibility)
Here, for each action, the classification device 10 calculates an index value based on the possibility that the user who performed the action reaches a predetermined action. For example, for each search query, the classification device 10 calculates an index value based on the possibility that the user who has input the search query will reach a predetermined action (that is, the possibility of conversion). Here, the classification device 10 calculates an index value based on a possibility that a user who has performed an action for which an index value is to be calculated (hereinafter, may be described as “target action”) may reach a predetermined action. If so, the index value may be calculated by any method.

  Note that the classification device 10 divides the content of the action performed by the user who has actually reached the predetermined action (hereinafter referred to as “arrival user”) and the content of the action performed by each user. Based on this, an index value is calculated based on the possibility that the user will reach a predetermined action. For example, the classification device 10 may calculate a ratio of reaching users who performed the target action for each target action, and calculate an index value based on the calculated ratio. Specifically, the classification device 10 counts the number of all users who have performed the target action and the number of reaching users among the users who have performed the target action. Then, the classification device 10 calculates, as an index value, a value obtained by dividing the number of reaching users among the users who have performed the target behavior by the number of all users who have performed the target behavior.

  For example, for each target behavior, the classification device 10 calculates, as an index value, a value obtained by dividing the number of times the reaching user has performed the target behavior by the number of times each user has performed the target behavior. Also good. For example, the classification device 10 acquires a history of search queries (hereinafter referred to as “query log”) input by the user. Further, the classification device 10 acquires a search query (hereinafter referred to as “arrival query”) input by a reaching user who has reached a predetermined conversion. More specifically, the classification device 10 acquires a reaching query input by the reaching user during a predetermined period such as 30 minutes until the user reaches conversion.

  Then, the classification device 10 selects a search query for which an index value is to be calculated, and counts the number of queries that are the same as the selected search query in the query log and the number of queries that are the same as the selected search query among the reached queries. To do. In other words, the classification device 10 counts the number of times each user has input a search query that is an index value calculation target and the number of times the reaching user has input the search query.

  Further, the classification device 10 divides the number of times each reaching user has input the search query by the number of times each user has input the search query for which the index value is to be calculated. The probability of inputting is calculated. Such a probability can be an index of the possibility that the user who has input the search query becomes a reaching user. Therefore, the classification device 10 uses the calculated probability as an index value of the search query. That is, the classification device 10 calculates the probability that a user who has performed a certain target action will browse or select a predetermined content, and the user who has performed the target action will be referred to as the reaching user. The index value is based on the possibility of

[1-2-3. (Classification of users based on index values)
Further, the classification device 10 identifies an index value calculated for the behavior of the user to be classified, and performs grouping of users to be classified based on the identified index value. Specifically, the classification device 10 classifies the users to be classified into any of a plurality of groups each having a different possibility of reaching a predetermined action. For example, the classification device 10 classifies users into groups that are more likely to reach a predetermined behavior as the index value calculated for the behavior performed by the user to be classified is higher. In the following description, the possibility of reaching a predetermined action, such as the possibility of reaching a predetermined conversion, may be described as an inflow distance, and each group may be described as a group having a different inflow distance.

  A more specific example will be described. First, the classification device 10 sets three groups with different probabilities of reaching a predetermined conversion. For example, the classification device 10 includes a group # 1 in which the probability of reaching a predetermined conversion is less than “1”%, a group # 2 in which the probability of reaching a predetermined conversion is “1”% or more and less than “2”%; A group # 3 in which the probability of reaching a predetermined conversion is “2”% or more is set. Further, the classification device 10 identifies the index value having the highest value among the index values calculated for each action performed by the user to be classified. Then, the classification device 10 classifies the users to be classified into groups corresponding to the specified index value values. For example, when the value of the specified index value is “1.3”%, for example, the classification device 10 classifies the users to be classified into the group # 2 corresponding to the index value.

[1-2-4. (Providing information based on classification results)
In addition, the classification device 10 provides content according to the classification result to the user. For example, when receiving a request for requesting distribution of content related to an advertisement from U01 from the user, the classification device 10 classifies the user U01 based on an index value of an action performed by the user U01. Then, the classification device 10 selects content corresponding to the group into which the user U01 is classified, and distributes the selected content to the user U01.

  More specifically, the classification device 10 holds a plurality of contents in association with each group to be classified. When the classification device 10 receives a request from the user U01, the classification device 10 identifies a plurality of contents corresponding to the group into which the user U01 is classified, and the user U01 is identified with respect to the user U01. The content to be distributed is selected based on the action of the user U01. Then, the classification device 10 distributes the selected content to the user U01.

  As described above, the classification device 10 calculates an index value based on the possibility that the user who performed the action reaches the predetermined action for each user action, and the user is determined based on the calculated index value. Classify. As a result, since the classification device 10 classifies each user according to the possibility of performing a predetermined action, the user can be classified more appropriately. For example, since the classification device 10 groups the users U01 according to the possibility of reaching a predetermined conversion, the classification device 10 appropriately performs grouping when delivering guidance information related to the predetermined conversion to the users U01. be able to.

[1-3. (Example of classification process)
Next, an example of classification processing executed by the classification device 10 will be described with reference to FIG. In the following description, a predetermined action as a target such as conversion is referred to as a “target”. In the following description, an example of processing targeting browsing, selection, etc. of each company's introduction page and application page related to a tour to Hawaii will be described. In the following description, as an example of the classification process, the classification device 10 calculates an index value based on the possibility of reaching the target, that is, the inflow distance to the target, for each search query input by the user, An example of processing for classifying users based on the inflow distance corresponding to the search query input by the target user will be described.

