JP7164683B1 - Information processing device, information processing method, and information processing program - Google Patents

Abstract

An object of the present invention is to provide an information processing device, an information processing method, and an information processing program capable of appropriately grasping a search query input by a user who has performed a predetermined action before performing the predetermined action. do. An information processing apparatus according to the present application includes an acquisition unit that acquires user information of a user and action information including a search history of the user, and A coefficient calculation unit that calculates a weighting coefficient based on the time difference between when the action is performed and when the user inputs a search query; and a predetermined action based on the search history, the time difference, and the weighting coefficient. and a relevance calculation unit that calculates a relevance to the search query. [Selection drawing] Fig. 4

Description

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

Information service providers that provide services to users via the Internet can obtain various types of data from users. For example, in Patent Document 1, a user who viewed an advertisement is identified from log data, a search keyword entered by the user is extracted, and a score is calculated for each search keyword based on the input frequency of the extracted search keyword. , discloses a technique for presenting search keywords with high scores as search-linked advertisement candidates.

JP 2014-6757 A

However, in the above-described technology, based on the relationship between the search query entered by the user and the viewing of the advertisement, the frequently entered search keyword is presented as the search keyword for the search-linked advertisement. Advertisements cannot be delivered based on a predetermined behavior of, for example, a contract with a mobile telecommunications service provider and a relationship with a search query. Moreover, it is not possible to distribute advertisements in consideration of the temporal relationship between the time when the user inputs a search query and the time when the user performs a predetermined action.

In view of the above problems, the present disclosure provides an information processing device, an information processing method, and an information processing program that can appropriately grasp a search query input by a user who has performed a predetermined action before performing the predetermined action. intended to provide

In order to solve the above-described problems and achieve the object, an information processing apparatus according to the present disclosure includes an acquisition unit that acquires user information of a user and behavior information including a search history of the user; a coefficient calculation unit for calculating a weighting coefficient based on the time difference between the time when the user who performed the action of performs the predetermined action and the time when the user inputs the search query; the search history; a relevance calculation unit that calculates a relevance between the predetermined action and the search query based on the time difference and the weighting factor.

According to one aspect of the embodiments, an information processing device, an information processing method, and an information processing program capable of appropriately grasping a search query input by a user who has performed a predetermined action before performing the predetermined action are provided. can provide.

FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 2 is a diagram showing examples of functions used for weighting coefficients. FIG. 3 is a diagram illustrating a configuration example of an information processing system according to the embodiment; FIG. 4 is a diagram illustrating a configuration example of an information processing apparatus according to the embodiment; 5 is a diagram illustrating an example of information stored in a user information storage unit of the information processing apparatus according to the embodiment; FIG. 6 is a diagram illustrating an example of information stored in an action information storage unit of the information processing apparatus according to the embodiment; FIG. 7 is a diagram illustrating an example of information stored in a degree-of-association storage unit of the information processing apparatus according to the embodiment; FIG. 8 is a diagram illustrating an example of information stored in a function storage unit of the information processing apparatus according to the embodiment; FIG. 9 is a diagram illustrating an example of information stored in a content storage unit of the information processing apparatus according to the embodiment; FIG. FIG. 10 is a diagram illustrating a configuration example of a user terminal according to the embodiment; FIG. 11 is a diagram illustrating a configuration example of a provider terminal according to the embodiment; FIG. 12 is a flowchart illustrating an example of information processing according to the embodiment; FIG. 13 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus.

Embodiments for implementing an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail below with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment.

(embodiment)
[1-1. Example of information processing according to the embodiment]
First, an example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 1 shows an example in which information processing according to an embodiment is executed by an information processing apparatus 100 .

In FIG. 1, the information processing apparatus 100 acquires behavior information including a search query input by a user in a predetermined search service and user information including information about the user, and performs a predetermined search based on the acquired information. Identify the group of users who have performed the behavior of the above, calculate the degree of relevance between the search query entered by the group of users and the predetermined behavior, and select the user who has not performed the predetermined behavior Based on the search query entered by the user and the calculated degree of relevance, the probability that the user will perform a predetermined action is calculated, and information such as content is provided to users whose probability is greater than or equal to a predetermined value. shows an example of delivering An example of information processing according to the embodiment will be described step by step with reference to FIG.

First, the information processing device 100 receives content and request information that the provider terminal 300 has received from the provider M1 (step S1). For example, the information processing apparatus 100 receives content received from the business operator M1 and request information regarding distribution of the content of the business operator M1 from the business operator terminal 300 according to a predetermined action of the user. Here, the request information is information related to the request when the provider distributes the content to the user, and includes "predetermined action", "time when the user performs a predetermined action", and "distribution of content". The information may include information such as the probability that the user will perform a predetermined action as a target condition.

The information processing device 100 acquires user information of users and behavior information of users from a plurality of user terminals 200 (step S2). For example, as shown in FIG. 1, the information processing apparatus 100 acquires user information and behavior information of users from user terminals 200A to 200F of users U1 to U6. Note that the users U1 to U6 and the user terminals 200A to 200F shown in FIG. Information and may be obtained.

The information processing apparatus 100 identifies a specific group, which is a group of users who have performed a predetermined action, from among the users based on the user information and the action information (step S3). For example, the information processing device 100 refers to behavior information of all users, and identifies users who have performed a “predetermined behavior” received from the business operator M1, thereby identifying a specific group. you can

The information processing apparatus 100 calculates the degree of relevance between the search query input by the specific group and the predetermined action in consideration of the time difference (step S4). For example, the information processing apparatus 100 refers to the search history included in the behavior information of the users corresponding to the specific group identified in step S3, and retrieves the search query and the input time entered by the user corresponding to the specific group. read out. The information processing apparatus 100 calculates the time difference between the time when a user corresponding to the specific group performs a predetermined action and the time when each search query is input. The information processing device 100 calculates a weighting factor based on the calculated time difference. Specifically, for example, a weighting factor for a search query that is input after a user corresponding to a specific group performs a predetermined action is calculated as a value of 0 or less, and before the user performs a predetermined action A weighting factor for the entered search query may be calculated as a positive value. The information processing apparatus 100 calculates the degree of association for each search query based on the calculated time difference, weighting coefficient, and search query input frequency. The information processing apparatus 100 calculates a higher degree of association as the input frequency of search queries input by a user who has performed a predetermined action is higher. In addition, since the weighting factor for the search query input before the user performs a predetermined action is a positive value, the more search queries input before the user performs a predetermined action, the higher the degree of relevance is calculated. be done. FIG. 1 shows that the degrees of association of search queries QR#1, QR#2, and QR#3 are calculated to be 0.3, 0.5, and 0.2, respectively.

