JP6945680B1 - Information processing equipment, information processing methods, and information processing programs - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processing device, an information processing method, and an information processing program capable of preferably displaying the relevance of a plurality of keywords at the time of planning at the time of information creation and setting of a theme. SOLUTION: A server device 10 includes a keyword acquisition unit 131 that acquires a keyword input by a terminal device 20 in association with an attribute of a keyword input person, a volume calculation unit 132 that calculates the number of acquisitions of each keyword, and the like. Correlation between the attribute and the number of acquisitions, the origin keyword acquisition unit 133 that acquires the origin keyword specified by the user, the related keyword extraction unit 136 that extracts a plurality of related keywords that are related to the origin keyword from a plurality of keywords. The index calculation unit (relevance calculation unit 135 and feature value calculation unit 137) that calculates the first index value based on the above and the second index value based on the relevance, and the first index value as the first axis and the second A mapping unit 138 for plotting points corresponding to a plurality of related keywords on biaxial coordinates with the index value as the second axis is provided. [Selection diagram] Fig. 2

Description

The present invention relates to an information processing device, an information processing method, and an information processing program that extracts and maps related keywords from a starting keyword.

Conventionally, various information has been provided via the Internet. The information provided is not limited to that created by companies and organizations, but is often created by individuals (see, for example, Non-Patent Document 1).
Non-Patent Document 1 introduces a platform for creators active in various fields to post their own works and video contents. With such a platform, it is possible to easily provide and disseminate information created by individuals, and it is possible to support the expansion of the range of activities of creators.

"Increasing the value of" individual "dissemination-until Yahoo creates a platform for" creators "", [online], newsHACK, [April 20, 2nd year of Reiwa], Internet (URL: https: // news. yahoo.co.jp/newshack/inside/creators.html)

By the way, in providing and disseminating information, it is important to set plans and themes that are of interest to readers and customers. However, it is not easy to grasp the preferences of readers, customers, etc. who receive the information and set the above-mentioned plans and themes. In addition, it is required to continuously set plans and themes in response to changes in current affairs. Platforms such as Non-Patent Document 1 can support the activities of creators by disclosing the information output by the creators, but cannot propose the above-mentioned plans and themes to creators. Conventionally, when providing such a project or theme to a creator, the requester who requests the creator to write an article needs to perform complicated work to find information that matches the characteristics of the creator from a huge amount of information, and the relevant matter. The work required experience, knowledge, and sense.

An object of the present invention is to provide an information processing apparatus, an information processing method, and an information processing program capable of preferably displaying the relevance of a plurality of keywords at the time of planning at the time of information creation and setting of a theme.

The information processing device of the present invention includes a keyword acquisition unit that acquires a keyword input by a terminal device in association with an attribute of an input person of the keyword, a volume calculation unit that calculates the number of acquisitions of each of the keywords, and a user. Correlation between the attribute and the number of acquisitions, the origin keyword acquisition unit that acquires the designated origin keyword, the related keyword extraction unit that extracts a plurality of related keywords that are related to the origin keyword from the plurality of the keywords. The index calculation unit that calculates the first index value based on the above and the second index value based on the relevance, and the two axes with the first index value as the first axis and the second index value as the second axis. A mapping unit for plotting points corresponding to the plurality of related keywords on the coordinates is provided.

In the present invention, mapping can be performed using the first index value based on the correlation between the attribute of the input person and the number of acquired keywords, and the second index value based on the relationship between the starting keyword and the related keyword. As a result, the relevance of a plurality of keywords can be preferably displayed at the time of planning at the time of information creation and setting of the theme.

The schematic diagram which shows the information processing system of one Embodiment of this invention. The block diagram which shows the schematic structure of the server apparatus of this embodiment. The flowchart which shows the information processing method in this embodiment. The figure which shows an example of the map generated in this embodiment. The figure which shows another example of the map generated by this embodiment.