  First, the classification device 01 estimates the correspondence between the inflow distance to the target and the search query based on the appearance probability of the query input by the reaching user (step S1). That is, the classification device 10 calculates an index value based on the possibility of reaching the target for each search query. For example, the classification device 10 acquires a query log that is a history of search queries input by various users, and registers the query log in the query log database 31. Further, the classification device 10 acquires a reaching query that is a history of the search query input by the reaching user and registers it in the reaching query database 32 during 30 minutes until the reaching user reaches the target. Then, the classification device 10 calculates the appearance probability of the reaching query (step S2). More specifically, for each reaching query, the classification device 10 calculates, as an appearance probability, a value obtained by dividing the number of times the reaching user has input the reaching query by the number of times the reaching query has been input by each user. . That is, for each reaching query, the classification device 10 calculates a value based on the probability that the user who has input the reaching query becomes the reaching user.

  Then, the classification device 10 estimates the correspondence between the inflow distance and the query based on the appearance probability (step S3). More specifically, the classification device 10 assigns each reaching query to a group having different inflow distances based on the probability value calculated for each reaching query. For example, the classification device 10 associates arrival queries such as “Guam”, “Company #A”, “Company #B”, and the like with relatively low calculated probabilities with “Group # 1” having the longest inflow distance to the target. In addition, for example, the classification device 10 reaches a target query such as “Hawaii”, “Waikiki Hotel”, “Pack Tour Company #A”, etc., with which the calculated probability is medium (for example, 1% to less than 3%). Is associated with “group # 2” which is the second longest inflow distance. For example, the classification device 10 associates a reaching query such as “Company #A Hawaii” having a high calculated probability (for example, 3% or more) with “Group # 3” having the shortest inflow distance to the target.

  Subsequently, the classification device 10 receives a request from the users U01 and U02 (step S4). Note that the timing at which the classification device 10 receives a request from each of the users U01 and U02 may not be the same. For example, the classification device 10 receives from the user terminal 100 a content distribution request related to an advertisement displayed together with a web page. In such a case, the classification device 10 divides the users into groups with different inflow distances to the target in accordance with the input queries of the users U01 and U02 (step S5).

  For example, the classification device 10 acquires an input query that is a search query input by the user U01 within a predetermined time (for example, for 30 minutes until the time of classification). For example, in the example illustrated in FIG. 1, the classification device 10 acquires the input query “company #A Hawaii”, “gourmet site”, “blog”, “Waikiki hotel”, “soccer”, and the like of the user U01. In such a case, the classification device 10 assigns the user U01 to the group whose inflow distance is closest to the target among the groups associated with the input query of the user U01. For example, the classification device 10 assigns the user U01 to the group # 3 associated with the input query “Company #A Hawaii”.

  On the other hand, in the example illustrated in FIG. 1, the classification device 10 acquires the input query “soccer”, “gourmet”, “baseball”, “Guam”, “blog”, and the like of the user U02. In such a case, the classification device 10 assigns the user U02 to the group whose inflow distance is closest to the target among the groups associated with the input query of the user U02. For example, the classification device 10 assigns the user U02 to the group # 1 associated with the input query “Guam”.

  Thereafter, the classification device 10 distributes the advertisement corresponding to the group # 3 to the user U01 (step S6). For example, the classification device 10 distributes, to the user U01, the content selected from the viewpoint of further increasing the CVR among the advertisements related to the target. On the other hand, the classification device 10 distributes the advertisement corresponding to the group # 1 to the user U02 (step S7). For example, the classification device 10 distributes the content selected from the viewpoint of notifying the user U02 of the content of the target by making various advertisements related to the target to be distributed to the user U02.

  Note that, for example, the classification device 10 may distribute contents in different distribution modes for users of the group # 1 and the group # 2 and users of the group # 3. For example, the classification device 10 distributes content as an advertisement or the like placed in the web content to the users of the group # 1 and the group # 2. On the other hand, the classification device 10 may push-distribute content such as advertisements to users in group # 3 in the form of e-mails or messages.

[2. (Configuration of classification device)
Hereinafter, an example of a functional configuration of the classification device 10 that realizes the above-described classification processing will be described. FIG. 2 is a diagram illustrating a configuration example of the classification device according to the embodiment. As illustrated in FIG. 2, the classification device 10 includes a communication unit 20, a storage unit 30, and a control unit 40.

  The communication unit 20 is realized by, for example, a NIC (Network Interface Card). The communication unit 20 is connected to the network N in a wired or wireless manner, and transmits / receives information to / from the user terminal 100, the search log server 200, and the behavior log server 300. The search log server 200 is a server device that manages a search query log input by each user, that is, a query log. The action log server 300 is a server device that manages information indicating content browsed or selected by the user.

  The storage unit 30 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. In addition, the storage unit 30 stores a query log database 31, an arrival query database 32, a group database 33, a user database 34, and a content database 35 (hereinafter may be collectively referred to as “each database 31 to 35”). Hereinafter, an example of information registered in each of the databases 31 to 35 will be described with reference to FIGS.