The information processing apparatus 100 calculates the probability that a user who does not belong to the specific group will perform a predetermined action after a predetermined period of time (step S5). For example, the information processing apparatus 100 refers to the search history included in the behavior information of the user who does not belong to the specific group, and reads the search query and input time input by the user. The information processing apparatus 100 calculates the time difference between the input time of the search query input by the user and the "time when the user performs a predetermined action" included in the request information. The information processing device 100 calculates a weighting factor based on the calculated time difference. The information processing apparatus 100 calculates the probability that the user will perform a predetermined action after a predetermined period of time based on the search query input by the user who does not belong to the specific group, the degree of relevance, and the weighting coefficient. . FIG. 1 shows that the probabilities that the users U2 and U3 perform the predetermined actions are calculated to be 0.7 and 0.6, respectively.

The information processing apparatus 100 determines users whose probability of performing a predetermined action is equal to or greater than a predetermined value as distribution targets (step S6). For example, the information processing apparatus 100 calculates the probability calculated in step S5 based on the value of "the probability that the user performs a predetermined action as a condition for content distribution" included in the request information received from the business operator. may be specified as a distribution target by specifying a user having a value equal to or greater than a predetermined value. Note that FIG. 1 shows that users U2 and U3 have been determined as distribution targets.

The information processing device 100 distributes the content to the user terminal 200 of the user determined as the distribution target (step S7). For example, in step S6, the information processing device 100 distributes the content to the user terminals 200B and 200C of the users U2 and U3 determined as distribution targets.

Thereby, the information processing apparatus 100 considers the temporal relationship between the predetermined behavior and the search query input by the user, estimates the probability that the user will perform the predetermined behavior, and based on the probability, It is possible to identify users who have a high probability of performing a predetermined action, and distribute content to those users. Therefore, for example, the business operator identifies users who are likely to purchase the company's product from among users who have not purchased the company's product, based on the search query entered by the user, and It is possible to target and deliver content to the user concerned. Therefore, the effect of content distribution can be enhanced.

[1-2. Another example 1 of information processing according to the embodiment (normal distribution)]
When the time difference is less than 0, the information processing apparatus 100 calculates the weighting coefficient based on the value of the normal distribution when the time difference is a random variable, and when the time difference is 0 or more, sets the weighting coefficient to a value of 0 or less. Calculate to

This information processing will be described step by step. First, the information processing apparatus 100 executes the same processes as steps S1 to S5 shown in FIG. The processing from steps S1 to S5 is the same as the processing described above. In this information processing, the process of calculating weighting coefficients based on the time difference is specifically specified in steps S4 and S5. The processing concerned will be described below.

The information processing apparatus 100 executes the process up to the process of calculating the time difference between when the user corresponding to the specific group performs a predetermined action and when each search query is input, as in step S4 described above. The information processing device 100 calculates a weighting factor based on the calculated time difference. In this information processing, when the calculated time difference is less than 0, the weighting factor is calculated based on the value of the normal distribution when the time difference is a random variable, and when the time difference is 0 or more, the weighting factor is set to 0. Calculate the following values. That is, the weighting factor for a search query input by a user who has performed a predetermined action after performing a predetermined action is calculated to be a value of 0 or less, and the weighting factor for a search query input before performing a predetermined action is A weighting factor is calculated based on a value of a normal distribution when the time difference is a random variable. After that, the information processing apparatus 100 calculates the degree of association for each search query based on the calculated time difference, weighting coefficient, and search query input frequency. Since the subsequent processing of step S4 is the same as the processing of step S4 described above, the description thereof is omitted.

As in step S5 described above, the information processing apparatus 100 determines the time difference between the input time of the search query input by the user who does not belong to the specific group and the "time when the user performs a predetermined action" included in the request information. Execute up to the calculation process. The information processing device 100 calculates a weighting factor based on the calculated time difference. In this information processing, when the calculated time difference is less than 0, the weighting factor is calculated based on the value of the normal distribution when the time difference is a random variable, and when the time difference is 0 or more, the weighting factor is set to 0. Calculate the following values. Since the time difference in this case is less than 0, the weighting factor is calculated based on the values of the normal distribution. The information processing apparatus 100 calculates the probability that the user will perform a predetermined action at a predetermined time based on the search query input by the user who does not belong to the specific group, the degree of relevance, and the weighting coefficient.

After that, the information processing apparatus 100 executes the same processing as steps S6 to S7 shown in FIG. 1, and distributes the content to the user terminal 200 of the user determined as the distribution target.

As a result, when calculating the degree of association between a search query and a predetermined action, the information processing apparatus 100 calculates the input time of the search query input by the user who performed the predetermined action and the time when the predetermined action was performed. Since the degree of relevance is calculated using a weighting factor according to a normal distribution based on the time difference, the weighting factor is calculated to be a large value the shorter the time difference is input before the predetermined action. Therefore, the degree of relevance calculated based on the weighting coefficient is also input before the predetermined action, and the shorter the time difference between the search queries, the higher the degree of relevance is calculated. As a result, it is possible to more accurately calculate the degree of relevance to a given action, so the probability of users who do not fall into the specific group calculated based on the degree of relevance to perform a given action can also be calculated more accurately. It becomes possible to Therefore, it is possible to accurately identify users who have a high probability of performing a predetermined action, and to distribute content to the identified users, thereby enhancing the effect of content distribution.

[1-3. Another example 2 of information processing according to the embodiment (t distribution)]
When the time difference is less than 0, the information processing apparatus 100 calculates the weighting coefficient based on the value of the normal distribution when the time difference is a random variable, and when the time difference is 0 or more, sets the weighting coefficient to a value of 0 or less. Calculate to

This information processing will be described step by step. First, the information processing apparatus 100 executes the same processes as steps S1 to S5 shown in FIG. The processing from steps S1 to S5 is the same as the processing described above. In this information processing, the process of calculating weighting coefficients based on the time difference is specifically specified in steps S4 and S5. The processing concerned will be described below.

The information processing apparatus 100 executes the process up to the process of calculating the time difference between when the user corresponding to the specific group performs a predetermined action and when each search query is input, as in step S4 described above. The information processing device 100 calculates a weighting factor based on the calculated time difference. In this information processing, when the calculated time difference is less than 0, the weighting factor is calculated based on the value of the t distribution when the time difference is a random variable, and when the time difference is 0 or more, the weighting factor is set to 0. Calculate the following values. That is, the weighting factor for a search query input by a user who has performed a predetermined action after performing a predetermined action is calculated to be a value of 0 or less, and the weighting factor for a search query input before performing a predetermined action is A weighting factor is calculated based on the value of the t distribution when the time difference is a random variable. After that, the information processing apparatus 100 calculates the degree of association for each search query based on the calculated time difference, weighting coefficient, and search query input frequency. Since the subsequent processing of step S4 is the same as the processing of step S4 described above, the description thereof is omitted.