Hereinafter, an embodiment according to the present invention will be described.
[Overview of information processing system]
FIG. 1 is a schematic view showing an information processing system of the present embodiment.
As shown in FIG. 1, the information processing system of the present embodiment includes a server device 10 which is an information processing device, a plurality of terminal devices 20 connected to the server device 10 via the Internet, and a creator terminal 30.
In the present embodiment, the server device 10 acquires the keyword input by the terminal device 20 managed by a general user (keyword input person, hereinafter referred to as "general user" for distinction). Further, the server device 10 is a creator terminal 30 which is a terminal device managed by a user who is a creator who is a support target for planning and setting a theme at the time of information creation (hereinafter, referred to as "target user" for distinction). Acquires the starting point keyword specified by the target user. Then, the server device 10 calculates the degree of relevance to the origin keyword for each keyword, and extracts a plurality of related keywords having relevance to the origin keyword from the plurality of keywords. Further, the server device 10 calculates a keyword feature value based on the attributes of a general user who is the input person of the keyword for each related keyword. Further, the server device 10 generates a map by plotting the points corresponding to the calculated relevance and the keyword feature value.
The object corresponding to each of the above-mentioned keywords may be any character string such as a noun such as a name, a word such as a verb or an adjective, a sentence, or a sentence as long as the object is of interest to a person.

Further, in the present embodiment, the creator terminal 30 managed by the target user is connected to the Internet, and information indicating the starting keyword and the target is transmitted to the server device 10, so that the server device 10 generates a map. Is returned to the creator terminal 30. Examples of the creator terminal 30 include a computer managed by a creator and an editor who creates information, a computer managed by a company which manages a platform for posting information created by the creator, and the like. The terminal device 20 managed by a general user may function as the creator terminal 30 of the present invention. In this case, the server device 10 returns the generated map to the terminal device 20 by transmitting the information indicating the starting point keyword and the target from the terminal device 20 to the server device 10.
Hereinafter, such an information processing system, particularly the server device 10, will be described in detail.

[Configuration of server device 10]
FIG. 2 is a block diagram showing a schematic configuration of the server device 10.
The server device 10 is composed of a general computer, and as shown in FIG. 2, includes each part constituting the computer, such as a communication unit 11, a storage unit 12, and a processor 13. The number of computers constituting the server device 10 is not particularly limited. For example, the server device 10 may be configured by one computer, or a cloud server constructed by connecting a plurality of computers via a network may be used as the server device 10.
The communication unit 11 is connected to the Internet and communicates with each device such as the terminal device 20 and the creator terminal 30 via the Internet.

The storage unit 12 records various information and information processing programs for controlling the server device 10.
Further, the storage unit 12 has a keyword database (keyword DB121) that records the keywords and the attributes of the general user who is the inputter of the keywords in association with each other, a map database (map DB122) that records information about the generated map, and general. It is provided with a database such as a user database (user DB123) for recording user information of the user.
Here, an example in which various databases and information such as the keyword DB 121, the map DB 122, and the user DB 123 are recorded in the storage unit 12 of the server device 10 will be shown, but the server device 10 is connected to the server device 10 via a network so as to be communicable. This information may be recorded in another data server or cloud storage.

In the keyword DB 121, the keyword and the attribute of the general user who is the input person of the keyword are recorded in association with each other. The attributes of general users are, for example, gender, age, age, and the like. As an attribute of a general user, a user ID that is included in the user information described later and identifies the user may be recorded. In addition, for example, information including the input date and time of the keyword, the acquisition destination information indicating the acquisition destination of the keyword, the target service information, and the like may be recorded. The keyword is a character string used in the terminal device 20. Here, in the present embodiment, as keywords, a search keyword input by a general user when a predetermined application is executed in the terminal device 20 and a search process for searching information is executed by the application is exemplified.

The map DB 122 records the map generated by the server device 10 and information about the map. This map is recorded for each starting keyword specified by the target user. The details of the map will be described later.
As information about the map, the starting keyword, a plurality of related keywords extracted for the starting keyword, the degree of relevance between the starting keyword and each related keyword, and the keyword of each related keyword based on the attributes of general users, etc. Feature values and are recorded. The keyword feature value is the ratio of the number of acquisitions for each attribute of a general user to the total number of acquisitions of related keywords. Here, the total number of acquisitions in the present embodiment is the total number of search processes performed using the target related keywords. That is, the keyword feature value indicates the ratio of the number of searches for each attribute of the general user who searched for the related keyword to the total number of searches for one related keyword searched by the general user.