  A query log that is a history of search queries input by various users is registered in the query log database 31. For example, FIG. 3 is a diagram illustrating an example of information registered in the query log database according to the embodiment. As shown in FIG. 3, a query log that is a history of search queries input by various users within a predetermined period is registered in the query log database 31. For example, in the example illustrated in FIG. 3, various search queries such as “company #A”, “Hawaii”, “SNS # A”, and the like are registered in the query log database 31.

  In the arrival query database 32, a user who has reached a predetermined action and a arrival query that is a search query input during a predetermined period (for example, 30 minutes) until the arrival user reaches the predetermined action are registered. The For example, FIG. 4 is a diagram illustrating an example of information registered in the reaching query database according to the embodiment. As illustrated in FIG. 4, information having items such as “arrival query”, “probability”, and “flag” is registered in the arrival query database 32.

  Here, the “reaching query” is a reaching query input by the reaching user. The “probability” is the appearance probability of the associated “arrival query”. The “flag” is information indicating whether or not the content of the associated “arrival query” is related to a preset small item. For example, in the example shown in FIG. 4, various small items such as “Hawaii”, “Proximity”, “Other overseas”, “Competition”, “Your company”, “Price”, “Travel”, etc. It is included. Various items other than the items shown in FIG. 4 may be registered in the arrival query database 32.

  For example, in the example shown in FIG. 4, a flag indicating that the sub-items “Hawaii”, “Your company”, and “Travel” correspond to the arrival query “Company #A Hawaii” and the probability “3.0”. It is registered with it. In such information, the appearance probability calculated for the arrival query “Company #A Hawaii” is “3.0”%, and the arrival query “Company #A Hawaii” is “Hawaii”, “Your company”, “Travel system” ”Indicates that the arrival query is related to“ ”. In the example shown in FIG. 4, an example of an arrival query corresponding to a certain target is described, but information having the same configuration as the information shown in FIG. 4 is registered in the arrival query database 32 for each target. It is assumed that

  In the group database 33, information on groups for classifying users is registered for each target. For example, FIG. 5 is a diagram illustrating an example of information registered in the group database according to the embodiment. In the example illustrated in FIG. 5, information such as “target ID (Identifier)”, “group ID”, “condition (probability)”, “arrival query”, and the like is registered in the group database 33.

  Here, the “target ID” is information for identifying a target such as a predetermined action or conversion. The “group ID” is information for identifying groups having different inflow distances to the corresponding target. Further, the “condition (probability)” is information indicating a condition used when classifying the reached content or the user to be classified into the associated group. More specifically, the “condition (probability)” is classified into the group. This is information indicating the range of the appearance probability of the search query input by the user.

  For example, in the example illustrated in FIG. 5, the target ID “target # 1”, the group ID “group # 1”, the condition (probability) “1% or less”, and the arrival query “Guam” are registered in association with each other. Such information includes, for example, a reaching query in which the probability of reaching the target indicated by the target ID “target # 1” is a condition (probability) “1% or less” among the reaching queries corresponds to the group ID “group # 1”. Indicates that it is attached. Such information indicates that the arrival query “Guam” is associated with the group indicated by the group ID “group # 1” among the groups corresponding to the target ID “target # 1”. .

  In the user database 34, groups to which each user belongs are registered. For example, FIG. 6 is a diagram illustrating an example of information registered in the user database according to the embodiment. In the example illustrated in FIG. 6, items such as “user ID”, “target ID”, and “group ID” are registered in the user database 34 in association with each other. In addition to the information shown in FIG. 6, arbitrary information related to users may be registered in the user database 34.

  Here, the “user ID” is information for identifying a user. For example, in the example illustrated in FIG. 6, a user ID “user # 1”, a target ID “target # 1”, and a group ID “group # 2” are registered in the user database 34 in association with each other. This information indicates that, for example, among the groups set for the target ID “target # 1”, the user indicated by the user ID “user # 1” is classified into the group indicated by the group ID “group # 2”. Indicates.

  In the content database 35, content to be distributed according to the classification result of the user is registered. More specifically, in the content database 35, content related to advertisements is registered as content distributed to users. For example, FIG. 7 is a diagram illustrating an example of information registered in the content database according to the embodiment. In the example illustrated in FIG. 7, items such as “advertisement ID”, “advertisement data”, “target ID”, and “group ID” are registered in the content database 35 in association with each other.

  Here, the “advertisement ID” is information for identifying an advertisement distributed to the user. The “advertisement data” is data of advertisements distributed to users. For example, in the example illustrated in FIG. 7, the content database 35 corresponds to the advertisement ID “advertisement # 1”, the advertisement data “advertisement data # 1”, the target ID “target # 1”, and the group ID “group # 1”. It is registered with it. Such information includes the advertisement indicated by the advertisement ID “advertisement # 1” for the users classified into the group indicated by the group ID “group # 1” among the groups set for the target ID “target # 1”. This indicates that the advertisement data “advertisement data # 1” is distributed.

  Returning to FIG. 2, the description will be continued. The controller 40 is a controller. For example, various programs stored in a storage device inside the classification device 10 are stored in a RAM or the like by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). This is realized by being executed as a work area. The control unit 40 is a controller, and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

  As illustrated in FIG. 2, the control unit 40 includes an acquisition unit 41, a calculation unit 42, a specification unit 43, a setting unit 44, a reception unit 45, a classification unit 46, and a provision unit 47.

  The acquisition unit 41 acquires a query log and a reaching query. For example, the acquisition unit 41 acquires, from the search log server 200 at a predetermined time interval, a search query before a predetermined period has elapsed since input. Then, the acquisition unit 41 registers the acquired search query in the query log database 31 as a query log.