As in step S5 described above, the information processing apparatus 100 determines the time difference between the input time of the search query input by the user who does not belong to the specific group and the "time when the user performs a predetermined action" included in the request information. Execute up to the calculation process. The information processing device 100 calculates a weighting factor based on the calculated time difference. In this information processing, when the calculated time difference is less than 0, the weighting factor is calculated based on the value of the t distribution when the time difference is a random variable, and when the time difference is 0 or more, the weighting factor is set to 0. Calculate the following values. Since the time difference is less than 0, the weighting factor is calculated based on the t-distribution values. The information processing apparatus 100 calculates the probability that the user will perform a predetermined action after a predetermined period of time based on the search query input by the user who does not belong to the specific group, the degree of relevance, and the weighting coefficient. .

As a result, when calculating the degree of association between a search query and a predetermined action, the information processing apparatus 100 calculates the input time of the search query input by the user who performed the predetermined action and the time when the predetermined action was performed. Since the degree of relevance is calculated using a weighting factor corresponding to the t distribution based on the time difference, the weighting factor is calculated to be a large value the shorter the time difference is input before the predetermined action. Therefore, the degree of relevance calculated based on the weighting coefficient is also input before the predetermined action, and the shorter the time difference between the search queries, the higher the degree of relevance is calculated. As a result, it is possible to more accurately calculate the degree of relevance to a given action, so the probability of users who do not fall into the specific group calculated based on the degree of relevance to perform a given action can also be calculated more accurately. It becomes possible to Therefore, it is possible to accurately identify users who have a high probability of performing a predetermined action, and to distribute content to the identified users, thereby enhancing the effect of content distribution.

[1-4. Another example 3 of information processing according to the embodiment (function according to search frequency)]
The information processing apparatus 100 calculates a weighting factor using a function based on the search frequency according to the time difference for each search query.

This information processing will be described step by step. First, the information processing apparatus 100 executes the same processes as steps S1 to S5 shown in FIG. The processing from steps S1 to S5 is the same as the processing described above. In this information processing, the process of calculating weighting coefficients based on the time difference is specifically specified in steps S4 and S5. The processing concerned will be described below.

The information processing apparatus 100 executes the process up to the process of calculating the time difference between when the user corresponding to the specific group performs a predetermined action and when each search query is input, as in step S4 described above. The information processing device 100 calculates a weighting factor based on the calculated time difference. In this information processing, a function of a weighting coefficient with the time difference as a variable is derived based on the search frequency and the time difference for each search query. In other words, draw a graph with the time difference on the horizontal axis and the search frequency on the vertical axis for each search query entered by a user who corresponds to a specific group, derive an approximate curve that closely matches the graph, and use the approximation Let the curve be a function of the weighting factors. For example, an approximation curve such as that shown in FIG. 2 may be used as a function of the weighting factors.

FIG. 2 is a diagram showing examples of functions used for weighting coefficients. As shown in example 1 of FIG. 2, for example, when the search frequency is high three days before the user performs a predetermined action, and the search frequency decreases as the time of the user's predetermined action approaches, three days before An approximation curve resembling the shape of a normal distribution with vertices may be used as a function of the weighting factors. Further, as shown in Example 2 of FIG. 2, for example, when the search frequency is extremely high four days before the user performs a predetermined action, and the search frequency becomes lower as the user performs the predetermined action, the search frequency becomes lower. , an approximation curve similar to the shape of a normal distribution with a high degree of kurtosis with an apex four days ago may be used as a function of the weighting factor. Further, as shown in Example 3 of FIG. 2, for example, the search frequency gradually increases three days before and two days before the user performs a predetermined action, and the search frequency reaches its highest value three days before and two days before. After that, if the search frequency becomes lower as the time point of performing a predetermined action approaches, an approximate curve similar to the shape of a normal distribution with negative skewness with peaks 3 days ago and 2 days ago is used as a function of the weighting factor. good. Further, as shown in Example 4 of FIG. 2, for example, the search frequency sharply rises 5 days before and 4 days before the user performs a predetermined action, and the search frequency reaches its highest value 5 days before and 4 days before. After that, if the search frequency gradually decreases as the point in time when the predetermined action is taken is approached, an approximate curve resembling the shape of a normal distribution with a positive degree of skewness with peaks five and four days before is used as the weighting factor. can be a function. Although not shown in examples 1 to 4 described above, a function is used in which the time difference is a positive value, that is, the weighting coefficient after performing a predetermined action has a value of 0 or less.

After that, the information processing apparatus 100 calculates the degree of association for each search query based on the calculated time difference, weighting coefficient, and search query input frequency. Since the subsequent processing of step S4 is the same as the processing of step S4 described above, the description thereof is omitted.

As in step S5 described above, the information processing apparatus 100 determines the time difference between the input time of the search query input by the user who does not belong to the specific group and the "time when the user performs a predetermined action" included in the request information. Execute up to the calculation process. The information processing device 100 calculates a weighting factor based on the calculated time difference. In this information processing, the weighting factor is calculated using the function derived for each search query in step S4. That is, the weighting factor is calculated from the weighting factor function according to the time difference. Since the time difference is less than 0, the weighting coefficient is calculated as a positive value. The information processing apparatus 100 calculates the probability that the user will perform a predetermined action at a predetermined time based on the search query input by the user who does not belong to the specific group, the degree of relevance, and the weighting coefficient.

As a result, the information processing apparatus 100 derives the function of the weighting coefficient as a function with the time difference as a variable for each search query, so that the degree of association between the search query and the predetermined action can be calculated more accurately. In addition, the probability that a user who has not performed a predetermined action will perform a predetermined action at a predetermined time is calculated using a weighting coefficient derived as a function with the time difference as a variable for each search query, so it is more accurate. , the probability can be calculated. Therefore, it is possible to accurately identify users who have a high probability of performing a predetermined action, and to distribute content to the identified users, thereby enhancing the effect of content distribution.

[2. Configuration of information processing system]
Next, the configuration of the information processing system according to the embodiment will be described using FIG. FIG. 3 is a diagram illustrating a configuration example of an information processing system according to the embodiment; As shown in FIG. 3 , the information processing system 1 includes an information processing device 100 , a user terminal 200 and a business operator terminal 300 . The information processing system 1 shown in FIG. 3 may include a plurality of information processing apparatuses 100 , a plurality of user terminals 200 , and a plurality of business operator terminals 300 . The information processing device 100, the user terminal 200, and the operator terminal 300 are connected to communicate by wire or wirelessly via a predetermined communication network (network N).