As each related keyword, all the keywords of the keyword DB 121 may be targeted, or only the keywords having a predetermined number of searches or more may be targeted. Further, the keyword of the keyword DB 121 may be a target to be extracted as a related keyword after performing a known narrowing process such as category selection. As such a narrowing process, for example, it is conceivable to use a technique such as Japanese Patent No. 6553793 by the applicant. Patent No. 6553793 uses a first learning model in which the characteristics of a plurality of search queries are learned, assuming that the distributed representations of a pair of search queries input by the same user within a predetermined time have similar characteristics. Therefore, a highly accurate search query can be classified by generating a second learning model that predicts the category to which the search query belongs from a predetermined search query. In the present embodiment, it is conceivable to perform the above-mentioned narrowing process by using the classification result of such a search query.
As the category to be selected, for the purpose of setting a plan or theme that attracts the interest of general users, for example, categories such as "worries", "questions", and "problems" can be considered. Further, as the period during which the related keyword is searched, all the keywords of the keyword DB 121 may be targeted unless otherwise specified.

The user DB 123 records user information about a plurality of general users.
The user information includes a user ID that identifies the user, user attributes, and the like. User attributes include at least one of demographic data and psychographic data. Demographic data is attributes based on demographic attributes such as the user's gender, age, occupation, and family structure, and psychographic data is psychological attributes such as hobbies, values, and habits. It is an attribute based on.

The processor 13 is composed of an arithmetic circuit such as a CPU and a recording circuit such as a RAM. The processor 13 expands the information processing program recorded in the storage unit 12 into the RAM, and executes various processes in cooperation with the program expanded in the RAM.
Then, by reading and executing the information processing program, the processor 13 reads and executes the information processing program, and as shown in FIG. 2, the keyword acquisition unit 131, the volume calculation unit 132, the starting keyword acquisition unit 133, the target acquisition unit 134, the relevance degree calculation unit 135, It functions as a related keyword extraction unit 136, a feature value calculation unit 137, a mapping unit 138, a transmission unit 139, and the like.

The keyword acquisition unit 131 acquires the keyword (search keyword) and the attribute of the general user who is the input person of the keyword, and stores and stores it in the keyword DB 121. For example, when the server device 10 is a search server that provides a search service, the keyword acquisition unit 131 may acquire information about keywords from the terminal device 20. Further, the terminal device 20 may be set to transmit information about the keyword to the server device 10 when the search process using a predetermined application is executed, and the server device 10 periodically relates to the keyword. A transmission program that transmits information may be installed.
Alternatively, the keyword acquisition unit 131 may acquire information about the keyword from the search server that performs the search process. For example, in the terminal device 20, when the search content is accessed using a web browser and the search process is performed, information on the keyword may be acquired from the search server that provides the search content. Similarly, in the terminal device 20, when the search process is performed by the application that posts or browses to the SNS, the information about the keyword may be acquired from the search server provided by the SNS.

The volume calculation unit 132 calculates the total number of searches and the number of searches for each attribute for each keyword stored in the keyword DB 121. Here, as an example, "male" and "female", "teens or younger", "20s", "30s", "40s", "50s", "60s", "70s or older" The number of searches for each attribute is calculated for each combination with any of the above. That is, when all the searches for each attribute of each combination are added, the total number of searches is obtained.
The total number of searches and the number of searches for each attribute by the volume calculation unit 132 may be executed each time the information about the keyword is stored in the keyword DB 121, or at the timing when the target user specifies. It may be executed.

The starting point keyword acquisition unit 133 acquires the starting point keyword that is the starting point of map generation from the creator terminal 30. The starting keyword is a keyword indicating a plan and a theme at the time of information creation, and is designated by a target user such as a creator or an editor who creates the information via the creator terminal 30.

The target acquisition unit 134 acquires a target, which is one of the conditions at the time of map generation, from the creator terminal 30. This target is an attribute of a general user who is the input person of the keyword. The target is designated via the creator terminal 30 by a target user such as a creator and an editor who creates information.

The relevance calculation unit 135 calculates the relevance degree between each keyword stored in the keyword DB 121 and the origin keyword acquired by the origin keyword acquisition unit 133. The degree of relevance is an index value indicating the relevance of each keyword to the starting keyword, and the more easily the keyword is searched in relation to the starting keyword, the higher the degree of relevance.
That is, when it is presumed that a general user who has searched for a certain starting keyword is more characteristically easy to search for the keyword, the degree of relevance is high. Further, when it is presumed that a general user who has searched for a certain starting keyword is more characteristically difficult to search for the keyword, the degree of relevance is low.
For the calculation of such a degree of relevance, for example, it is conceivable to use a technique such as Japanese Patent No. 6679682 by the applicant. In Japanese Patent No. 6679682, an input query that is a query input by a user who has input one of a plurality of reference queries and is different from the plurality of reference queries is acquired. Then, for each reference query, the degree of relevance indicating the relevance to the input query is calculated, and based on each relevance, the characteristics of the input query based on the reference query are specified, so that the query entered by the user You can understand the characteristics of. In the present embodiment, it is conceivable to calculate the degree of relevance by using the characteristics of the query grasped in this way.
In the calculation of the relevance degree, the relevance degree may be calculated by adding the information regarding the attributes of the general user, or the relevance degree may be calculated regardless of the information regarding the attributes of the general user. When calculating the relevance regardless of the information about the attributes of general users, it is possible to map various keywords that are not affected by the attributes.