  Moreover, the acquisition part 41 acquires the information which shows the user who performed predetermined | prescribed action, ie, an arrival user, from the action log server 300 at predetermined time intervals. Then, the acquisition unit 41 acquires a reaching query that is a search query input by the reaching user from the search log server 200, and registers the acquired reaching query in the reaching query database 32. The acquisition unit 41 acquires, as a reaching query, a search query input within a predetermined period, such as a search query input during 30 minutes until a predetermined action is performed, among search queries input by a reaching user. May be.

  In addition, the acquisition unit 41 stores, in the arrival query database 32, a small item flag indicating an attribute of the arrival query using a predetermined character analysis technique or the like. For example, when the acquired arrival query is “Guam”, the acquisition unit 41 sets a flag of a small item such as “other overseas” or “travel system” associated with the arrival query “Guam” to “ Update to “1”.

  The calculation unit 42 calculates an index value based on the possibility that the user who performed the action will reach the predetermined action for each user action. Specifically, the calculation unit 42 calculates an appearance probability value for each reaching query, and registers the calculated appearance probability value in the reaching query database 32. For example, for each user behavior, the calculation unit 42 calculates, as an index value, a value obtained by dividing the number of times the reaching user has performed the behavior by the number of times the user has performed the behavior. More specifically, the calculation unit 42 calculates an index value based on the possibility that the user who performed the action will reach the predetermined action for each action performed by the reaching user during the predetermined period. In addition, for each user action, the calculation unit 42 calculates the ratio of users who have reached a predetermined action among the users who have performed the action, and calculates an index value based on the calculated ratio.

  Hereinafter, an example of processing executed by the calculation unit 42 will be described. For example, for each search query input by the user, the calculation unit 42 calculates an index value based on the possibility that the user who has input the search query will reach a predetermined action as the user's action. More specifically, the calculation unit 42 refers to the arrival query database 32 and selects one arrival query whose appearance probability is not calculated as a processing target. Subsequently, the calculation unit 42 refers to the query log database 31 and counts the number of times that the same search query as the reaching query selected as the processing target is included in the query log (hereinafter referred to as “parameter”). . In addition, the calculation unit 42 identifies the arrival query input by the reaching user from the query log, and the number of arrival queries selected as a processing target in the identified specific query (hereinafter referred to as “number of children”). Count). Note that the calculation unit 42 may acquire, from the search log server 200 or the like, the number of times each reaching user inputs a reaching query as a processing target as an index.

  Then, the calculation unit 42 calculates a value obtained by dividing the counted number of children by the parameter as the appearance probability of the reaching query selected as the predetermined target. In other words, the calculation unit 42 calculates an index value based on the possibility that the user who has input the selected arrival query reaches a predetermined action or conversion. Thereafter, the calculation unit 42 registers the calculated appearance probability in the arrival query database 32. In addition, the calculation part 42 calculates an appearance probability about all the arrival queries by repeatedly performing the process mentioned above.

  Here, as long as the calculation unit 42 calculates an index value based on the possibility that the user who performed the action reaches the predetermined action for each action of the user, the calculation unit 42 may execute another process. . For example, the calculation unit 42 may calculate an index value based on the possibility that the user who has browsed or selected the content will reach a predetermined behavior for each content that has been viewed or selected by the user as the user's behavior. . More specifically, the calculation unit 42 calculates, for a certain content, a value obtained by dividing the number of times the reaching user has viewed or selected the content by the number of times each user has viewed or selected the content. It may be calculated as an index value. The calculation unit 42 may calculate the index value from the calculated value in consideration of various weightings.

  The specifying unit 43 specifies user actions corresponding to a plurality of groups each having a different inflow distance based on the index value. More specifically, the specifying unit 43 specifies a search query input by a user classified into each group corresponding to a predetermined target.

  For example, the specifying unit 43 refers to the reaching query database 32 and extracts a reaching query corresponding to the target to be processed. Subsequently, the specifying unit 43 specifies the appearance probability of the extracted arrival query. And the specific | specification part 43 specifies the group corresponding to the extracted arrival query according to the value of the specified appearance probability.

  For example, when the arrival query shown in FIG. 4 is registered in the arrival query database 32 as the arrival query corresponding to the target ID “target # 1”, the specifying unit 43 has an appearance probability of the arrival query “company #A Hawaii”. Specify "3.0"%. In such a case, the specifying unit 43 specifies a group in which the value of the item “condition (probability)” satisfies the appearance probability “3.0”% among the groups corresponding to the target ID “target # 1”. For example, when the condition shown in FIG. 5 is registered in the group database 33, the specifying unit 43 determines that the appearance probability of the arrival query “company #A Hawaii” matches the condition of the group indicated by the group ID “group # 3”. Judge that.

  The setting unit 44 sets user actions classified into the groups for a plurality of groups each having a different inflow distance. For example, when the specifying unit 43 determines that the appearance probability of the arrival query “company #A Hawaii” matches the group condition indicated by the group ID “group # 3”, the setting unit 44 sets the group ID “group The arrival query “Company #A Hawaii” is linked to the group indicated by “# 3”. For example, the setting unit 44 associates the target ID “target # 1”, the group ID “group # 3”, and the arrival query “company #A Hawaii” and registers them in the group database 33.