The information processing apparatus 100 may be an information processing apparatus such as a PC (Personal Computer), a WS (Work Station), or a computer having server functions. The information processing device 100 performs processing based on information transmitted via the network N from the user terminal 200 and the operator terminal 300 .

A user terminal 200 is an information processing device used by a user. The user terminal 200 may be, for example, an information processing device such as a smart phone, tablet terminal, desktop PC, notebook PC, mobile phone, PDA (Personal Digital Assistant). Note that the example shown in FIG. 1 shows a case where the user terminal 200 is a smart phone.

The operator terminal 300 is an information processing device used by the operator. The business terminal 300 may be, for example, an information processing device such as a smart phone, a tablet terminal, a desktop PC, a notebook PC, a mobile phone, or a PDA. Note that the example shown in FIG. 1 shows a case where the business terminal 300 is a notebook PC.

[3. Configuration of Information Processing Device]
Next, the configuration of the information processing apparatus 100 according to the embodiment will be described using FIG. FIG. 4 is a diagram illustrating a configuration example of an information processing apparatus according to the embodiment; As shown in FIG. 4, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit . Although not shown in FIG. 4, the information processing apparatus 100 includes an input unit (for example, a keyboard, a mouse, etc.) for receiving various operations from an administrator of the information processing apparatus 100, and a display for displaying various information. You may have a part (for example, a liquid crystal display etc.).

(Regarding communication unit 110)
The communication unit 110 is implemented by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information between the user terminal 200 and the operator terminal 300 .

(Regarding storage unit 120)
The storage unit 120 is implemented by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk, SSD (Solid State Drive), or optical disc. As shown in FIG. 4 , the storage unit 120 has a user information storage unit 121 , an action information storage unit 122 , a degree of association storage unit 123 , a function storage unit 124 and a content storage unit 125 .

(Regarding the user information storage unit 121)
The user information storage unit 121 stores information about users. Here, an example of information stored by the user information storage unit 121 will be described with reference to FIG. 5 is a diagram illustrating an example of information stored in a user information storage unit of the information processing apparatus according to the embodiment; FIG.

In the example shown in FIG. 5, the user information storage unit 121 associates and stores information related to items such as "user ID", "date of birth", "sex", and "occupation".

A “user ID” is an identifier that identifies a user and is represented by a character string, number, or the like. “Date of birth” is information related to the date of birth of the user associated with the “user ID”. “Gender” is information about the gender of the user associated with the “user ID”. "Occupation" is information on the occupation of the user linked to the "user ID".

That is, in FIG. 5, the date of birth of the user identified by the user ID “UID #1” is “date of birth #U1”, the gender is “female”, and the occupation is “occupation #U1”. ”.

The information stored in the user information storage unit 121 is not limited to information related to items such as "user ID", "date of birth", "sex", and "occupation". of users may be stored.

(Regarding the action information storage unit 122)
The behavior information storage unit 122 stores information about the behavior history of the user. Here, an example of information stored by the behavior information storage unit 122 will be described with reference to FIG. 6 is a diagram illustrating an example of information stored in an action information storage unit of the information processing apparatus according to the embodiment; FIG.

In the example shown in FIG. 6, the action information storage unit 122 stores information related to the items "user ID", "search history", "browsing history", "purchase history", "route search history", and "bulletin board posting history". Link and store information.

A “user ID” is an identifier that identifies a user and is represented by a character string, number, or the like. “Search history” is information including search queries used for searches by users associated with “user IDs” and input times. "Browsing history" is information including the browsing site and browsing time of the user's website associated with the "user ID". “Purchase history” is information including the purchased product or purchased service and the purchase time on the Internet mail-order site or the predetermined service contract site of the user associated with the “user ID”. "Route search history" is information including route search results and search times of users associated with "user IDs". “Bulletin board posting history” is information including bulletin board postings and posting times of users associated with “user IDs”.

That is, in FIG. 6, the search history of the user identified by the user ID "UID#1" is "search history #U1", the browsing history of the user is "browsing history #U1", and the purchase history is "browsing history #U1". It indicates that the history is "purchase history #U1", the route search history is "route search history #U1", and the bulletin board posting history is "bulletin board posting history #U1".

The information stored in the action information storage unit 122 relates to the items "user ID", "search history", "browsing history", "purchase history", "route search history", and "posting history on bulletin board". It is not limited to information, and any other information related to user behavior may be stored.

(Regarding the degree of association storage unit 123)
The degree-of-relevance storage unit 123 stores the degree of relevance between each action of the user and the search query. Here, an example of information stored in the degree-of-association storage unit 123 will be described with reference to FIG. 7 is a diagram illustrating an example of information stored in a degree-of-association storage unit of the information processing apparatus according to the embodiment; FIG.

In the example shown in FIG. 7, the degree-of-relevance storage unit 123 associates and stores information related to the items "behavior type", "search query", and "degree of relevance".

"Action type" is information indicating a predetermined action of the user. The predetermined action of the user indicated by the action type corresponds to the "predetermined action" specified as the request information by the operator, and indicates the action stored as the action history in the action information storage unit 122. . “Search query” is information indicating a search query input by a user who performed a predetermined action indicated in “action type”. “Relevance” is information indicating the degree of relevance between a predetermined action indicated by “action type” and a search query indicated by “search query”.

That is, FIG. 7 shows that the degree of association between the user's behavior indicated by the behavior type "AC#1" and the search query indicated by the search query "QR#1" is 0.3.

The information stored in the degree-of-relevance storage unit 123 is not limited to information related to items such as “behavior type”, “search query”, and “degree of relevance”. Information may be stored.

(Regarding function storage unit 124)
The function storage unit 124 stores a weighting coefficient function used when calculating the degree of association between a user's predetermined behavior and a search query. An example of information stored in the function storage unit 124 will now be described with reference to FIG. 8 is a diagram illustrating an example of information stored in a function storage unit of the information processing apparatus according to the embodiment; FIG.

In the example shown in FIG. 8, the function storage unit 124 associates and stores information related to the items "function ID", "search query", and "function data".

"Function ID" is an identifier for identifying each function and is represented by a character string or number. "Search query" is information indicating a search query for calculating a weighting factor when calculating the degree of association by a function identified by "function ID". "Function data" is information indicating data of the function identified by the "function ID". That is, "function data" stores data of a function for outputting a weighting coefficient with the time difference as a variable. For example, it may be data in which the value of the time difference and the value of the weighting factor are associated one-to-one in a table format and stored.

That is, in FIG. 8, the function indicated by the function ID "FN#1" is associated with the search query indicated by the search query "QR#1", and the function data indicated by the function data "FD#1" is stored. It is shown that

Note that the information stored in the function storage unit 124 is not limited to information related to the items "function ID", "search query", and "function data", and is related to other arbitrary weighting coefficient functions. Information to do may be stored.