The related keyword extraction unit 136 extracts a plurality of related keywords that are related to the origin keyword acquired by the origin keyword acquisition unit 133 from the keywords stored in the keyword DB 121. The related keyword extraction unit 136 extracts related keywords from the keywords stored in the keyword DB 121, for example, by extracting the keywords in descending order of the degree of relevance calculated by the relevance calculation unit 135. The extraction of related keywords is not limited to the extraction based on the degree of relevance calculated by the relevance calculation unit 135, and can be performed by using a known technique.

The feature value calculation unit 137 calculates a keyword feature value for each related keyword extracted by the related keyword extraction unit 136. The keyword feature value is an index value based on the correlation between the target acquired by the target acquisition unit 134 and the number of acquisitions of each related keyword. For example, in the present embodiment, the feature value calculation unit 137 calculates the ratio of the number of target searches to the total number of searches for related keywords.

The mapping unit 138 uses the keyword feature value calculated by the feature value calculation unit 137 as the first index value, the relevance degree calculated by the relevance calculation unit 135 as the second index value, and the first index value as the first axis. A map is generated by plotting the points corresponding to each related keyword extracted by the related keyword extraction unit 136 on the two-axis coordinates with (horizontal axis) and the second index value as the second axis (vertical axis). do.
When the transmission unit 139 receives the information indicating the starting keyword and the target from the creator terminal 30, the transmission unit 139 transmits the map to the creator terminal 30.
The detailed operation of each function configuration will be described later.

[Configuration of terminal device 20 and creator terminal 30]
The terminal device 20 is a computer managed by a general user, and is composed of, for example, a smartphone, a tablet terminal, a personal computer, or the like. Further, the creator terminal 30 is a computer managed by a target user who is a user who is a support target for planning and theme setting at the time of information creation, and like the terminal device 20, for example, a smartphone, a tablet terminal, a personal computer, or the like. It is configured. As described above, the terminal device 20 may function as the creator terminal 30 of the present invention.
Although the illustration of the specific configuration of the terminal device 20 and the creator terminal 30 is omitted, the terminal device 20 and the creator terminal 30 have the basic configuration of a general computer. That is, the terminal device 20 and the creator terminal 30 include an input operation unit that accepts an operator's operation, a display that displays image information, a recording device that records various information, and an arithmetic circuit (CPU, etc.) that performs arithmetic processing of various information. ing.

[Information processing method]
Next, the map generation and display method in the information processing system of the present embodiment will be described with particular focus on the information processing method in the server device 10.
FIG. 3 is a flowchart showing an information processing method according to the present embodiment.
In order to generate a map, the keyword acquisition unit 131 of the server device 10 first acquires information about the keywords input by the terminal device 20 (step S1: keyword acquisition step). In addition, the keyword acquisition unit 131 stores information about the acquired keyword in the keyword DB 121.
In this step S1, the keyword acquisition unit 131 may acquire information about the keyword transmitted from the terminal device 20 at an arbitrary timing, or may acquire information about the keyword transmitted from the search server at an arbitrary timing. good. The arbitrary timing may be, for example, the timing at which the user inputs a keyword in the terminal device 20 and performs the search process, or the timing at which the search server receives the keyword from the terminal device 20. Further, the terminal device 20 or the search server may store information about the keywords and transmit the information about the keywords stored periodically (for example, at a preset time) to the server device 10. Alternatively, the terminal device 20 or the search server may accumulate information on keywords, and at the timing when a predetermined number of keywords are accumulated, the information on these keywords may be transmitted to the server device 10.

The volume calculation unit 132 of the server device 10 calculates the total number of searches and the number of searches for each attribute of the general user for each keyword accumulated in the keyword DB 121 (step S2: volume calculation step).