  The accepting unit 45 accepts various requests from the user terminal 100. In such a case, the reception unit 45 identifies a user who uses the user terminal 100 that is the request source, and notifies the classification unit 46 of the identified user.

  The classification unit 46 classifies the user based on the index value calculated for the action performed by the user who is the request source, that is, the user who is the classification target. Specifically, the classification unit 46 classifies the users to be classified into any of a plurality of groups each having a different possibility of reaching a predetermined action. More specifically, the classification unit 46 classifies users into groups that are more likely to reach a predetermined action as the index value calculated for the action performed by the user to be classified is higher.

  For example, the classification unit 46 classifies the user based on the index value calculated for the search query input by the user to be classified. In another example, the classification unit 46 classifies users based on index values calculated for content browsed or selected by users to be classified.

  Hereinafter, an example of processing performed by the classification unit 46 will be described. First, the classification unit 46 refers to the user database 34 and determines whether or not a group corresponding to each target is associated with the user ID indicating the user notified from the reception unit 45. That is, the classification unit 46 determines whether the user has already been classified. And the classification | category part 46 requests | requires information provision to the provision part 47, when the user is classified.

  On the other hand, the classification unit 46 executes the following process when the user is not classified. First, the classification unit 46 acquires an input query input by a user to be classified within a predetermined period. And the classification | category part 46 specifies the group with the shortest inflow distance with a target among the groups matched with the acquired input query with reference to the group database 33 for every target. For example, when the user has input both the input query “Guam” and the input query “Company #A Hawaii”, the classification unit 46 selects the input from the group corresponding to the target ID “Target # 1”. The group ID “group # 1” associated with the query “Guam” and the group ID “group # 3” associated with the input query “company #A Hawaii” are specified. Then, the classifying unit 46 indicates a group having a closer inflow distance to the target indicated by the target ID “target # 1” among the identified group ID “group # 1” and the group ID “group # 3”. The ID, that is, the group ID “group # 3” is specified. For example, the classification unit 46 sets a group ID of a group having a higher associated “condition (probability)” value among the identified group IDs as a group ID indicating a group having a closer inflow distance to the target. .

  In such a case, the classification unit 46 registers the user ID of the user, the target ID “target # 1”, and the group ID “group # 3” in the user database 34 in association with each other. Further, the classification unit 46 performs the same process for other target IDs, thereby identifying the group to which the user to be classified belongs, and classifying the user. And the classification | category part 46 requests | requires information provision with respect to the provision part 47, when a user is classified also about each target ID.

  The providing unit 47 provides content according to the classification result to the user. More specifically, the providing unit 47 provides the content selected according to the action performed by the user among the contents corresponding to the classification result. For example, the providing unit 47 identifies a target ID and a group ID associated with the request source user from the user database 34. Next, the providing unit 47 refers to the content database 35 and identifies an advertisement associated with the set of target ID and group ID identified from the user database 34. The providing unit 47 distributes the identified advertisement to the requesting user.

  The providing unit 47 can select any targeting technique as to which of the specified advertisements are distributed. For example, when the providing unit 47 specifies a plurality of advertisements associated with the same target ID and group ID pair, the providing unit 47 determines the specified advertisement based on the input query input by the requesting user. An advertisement to be distributed may be further selected from among them, and the selected advertisement may be distributed to the requesting user. For example, the providing unit 47 identifies a small item related to the input query input by the request source user based on the flag registered in the arrival query database 32, and distributes the item according to the identified small item. A target advertisement may be selected. That is, the providing unit 47 may change the content to be distributed in accordance with the appearance probability of the input query input by the requesting user and the contents of the small items corresponding to the input query.

[3. (Concept of classification processing executed by classification device)
Next, the concept of the classification process executed by the classification device 10 will be described with reference to FIG. FIG. 8 is a diagram illustrating the concept of classification processing executed by the classification device according to the embodiment. In the example illustrated in FIG. 8, as an example of the classification process performed by the classification device 10, an index value (that is, an inflow distance) to a target is calculated for each search query, and a search input by a user to be classified. An example of classification processing for classifying users according to the index value of a query has been described.

  First, as shown in FIG. 8A, the classification device 10 calculates a probability that a user who inputs each search query will reach a predetermined action. For example, in the example shown in FIG. 8, the arrival queries entered by each reaching user U10 include arrivals such as “Guam”, “Blog”, “Company #A”, “Waikiki Hotel”, “Pack Tour Company #A”, etc. There is a query. In such a case, the classification device 10 calculates the number of times the arrival user U10 has input each arrival query within a predetermined period until the target arrives (that is, within a predetermined period until a predetermined action is performed). , For each reaching query. On the other hand, the classification device 10 calculates, for each arrival query, the number of times all users U20 have input each arrival query within a predetermined period until the arrival at the target. And the classification | category apparatus 10 makes the appearance probability the value which divided | segmented the frequency | count that the arrival user U10 input the arrival query for every arrival query by the frequency | count that all the users U20 input the arrival query.

  Here, as shown in FIG. 8B, a general search query that is not related to conversion, such as “blog”, that is, a reaching query that is rarely related to the target is a search query that can be generally input. Therefore, it is considered that all users U20 input frequently. For this reason, the value of the appearance probability of a general search query not related to conversion such as “blog” is considered to be a low value to some extent. On the other hand, as shown in FIG. 8C, it is considered that a reaching query having a significant related example of conversion such as “Waikiki Hotel” is input more frequently by the arriving user U01 than all the users U20. It is done. For this reason, the value of the appearance probability of a reaching query having a significant related example with respect to conversion such as “Waikiki Hotel” is considered to be high to some extent.