(Regarding the content storage unit 125)
The content storage unit 125 stores the content input by the provider received from the provider terminal 300 . 9 is a diagram illustrating an example of information stored in a content storage unit of the information processing apparatus according to the embodiment; FIG.

In the example shown in FIG. 9 , the content storage unit 125 associates and stores information related to the items “enterprise ID”, “content ID”, “content data”, and “behavior type”.

"Business ID" is an identifier that identifies a business and is represented by a character string, number, or the like. The “content ID” is an identifier for identifying content received from the business operator, and is represented by a character string, number, or the like. "Content data" is data of contents that the business wishes to distribute. The “behavior type” is information indicating a predetermined behavior of a user that serves as a criterion for selecting users to whom the provider wishes to distribute content.

That is, in FIG. 9 , the content data indicated by the content data “CD#1” as the content identified by the content ID “CT#1” is transferred from the business indicated by the business ID “M1” to the action type “AC #1” is specified and input to the operator terminal 300, accepted by the reception unit 132 of the information processing device 100, and stored in the content storage unit 125.

Note that the content storage unit 125 is not limited to information related to items such as "enterprise ID", "content ID", "content data", and "behavior type", and can store information related to any other content. may be stored.

(Regarding the control unit 130)
Next, returning to FIG. 3, the control unit 130 will be described. The control unit 130 is realized by executing various programs stored in the storage device of the information processing apparatus 100 by using a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like, using the RAM as a work area. Also, the control unit 130 may be realized by an integrated circuit such as an ASIC (Application Specific Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3 , control unit 130 includes acquisition unit 131 , reception unit 132 , identification unit 133 , calculation unit 134 , determination unit 135 , distribution unit 136 , and output unit 137 .

(Regarding the acquisition unit 131)
The acquisition unit 131 acquires user information and behavior information from the user terminal 200 . Here, the user information is information about the user, for example, information provided to an information service provider when the user uses a predetermined information service. Further, the action information is information indicating the user's action using the predetermined information service caused by the use of the user's predetermined information service. After obtaining the user information, the obtaining unit 131 stores the obtained user information in the user information storage unit 121 . After obtaining the behavior information, the obtaining unit 131 stores the obtained behavior information in the behavior information storage unit 122 . Note that the acquisition unit 131 may acquire one or both of the user information and the behavior information at predetermined dates and times, or acquire the user information each time the user accesses the information processing apparatus 100 . , and behavior information, or both.

(Regarding the reception unit 132)
The reception unit 132 receives content input by the operator from the operator terminal 300 of the operator. Upon receiving content from the operator terminal 300 , the receiving unit 132 stores the received content in the content storage unit 125 .

The reception unit 132 also receives request information input by the business operator from the business operator terminal 300 . Upon receiving the request information from the operator terminal 300, the receiving unit 132 outputs the received request information to the identifying unit 133 and the calculating unit 134 so as to be used in the processing of the identifying unit 133 and the calculating unit 134. FIG.

(Regarding the specifying unit 133)
The specifying unit 133 specifies a user who has performed a predetermined action based on the user information and the action information. For example, when the operator has specified and entered a contract with the mobile phone carrier A as the "predetermined action" included in the request information, the specifying unit 133 By referring to the purchase history included in the action information, the user who made a "contract with mobile phone carrier A" is identified. After identifying the users who have made a contract with the mobile phone carrier A, the identifying unit 133 sorts out the identified users as a specific group and outputs it to the calculating unit 134 .

Further, the identifying unit 133 identifies users who have performed a predetermined action, organizes the identified users into a specific group, and then organizes users who have not performed a predetermined action into a non-specific group.

(Regarding the calculator 134)
The calculator 134 includes a coefficient calculator 1341 , a degree-of-association calculator 1342 , and a probability calculator 1343 .

The coefficient calculation unit 1341 calculates a weighting coefficient based on the time difference between when the user who has performed a predetermined action performs the predetermined action and when the user inputs a search query. For example, if the time difference is a positive value, the weighting factor may be calculated as a value of 0 or less, and if the time difference is a negative value, the weighting factor may be calculated as a positive value. As a result, when calculating the degree of relevance, it is possible to calculate a low degree of relevance of a search query that is input after a predetermined action that is considered to have a low degree of relevance to the predetermined action of the user.

In addition, when the time difference is less than 0, the coefficient calculation unit 1341 calculates a weighting coefficient based on the value of the normal distribution when the time difference is a random variable, and when the time difference is 0 or more, the weighting coefficient is 0 or less. calculated to the value of That is, the coefficient calculation unit 1341 calculates the weighting coefficient using the value of the portion that progresses toward the bottom of the normal distribution, the earlier the time at which the search query is input from the time at which the predetermined action is performed. do. It should be noted that the apex of the normal distribution is located at the position where the time difference is 0 when the time difference is a random variable. That is, the mean μ of the normal distribution is 0. Also, the variance σ of the normal distribution may be any value. When the time difference is 0 or more, the coefficient calculator 1341 calculates the weighting coefficient to a value of 0 or less. As a result, it is possible to calculate a low weighting factor used for calculating the degree of relevance of a search query input by the user after the predetermined action, which is considered to have a low degree of relevance to the user's predetermined action.

In addition, when the time difference is less than 0, the coefficient calculation unit 1341 calculates a weighting coefficient based on the value of the t distribution when the time difference is a random variable, and when the time difference is 0 or more, the weighting coefficient is 0 or less. calculated to the value of That is, the coefficient calculation unit 1341 calculates the weighting coefficient using the value of the part that progresses toward the bottom of the t distribution, the earlier the time at which the search query is input from the time at which the predetermined action is performed. do. Note that the apex of the t-distribution is located at a position where the time difference is 0 when the time difference is a random variable. Also, the degree of freedom ν of the t-distribution may be any value. When the time difference is 0 or more, the coefficient calculator 1341 calculates the weighting coefficient to a value of 0 or less. As a result, it is possible to calculate a low weighting factor used for calculating the degree of relevance of a search query input by the user after the predetermined action, which is considered to have a low degree of relevance to the user's predetermined action.

In addition, the coefficient calculation unit 1341 derives a weighting coefficient function with the time difference as a variable based on the search frequency and the time difference for each search query, and performs weighting based on the time difference and the function of the weighting coefficient for each search query. Calculate the coefficient. That is, the coefficient calculation unit 1341 draws a graph with the time difference on the horizontal axis and the search frequency on the vertical axis for each search query input by the user corresponding to the specific group, and draws an approximate curve that closely matches the graph. and make the relevant approximation curve a function of the weighting factors. The coefficient calculator 1341 calculates the weighting coefficient based on the time difference using the derived weighting coefficient function.