  Therefore, the classification device 10 specifies the relationship between the reaching query and the target by calculating the appearance probability for each reaching query. Then, as shown in FIG. 8D, the classification device 10 classifies users based on the identification result. For example, the classification device 10 inputs the user U01 to be classified during a predetermined period until the processing (reference time) for classifying the user U01 as shown in FIG. 8E. Get input query. For example, the classification device 10 acquires “baseball”, “Waikiki hotel”, “soccer”, “blog”, and the like.

  Here, it is considered that the input query “baseball” shown in FIG. 8F has little relation to the target. On the other hand, as shown in FIG. 8G, the user U01 has input an input query such as “Waikiki Hotel”. Therefore, the classification device 10 determines the user U01 based on the value of the appearance probability calculated for the “Waikiki Hotel”, that is, the index value of the possibility that the user who has entered “Waikiki Hotel” will be the reaching user U10. Classify. For example, the classification device 10 classifies the user U01 into the group # 2 whose inflow distance to the target is somewhat close.

  As described above, the classification device 10 classifies the user U01 based on an index value indicating that the user who has input the same search query as the input query input by the user U01 may become the reaching user U10. For this reason, the classification device 10 can perform the classification of the user U01 more appropriately.

[4. Example of classification process flow)
Next, an example of the flow of classification processing executed by the classification device 10 will be described with reference to FIGS. FIG. 9 is a flowchart illustrating an example of a process flow for calculating an index value among the classification processes executed by the classification apparatus according to the embodiment. Moreover, FIG. 10 shows an example of the flow of the process which classifies a user according to the index value of the input query which the user who becomes classification | category input among the classification processes which the classification | category apparatus which concerns on embodiment performs. It is a flowchart.

  First, an example of a process flow for calculating an index value will be described with reference to FIG. For example, the classification device 10 acquires a query log (step S101). Subsequently, the classification device 10 acquires an arrival log that is a log of an arrival query for a predetermined target (step S102). Then, the classification device 10 uses the query log and the arrival log to calculate an index value based on the possibility that the user who has input the arrival query reaches a predetermined target for each arrival query (step S103). Then, the classification device 10 associates each arrival query with each group having a different inflow distance to the target based on the calculated index value (step S104), and ends the process.

  Next, an example of a process flow for classifying users will be described with reference to FIG. For example, the classification device 10 determines whether or not a request has been received from the user (step S201). If the request has been received (step S201: Yes), the requesting user has been classified into any group. It is determined whether or not (step S202). If the requesting user is not classified into a group (step S202: No), the classification device 10 identifies an input query input by the user within a predetermined time (step S203), and identifies the input. The users are classified into groups according to the index value of the query (step S204).

  Subsequently, the classification device 10 selects an advertisement corresponding to the group into which the users are classified (Step S205), distributes the selected advertisement (Step S206), and ends the process. On the other hand, if the requesting user has already been classified into any group (step S202: Yes), the classification device 10 executes step S205. On the other hand, if the classification device 10 has not received a request from the user (step S201: No), the classification device 10 waits until it is received.

[5. (Modification)
In the above, an example of the classification process by the classification device 10 has been described. However, the embodiment is not limited to this. Hereinafter, variations of the classification process performed by the classification device 10 will be described.

[5-1. About classification)
The classification device 10 described above classifies users into a plurality of groups with different inflow distances to a target set in advance based on the index value, and distributes advertisements according to the classification results. Here, the classification device 10 may classify each user into an arbitrary number of groups. For example, the classification device 10 may classify users into two groups having different inflow distances to the target, or classify users into an arbitrary number of groups set according to the request of the distribution source of the guidance information. Also good. In the example described above, the classification device 10 calculates an index value for each search query, sets the correspondence between the search query and each group according to the calculated index value, and determines the users U01 and U02 as the users. U01 and U02 were classified into groups associated with the input query. However, the embodiment is not limited to this. For example, the classification device 10 may calculate an index value for each search query and classify the users U01 and U02 based on the index value of the same search query as the input query input by the users U01 and U02. Good. That is, the classification device 10 does not have to associate the group with the search query as long as the user can be classified.

[5-2. (Processing after classification)
Further, the classification device 10 may perform analysis of users or the like in units of groups in which users are classified. For example, suppose that browsing of application pages for trips organized by different companies is regarded as conversion, and the users are classified into groups having different inflow distances until conversion. In such a group, not only the possibility of conversion but also the rate at which competition occurs and the rate at which lost that does not result in conversion differ from group to group.

  Therefore, the classification device 10 may count the ratio at which competition occurs or the ratio at which lost occurs for each group, and provide the counted contents to the advertiser or the like as a report. Further, the classification device 10 may select the content to be distributed according to the content counted for each group, and may change the content content and the distribution mode. For example, the classification device 10 delivers various advertisements for the purpose of enclosure to groups with a long inflow distance but little competition, and discount prices and sales for groups with a short inflow distance but much competition. Processing such as presenting a price may be performed. Further, the classification device 10 delivers advertisements displayed together with web pages to users in groups with a long inflow distance, and direct mail or the like for users in groups with a short inflow distance. , You may push advertisements.

  Moreover, the classification device 10 may measure the conversion depth for each group and execute various processes according to the measured conversion depth. For example, when the classification device 10 is targeted for purchase of a certain product, the classification device 10 calculates a ratio such as whether each user has purchased the product or viewed a web page of the product for each group. In other words, the classification device 10 calculates the ratio of acts with different conversion depths for each group. Then, the classification device 10 may perform advertisement distribution based on the ratio calculated for each group.

[5-3. (Target setting)
The classification device 10 can set an arbitrary action as a target. Here, considering the viewpoint of increasing the number of user behaviors (for example, search queries) for which the index value is calculated, that is, increasing the number of samples, the behavior set as the target has the same purpose. It is better to include as much as possible the same kind of behavior that satisfies. For example, if you want to browse the application page for tours in Hawaii, in order to increase the number of search queries for which index values are calculated, not only tours of a given company, but also tours provided by competitors. Browsing the application page should also be included in the target. As a result, the classification device 10 can increase the number of behaviors for which index values are to be calculated, so that the classification accuracy of the user can be further increased. The target when the classification device 10 calculates an index value for each search query (that is, for each user's action) is various information distributed to the users U01 and U02 after classifying the users U01 and U02. It may be a related target or an unrelated target.

  Further, the classification device 10 may change the period in which the search query and the arrival query used for calculating the index value are input according to the target. For example, in the purchase of condominiums and purchases of high-priced products, it is considered that the time until the user converts is increased. Therefore, the classification device 10 sets a period in which a search query and an arrival query used for calculating an index value are input to a longer period when targeting an act related to real estate or an act of purchasing a high-priced product. May be. For example, the classification device 10 may use a search query input by the reaching user as a reaching query during one month until the reaching user reaches conversion.

In addition, the classification device 10 receives a period in which a search query used for calculating an index value is input among search queries input by each user and a reaching query among search queries input by a reaching user. The period may be set to a different value. For example, the classification device 10 may use a search query input during the past month as a query log, and may use a search query input during one hour until the user reaches conversion as a reaching query.
[5-4. Device configuration〕
The classification device 10 may be communicably connected to an arbitrary number of user terminals 100. The classification device 10 may be realized by a front-end server that exchanges information with the user terminal 100 and a back-end server that selects an input item. In such a case, the acquisition unit 41, the calculation unit 42, the identification unit 43, and the setting unit 44 illustrated in FIG. 2 are arranged in the back-end server, and the reception unit 45, the classification unit 46, and the provision are provided in the front-end server. The part 47 etc. will be arranged. Further, each of the databases 31 to 35 stored in the storage unit 30 may be stored in an external storage server, for example, instead of in the classification device 10.

[5-5. About each database item)
In the above description, the information and information items registered in each of the databases 31 to 35 are merely examples, and any information or item can be registered as long as the above-described classification process can be performed appropriately. May have been.

[5-6. Others]
In addition, among the processes described in the above embodiment, all or part of the processes described as being automatically performed can be performed manually, or the processes described as being performed manually can be performed. All or a part can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  In addition, the above-described embodiments can be appropriately combined within a range in which processing contents are not contradictory.

[6. program〕
Further, the classification device 10 according to the above-described embodiment is realized by a computer 1000 having a configuration as shown in FIG. 11, for example. FIG. 11 is a diagram illustrating an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and an arithmetic device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected via a bus 1090. Have

  The arithmetic device 1030 operates based on a program stored in the primary storage device 1040 and the secondary storage device 1050, a program read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device such as a RAM that temporarily stores data used by the arithmetic device 1030 for various arithmetic operations. The secondary storage device 1050 is a storage device in which data used for various calculations by the calculation device 1030 and various databases are registered, and is realized by a ROM (Read Only Memory), HDD, flash memory, or the like.

  The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information such as a monitor and a printer. For example, USB (Universal Serial Bus), DVI (Digital Visual Interface), This is realized by a standard connector such as HDMI (registered trademark) (High Definition Multimedia Interface). The input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, a keyboard, and a scanner, and is realized by, for example, a USB.

  The input device 1020 includes, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), and a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), and a tape. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. The input device 1020 may be an external storage medium such as a USB memory.

  The network IF 1080 receives data from other devices via the network N and sends the data to the arithmetic device 1030, and transmits data generated by the arithmetic device 1030 to other devices via the network N.

  The arithmetic device 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic device 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040, and executes the loaded program.

  For example, when the computer 1000 functions as the classification device 10, the arithmetic device 1030 of the computer 1000 implements the function of the control unit 40 by executing a program loaded on the primary storage device 1040.

[7. effect〕
As described above, the classification device 10 calculates, for each user action, an index value based on the possibility that the user who performed the action will reach the predetermined action. Then, the classification device 10 classifies the user based on the index value calculated for the action performed by the user to be classified.

  That is, for each user action, the classification device 10 calculates an index value based on the possibility that the user who actually performed the action reaches the target, and the action actually performed by the user to be classified Based on the calculated index value, users are classified. As described above, the classification device 10 calculates the index value based on the actually performed action instead of the preset correspondence, and performs the classification according to the calculated index value. As a result, the classification device 10 can classify the user based on the relationship between the actually performed action and the target, so that the classification accuracy of the user can be improved.

  Moreover, the classification device 10 calculates an index value based on the possibility that the user who has input the search query reaches the predetermined behavior for each search query input by the user as the user's behavior. Then, the classification device 10 classifies the user based on the index value calculated for the search query input by the user to be classified. For this reason, the classification device 10 can appropriately classify the user based on the search query input by the user.