The degree-of-relevance calculator 1342 calculates the degree of relevance between a predetermined action and a search query based on the search history, the time difference, and the weighting coefficient. The degree-of-association calculation unit 1342 reads from the behavior information storage unit 122 search histories of users who have performed predetermined behaviors. Next, the degree-of-association calculation unit 1342 calculates the time difference between the point in time when the user who performed the predetermined action performed the predetermined action and the point in time when each search query was input. Next, the degree-of-association calculator 1342 calculates a weighting factor based on the time difference calculated for each search query. Next, the relevance calculation unit 1342 calculates the relevance by multiplying the value obtained by multiplying the calculated weighting factor by 1 by the number of times each search query is input. That is, the higher the value of the weighting factor and the higher the number of times each search query is input, the higher the degree of association is calculated. After calculating the degree of association, the degree-of-association calculation unit 1342 stores the calculated degree of association in the degree-of-association storage unit 123 .

The probability calculation unit 1343 calculates the probability that the user who has not performed the predetermined action will perform the predetermined action based on the search query input by the user who has not performed the predetermined action, the weighting coefficient, and the degree of association. calculate. The probability calculation unit 1343 reads the search history of users who have not performed a predetermined action from the action information storage unit 122 for each user. Next, the probability calculation unit 1343 calculates the time difference based on the input time of each search query by the user who has not performed the predetermined action and the "time when the user performs the predetermined action" included in the request information. calculate. Next, the probability calculator 1343 calculates a weighting factor based on the calculated time difference.

In this process, if the time difference is less than 0, the weighting factor is calculated based on the value of the normal distribution when the time difference is a random variable, and if the time difference is 0 or more, the weighting factor is 0 or less. can be calculated to the value of When the time difference is less than 0, the weighting factor is calculated based on the value of the t distribution when the time difference is a random variable, and when the time difference is 0 or more, the weighting factor is calculated to be 0 or less. good too. Alternatively, for each search query, based on the search frequency and the time difference, derive a weighting coefficient function with the time difference as a variable, and calculate the weighting coefficient based on the time difference and the weighting coefficient function for each search query. good.

Next, the probability calculation unit 1343 multiplies the number of searches for each search query, the calculated weighting coefficient, and the degree of relevance for each search query to Calculate the probability of performing the action of

(About decision unit 135)
The determination unit 135 determines the users to whom the content is to be distributed based on the probability that the user who has not performed the predetermined behavior will perform the predetermined behavior calculated by the probability calculation unit 1343 . That is, the determination unit 135 determines that the probability that the user who has not performed the predetermined behavior, calculated by the probability calculation unit 1343, will perform the predetermined behavior is included in the request information. A user whose probability of performing a predetermined action is equal to or higher than the value of "probability of performing a predetermined action" is determined as a content distribution target.

(Regarding the distribution unit 136)
The distribution unit 136 distributes the content to the user terminal 200 of the user determined by the determination unit 135 as the content distribution target. For example, when the determination unit 135 determines the user U2 and the user U3 as content distribution targets, the distribution unit 136 reads the content input by the operator from the content storage unit 125 and transmits the content via the communication unit 110. Then, the user terminal 200B of user U2 and the user terminal 200C of user U3 are distributed.

(Regarding the output unit 137)
The output unit 137 outputs the degree of association between the predetermined action of the user and the search query calculated by the degree-of-association calculation unit 1342 . That is, after the degree-of-relevance calculation unit 1342 calculates the degree of relevance based on the “predetermined action” included in the request information input by the business operator, the output unit 137 outputs the degree of relevance stored in the degree-of-relevance storage unit 123. , is read from the degree-of-association storage unit 123 and transmitted to the operator terminal 300 via the communication unit 110 . This enables the business operator to know the search query that the user has entered before performing a predetermined action.

[4. Configuration of user terminal]
Next, the configuration of the user terminal 200 according to the embodiment will be described using FIG. FIG. 10 is a diagram illustrating a configuration example of a user terminal according to the embodiment; As shown in FIG. 10, the user terminal 200 has a communication section 210, an input section 220, an output section 230, and a control section 240.

The communication unit 210 is implemented by, for example, a NIC. The communication unit 210 is connected to the network N by wire or wirelessly, and transmits and receives various information to and from the information processing apparatus 100 via the network N.

The input unit 220 receives various kinds of operation information from the user. For example, the input unit 220 may receive various operations from the user via the display surface (for example, the output unit 230) of a touch panel. The input unit 220 may also receive various operations from buttons provided on the user terminal 200 or from a keyboard or mouse connected to the user terminal 200 .

The output unit 230 is, for example, a display screen of a tablet terminal realized by a liquid crystal display, an organic EL (Electro-Luminescence) display, or the like, and is a display device for displaying various information. In other words, when the input unit 220 is a touch panel, the user terminal 200 accepts input from the user through the display screen, which is the output unit 230, and outputs the input to the user. Also, the output unit 230 is a speaker, and may output sound through the speaker.

The control unit 240 is realized, for example, by executing various programs stored in the user terminal 200 using the RAM as a work area by means of a CPU, MPU, or the like. Also, the control unit 240 may be implemented by an integrated circuit such as an ASIC or FPGA, for example.

As shown in FIG. 10 , the control section 240 has a providing section 241 .

The providing unit 241 provides the content distributed from the information processing apparatus 100 to the user. For example, when the content distributed from the information processing apparatus 100 is a moving image, the providing unit 241 causes the output unit 230 to output the moving image and provides the content to the user. Further, for example, when the content distributed from the information processing apparatus 100 is audio, the providing unit 241 may provide the content to the user by causing the output unit 230 to output the audio of the content. Further, for example, when the content distributed from the information processing apparatus 100 is text data, the providing unit 241 may display the text on the output unit 230 to provide the content to the user.

[5. Configuration of operator terminal]
Next, the configuration of the operator terminal 300 according to the embodiment will be described with reference to FIG. 11 . FIG. 11 is a diagram illustrating a configuration example of a provider terminal according to the embodiment; As shown in FIG. 11 , the operator terminal 300 has a communication section 310 , an input section 320 , an output section 330 and a control section 340 .

The communication unit 310 is implemented by, for example, a NIC. The communication unit 310 is connected to the network N by wire or wirelessly, and transmits and receives various information to and from the information processing apparatus 100 via the network N.

The input unit 320 receives various kinds of operation information from the operator. For example, the input unit 320 may receive various operations of the operator from a keyboard or mouse connected to the operator terminal 300 . Further, the input unit 320 may receive various operations from the operator via the display surface (for example, the output unit 330) of the touch panel.