  Moreover, the classification device 10 calculates an index value based on the possibility that the user who browsed or selected the content will reach a predetermined behavior for each content browsed or selected by the user as the behavior of the user. Then, the classification device 10 classifies the user based on the index value calculated for the content browsed or selected by the user to be classified. For this reason, the classification device 10 can appropriately classify the user using the content browsed or selected by the user.

  Further, for each user action, the classification device 10 calculates a ratio of users who have reached the predetermined action among the users who have performed the action, and calculates an index value based on the calculated ratio. Further, for each user action, the classification device 10 calculates, as an index value, a value obtained by dividing the number of times the reaching user has performed the action by the number of times the user has performed the action. In addition, the classification device 10 identifies an action performed by a reaching user during a predetermined period, and an index value based on the possibility that the user who performed the action reaches the predetermined action for each identified action. calculate. As described above, the classification device 10 calculates the index value based on the ratio that the reaching user performs the action for which the index value is calculated. As a result, the classification device 10 can calculate the value of the index value based on the actual measurement, so that the classification accuracy of the user can be further improved.

  Further, the classification device 10 calculates an index value based on the possibility that the user will browse the predetermined content or the index value based on the possibility that the user will select the predetermined content as the index value. For this reason, the classification device 10 can perform grouping of users based on the inflow distance until conversion for browsing or selecting predetermined content.

  Further, the classification device 10 classifies the users to be classified into any of a plurality of groups each having a different possibility of reaching a predetermined action. More specifically, the classification device 10 classifies the user into a group that is more likely to reach a predetermined action as the index value calculated for the action performed by the user to be classified is higher. . As a result, the classification device 10 can perform grouping of users according to the inflow distance to the target.

  In addition, the classification device 10 provides content according to the classification result to the user. For example, the classification device 10 provides the content selected according to the action performed by the user among the contents corresponding to the classification result. In this way, the classification device 10 distributes content according to the group into which the user is classified, not the action itself such as the search query input by the user. For this reason, the classification device 10 can realize the distribution of content to the user according to, for example, the relationship between the user's behavior and conversion and the inflow distance to the target.

  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.

  Moreover, the above-mentioned “section (module, unit)” can be read as “means”, “circuit”, and the like. For example, the classification unit can be read as classification means or a classification circuit.

DESCRIPTION OF SYMBOLS 10 Classification apparatus 20 Communication part 30 Storage part 31 Query log database 32 Arrival query database 33 Group database 34 User database 35 Content database 40 Control part 41 Acquisition part 42 Calculation part 43 Identification part 44 Setting part 45 Reception part 46 Classification part 47 Provision part 100 user terminal

Claims (13)

For each user action, a calculation unit that calculates an index value based on the possibility that the user who performed the action will reach the predetermined action;
A classification apparatus comprising: a classification unit that classifies a user based on an index value calculated for an action performed by a user to be classified. The calculation unit calculates an index value based on a possibility that a user who inputs the search query reaches the predetermined action for each search query input by the user as the user's action,
The classification device according to claim 1, wherein the classification unit classifies the user based on an index value calculated for a search query input by a user to be classified. The calculation unit calculates an index value based on a possibility that the user who browsed or selected the content reaches the predetermined behavior for each content browsed or selected by the user as the user's behavior,
The classification device according to claim 1, wherein the classification unit classifies the user based on an index value calculated for content browsed or selected by a user to be classified. The calculation unit calculates, for each of the user's actions, a ratio of users who have reached the predetermined action among users who have performed the action, and calculates an index value based on the calculated ratio. The classification device according to any one of claims 1 to 3. The calculation unit, for each of the user's actions, calculates a value obtained by dividing the number of times the user has performed the action to the predetermined action by the number of times the user has performed the action. The classification device according to claim 1, wherein the classification device is calculated as follows. The calculation unit identifies an action performed by a user who has reached a predetermined action during a predetermined period, and is based on a possibility that the user who has performed the action reaches the predetermined action for each specified action. An index value is calculated. The classification device according to any one of claims 1 to 5. The calculation unit calculates, as the index value, an index value based on a possibility that the user browses predetermined content or an index value based on a possibility that the user selects predetermined content. The classification device according to claim 1, wherein the classification device is a feature. The said classification | category part classify | categorizes the user who becomes the said classification | category object into either of the several group from which the possibility of reaching the said predetermined | prescribed action differs, respectively. Classification device according to. The classification unit classifies the user into a group that is more likely to reach the predetermined action as the index value calculated for the action performed by the user to be classified is higher. The classification device according to any one of claims 1 to 8. The classification device according to claim 1, further comprising: a providing unit that provides content corresponding to a classification result by the classification unit to the user. The classification device according to claim 10, wherein the providing unit provides the content selected according to the action performed by the user among the contents corresponding to the classification result by the classification unit. A classification method performed by a classification device,
For each user action, a calculation step for calculating an index value based on a possibility that the user who performed the action will reach a predetermined action;
A classification method comprising: a classification step of classifying a user based on an index value calculated for an action performed by a user to be classified. For each user action on the computer, a calculation procedure for calculating an index value based on the possibility that the user who performed the action will reach the predetermined action,
A classification program for executing a classification procedure for classifying a user based on an index value calculated for an action performed by a user to be classified.

Images