The output unit 330 is a display screen realized by, for example, a liquid crystal display or an organic EL display, and is a display device for displaying various information. When the input unit 320 of the business operator terminal 300 receives various operations from the business operator via the touch panel, the display screen serving as the output unit 330 receives input from the user and outputs to the user.

The control unit 340 is implemented, for example, by executing various programs stored in the business operator terminal 300 using the RAM as a work area, using a CPU, MPU, or the like. Also, the control unit 340 may be implemented by an integrated circuit such as an ASIC or FPGA, for example.

As shown in FIG. 11 , the control section 340 has a reception section 341 .

The reception unit 341 receives content from businesses. The content may be, for example, data including characters, voice, still images, moving images, etc. advertising products and services of the business. In addition, if the business operator is an information service provider, search service, shopping service, payment service, route search service, map provision service, travel service, restaurant introduction service, weather forecast service, schedule management service, news provision service , auction service, video content distribution service, financial transaction (stock trading, etc.) service, and the like.

For example, the reception unit 341 receives content in association with a “predetermined action” included in request information from a business operator. In other words, the reception unit 341 receives the operator ID that identifies the operator, the data indicating the content, and the "predetermined action" of the user to whom the operator wishes to distribute the content, in association with each other.

Also, the reception unit 341 receives request information from the business operator. Here, the request information is, as described above, information related to a request when the provider distributes the content to the user, and includes "predetermined action", "time when the user performs a predetermined action", " The information may include information such as the probability that the user will perform a predetermined action as a condition for content distribution.

[6. Information processing flow]
Next, a procedure for information processing by the information processing apparatus 100 according to the embodiment will be described with reference to FIG. 12 . FIG. 12 is a flowchart illustrating an example of information processing according to the embodiment; For example, the information processing device 100 receives content and request information from the provider terminal 300 (step S101). Then, the information processing device 100 acquires user information and action information from the user terminal 200 (step S102). Then, the information processing apparatus 100 identifies a specific group, which is a group of users who have performed a predetermined action, from among the users (step S103). Then, the information processing apparatus 100 calculates the degree of association between the search query input by the specific group and the predetermined action in consideration of the time difference (step S104). Then, the information processing apparatus 100 calculates the probability that users who do not belong to the specific group perform a predetermined action at a predetermined time (step S105). Then, the information processing apparatus 100 determines users whose probability of performing a predetermined action is equal to or greater than a predetermined value as distribution targets (step S106). Then, the information processing apparatus 100 distributes the information to the user determined as the distribution target (step S107).

[7. Hardware configuration]
Also, the information processing apparatus 100 according to the above-described embodiment is implemented by a computer 1000 configured as shown in FIG. 13, for example. FIG. 13 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus. A 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 by a bus 1090. have

The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs 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 calculations. The secondary storage device 1050 is a storage device in which data used for various calculations by the arithmetic device 1030 and various databases are stored. It is realized by

The output IF 1060 is an interface for transmitting information to be output to the output device 1010 that outputs various types of information such as a monitor and a printer. It is realized by a connector conforming to a standard such as HDMI (registered trademark) (High Definition Multimedia Interface). Also, the input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, keyboard, scanner, etc., and is realized by, for example, USB.

Note that the input device 1020 includes, for example, optical recording media such as CDs (Compact Discs), DVDs (Digital Versatile Discs), PDs (Phase change rewritable discs), magneto-optical recording media such as MOs (Magneto-Optical discs), and tapes. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. Also, the input device 1020 may be an external storage medium such as a USB memory.

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

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, arithmetic device 1030 loads a program from input device 1020 or secondary storage device 1050 onto primary storage device 1040 and executes the loaded program.

For example, when the computer 1000 functions as the information processing device 100, the arithmetic device 1030 of the computer 1000 implements the functions of the control unit 130 of the information processing device 100 by executing a program loaded on the primary storage device 1040. do.

[8. Configuration and effect]
The information processing apparatus 100 according to the present disclosure includes an acquisition unit 131 that acquires user information of a user and behavior information including a search history of the user, and and the time when the user inputs a search query, a coefficient calculation unit 1341 that calculates a weighting coefficient based on the time difference, and a predetermined action based on the search history, the time difference, and the weighting coefficient. and a relevance calculation unit 1342 that calculates the relevance to the search query.

According to this configuration, it is possible to appropriately grasp the search query input by the user who has performed the predetermined action before performing the predetermined action.

Further, the information processing apparatus 100 according to the present disclosure allows a user who has not performed a predetermined action to perform a predetermined and a probability calculation unit 1343 that calculates the probability of performing the action of .

According to this configuration, the probability that a user who has not performed a predetermined action will perform a predetermined action is estimated in consideration of the temporal relationship between the user's predetermined action and the search query input by the user. can do.

In addition, when the time difference is less than 0, the coefficient calculation unit 1341 of the information processing device 100 according to the present disclosure calculates a weighting coefficient based on the value of the normal distribution when the time difference is a random variable, and the time difference is 0 or more. , the weighting factor is calculated to be a value of 0 or less.

According to this configuration, when calculating the degree of association between a search query and a predetermined action, the time difference between the input time of the search query input by the user who performed the predetermined action and the time when the predetermined action was performed Since the degree of association is calculated using a weighting coefficient according to the normal distribution based on the above, the weighting coefficient is calculated to be a large value as the time difference is shorter and the input is made before the predetermined action. Therefore, the degree of relevance calculated based on the weighting coefficient is also input before the predetermined action, and the shorter the time difference between the search queries, the higher the degree of relevance is calculated. As a result, it is possible to more accurately calculate the degree of relevance to a given action, so the probability of users who do not fall into the specific group calculated based on the degree of relevance to perform a given action can also be calculated more accurately. It becomes possible to

In addition, when the time difference is less than 0, the coefficient calculation unit 1341 of the information processing apparatus 100 according to the present disclosure calculates a weighting coefficient based on the value of the t distribution when the time difference is a random variable, and the time difference is 0 or more. , the weighting factor is calculated to be a value of 0 or less.

According to this configuration, when calculating the degree of association between a search query and a predetermined action, the time difference between the input time of the search query input by the user who performed the predetermined action and the time when the predetermined action was performed Since the degree of association is calculated using a weighting factor according to the t distribution based on the above, the weighting factor is calculated to be a large value as the time difference is shorter and the input is made before the predetermined action. Therefore, the degree of relevance calculated based on the weighting coefficient is also input before the predetermined action, and the shorter the time difference between the search queries, the higher the degree of relevance is calculated. As a result, it is possible to more accurately calculate the degree of relevance to a given action, so the probability of users who do not fall into the specific group calculated based on the degree of relevance to perform a given action can also be calculated more accurately. It becomes possible to

In addition, the coefficient calculation unit 1341 of the information processing apparatus 100 according to the present disclosure derives a weighting coefficient function with the time difference as a variable based on the search frequency and the time difference for each search query, and the time difference and each search query. A weighting factor is calculated based on a function of the weighting factor of .

According to this configuration, since the function of the weighting coefficient is derived as a function with the time lag as a variable for each search query, it is possible to more accurately calculate the degree of association between the search query and the predetermined action. In addition, the probability that a user who has not performed a predetermined action will perform a predetermined action after a predetermined time is calculated using a weighting coefficient derived as a function with the time difference as a variable for each search query. Probability can be calculated accurately.

In addition, the information processing apparatus 100 according to the present disclosure determines users to whom content is distributed based on the probability that a user who has not performed a predetermined action will perform a predetermined action calculated by the probability calculation unit 1343. It further includes a determination unit 135 and a distribution unit 136 that distributes content to the user terminal 200 of the user determined by the determination unit 135 .

According to this configuration, it is possible to identify a user who has a high probability of performing a predetermined action, and distribute content to the identified user, thereby enhancing the effect of content distribution.

Further, the information processing method according to the present disclosure includes a step of acquiring user information of a user and action information including a search history of the user, and calculating a weighting factor based on the time difference between the time when the search query was performed and the time when the user entered the search query; A step of calculating a degree of relevance, and a user who has not performed a predetermined action performs a predetermined action based on a search query input by a user who has not performed a predetermined action, a weighting coefficient, and a degree of relevance. It includes a step of calculating the probability, a step of determining a user to whom content is to be distributed based on the probability, and a step of distributing information to the user terminal 200 of the determined user.

According to the information processing method with this configuration, the probability that the user will perform the predetermined action is calculated in consideration of the temporal relationship between the user's predetermined action and the search query input by the user. Based on the probability, it is possible to identify a user who has a high probability of performing a predetermined action, and distribute content to the identified user, thereby enhancing the effect of content distribution.

In addition, the information processing program according to the present disclosure includes a step of acquiring user information of a user and action information including a search history of the user; calculating a weighting factor based on the time difference between the time when the search query was performed and the time when the user entered the search query; A step of calculating a degree of relevance, and a user who has not performed a predetermined action performs a predetermined action based on a search query input by a user who has not performed a predetermined action, a weighting coefficient, and a degree of relevance. A step of calculating a probability, a step of determining a user to whom content is to be distributed based on the probability, and a step of distributing information to the user terminal 200 of the determined user. let it run.

According to the information processing program having this configuration, the probability that the user will perform the predetermined action is calculated in consideration of the temporal relationship between the user's predetermined action and the search query input by the user. Based on the probability, it is possible to identify a user who has a high probability of performing a predetermined action, and distribute content to the identified user, thereby enhancing the effect of content distribution.

As described above, the embodiments of the present application have been described in detail with reference to the drawings, but these are examples, and various modifications and improvements, including the aspects described in the section of the disclosure of the invention, can be made based on the knowledge of those skilled in the art. It is possible to implement the invention in other forms.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit 131 can be read as acquisition means or an acquisition circuit.

100 information processing device 110 communication unit 120 storage unit 121 user information storage unit 122 action information storage unit 123 relevance storage unit 124 function storage unit 125 content storage unit 130 control unit 131 acquisition unit 132 reception unit 133 identification unit 134 calculation unit 1341 Coefficient calculation unit 1342 Relevance calculation unit 1343 Probability calculation unit 135 Determination unit 136 Distribution unit 137 Output unit 200 User terminal 300 Business operator terminal N Network

Claims (7)

an acquisition unit that acquires user information of a user and action information including a search history of the user;
A coefficient calculation unit that calculates a weighting coefficient based on the time difference between when a user who has performed a predetermined action performs the predetermined action and when the user inputs a search query;
a degree-of-relevance calculation unit that calculates a degree of relevance between the predetermined action and the search query based on the search history, the time difference, and the weighting factor;
A probability that a user who has not performed a predetermined action will perform a predetermined action after a predetermined period of time based on the search query input by the user who has not performed the predetermined action, the weighting factor, and the degree of relevance. a probability calculation unit that calculates
comprising a
Information processing equipment. When the time difference is less than 0, the coefficient calculation unit calculates a weighting coefficient based on a value of a normal distribution when the time difference is a random variable, and when the time difference is 0 or more, sets the weighting coefficient to 0. calculated to the following values,
The information processing device according to claim 1 . When the time difference is less than 0, the coefficient calculation unit calculates a weighting coefficient based on a value of t distribution when the time difference is a random variable, and when the time difference is 0 or more, sets the weighting coefficient to 0. calculated to the following values,
The information processing device according to claim 1 . The coefficient calculation unit calculates a weighting coefficient using a function based on the search frequency according to the time difference for each search query,
The information processing device according to claim 1 . a determination unit that determines a user to whom content is to be distributed based on the probability that a user who has not performed a predetermined action will perform a predetermined action calculated by the probability calculation unit;
A distribution unit that distributes content to the user terminal of the user determined by the determination unit,
The information processing apparatus according to any one of claims 1 to 4 . A computer-executed information processing method comprising:
obtaining user information of the user and behavior information including the user's search history;
calculating a weighting factor based on the time difference between when a user who has performed a predetermined action performs the predetermined action and when the user inputs a search query;
calculating a degree of relevance between the predetermined action and the search query based on the search history, the time difference, and the weighting factor;
calculating a probability that a user who has not performed a predetermined action will perform a predetermined action based on a search query input by a user who has not performed a predetermined action, the weighting factor, and the degree of association; ,
determining a user to whom the content is to be distributed based on the probability;
a step of distributing information to the user terminal of the determined user;
A probability that a user who has not performed a predetermined action will perform a predetermined action after a predetermined period of time based on the search query input by the user who has not performed the predetermined action, the weighting factor, and the degree of relevance. a step of calculating
Information processing methods, including obtaining user information of the user and behavior information including the user's search history;
calculating a weighting factor based on the time difference between when a user who has performed a predetermined action performs the predetermined action and when the user inputs a search query;
calculating a degree of relevance between the predetermined action and the search query based on the search history, the time difference, and the weighting factor;
calculating a probability that a user who has not performed a predetermined action will perform a predetermined action based on a search query input by a user who has not performed a predetermined action, the weighting factor, and the degree of association; ,
determining a user to whom the content is to be distributed based on the probability;
a step of distributing information to the user terminal of the determined user;
A probability that a user who has not performed a predetermined action will perform a predetermined action after a predetermined period of time based on the search query input by the user who has not performed the predetermined action, the weighting factor, and the degree of relevance. and calculating
An information processing program that causes a computer to execute

Images