On the other hand, when a predetermined application such as a browser is executed on the creator terminal 30 and a target user who is an operator of the creator terminal 30 specifies a starting point keyword as a starting point for generating a map, the creator terminal 30 receives the creator terminal 30. As shown in FIG. 3, information indicating the designated starting point keyword is transmitted to the server device 10 (step S21). Further, when a predetermined application such as a browser is executed on the creator terminal 30 and the target user specifies the target to be mapped, the creator terminal 30 provides information indicating the designated target to the server device 10. (Step S22).
In the example of FIG. 3, an example in which the creator terminal 30 transmits information indicating a starting keyword and a target is shown, but as described above, the terminal device 20 is a creator terminal 30 that specifies the starting keyword and the target of the present invention. In this case, information indicating the starting point keyword and the target is transmitted from the terminal device 20 to the server device 10. The same applies to the subsequent processing performed by the creator terminal 30, and may be performed by the terminal device 20.

The starting point keyword acquisition unit 133 acquires information indicating the starting point keyword, and the target acquisition unit 134 acquires information indicating the target (step S3: starting point keyword acquisition step). Then, the relevance calculation unit 135 calculates the relevance degree (step S4: relevance degree calculation step, index calculation step), and the related keyword extraction unit 136 extracts a plurality of related keywords having relevance to the starting keyword (step). S5: Related keyword extraction step). Then, the feature value calculation unit 137 calculates the keyword feature value for each related keyword extracted by the related keyword extraction unit 136 (step S6: feature value calculation step, index calculation step).

Then, the mapping unit 138 plots the points corresponding to each related keyword extracted by the related keyword extraction unit 136 on the two-axis coordinates with the calculated keyword feature value as the horizontal axis and the calculated relevance degree as the vertical axis. Then, a map is generated (step S7: mapping step). At this time, the mapping unit 138 plots only the keyword feature values related to the attributes of the target to be mapped. If the target has not been specified, the default target specification may be adopted, or the history of the latest target may be inherited.

4 and 5 are diagrams showing an example of a map generated by the mapping unit 138. As shown in FIG. 4, the mapping unit 138 plots the points corresponding to each keyword on the two-axis coordinates with the vertical axis as the relevance degree and the horizontal axis as the keyword feature value, and generates a map. Note that FIG. 4 illustrates a map generated when the target of the map is "men and women in their teens to 20s". In FIG. 4, points corresponding to each related keyword are plotted in the first area A1, the target that is the target of the map is plotted in the second area A2, and more specifically, the target that is the target of calculating the keyword feature value. The attributes of a general user are shown.

In FIG. 4, "keyword A" and "keyword B" having a relatively high degree of relevance are keywords that are easily searched in relation to the starting keyword and are highly related to the starting keyword. Further, in FIG. 4, "keyword C" and "keyword D" having relatively small feature values are keywords in which the ratio of the number of searches by "men and women in their teens to 20s" to the total number of searches is low. On the contrary, in FIG. 4, "keyword F", "keyword G", and "keyword H" having relatively large feature values are the number of searches by "men and women in their teens to 20s" with respect to the total number of searches. The ratio is high, and "men and women in their teens to 20s" is a keyword to search more characteristically.

In other words, related keywords that are highly related to the starting keyword are mapped to the upper area of the map, and related keywords that are related to the starting keyword and have a different expression from the starting keyword are mapped toward the lower side. It will be. Therefore, by referring to the related keywords mapped to the upper area of the map, it is possible to support the setting of the theme that is highly related to the starting keyword and easily attracts the interest of the target.
In the area on the upper side of the map, the keyword feature value increases toward the right side. Therefore, the related keywords mapped to the area on the upper side and the right side of the map are related to the starting keyword and the volume (number of searches and volume). It is a related keyword that also has the number of acquisitions). Therefore, for example, it can be useful information as a reference for the best-selling products in product sales. On the other hand, in the area on the upper side of the map, the keyword feature value becomes smaller toward the left side. Therefore, the related keywords mapped to the area on the upper side and the left side of the map are related to the starting keyword, but the volume (search). It is a related keyword with a small number (number and number of acquisitions).

Also, as you move toward the right side of the map, related keywords with a larger target volume (number of searches and number of acquisitions) will be mapped. Therefore, for example, in planning and setting a theme at the time of information creation, it can be information that can be used as a reference for setting a theme that easily attracts the interest of the target. On the other hand, as the target volume (number of searches and number of acquisitions) is smaller, related keywords are mapped toward the left side of the map. Therefore, for example, in the above-mentioned theme setting, there is a high possibility that the target will not be interested, and it can be useful information for the theme to be avoided.

Furthermore, such a map makes it possible to visualize the correlation between the degree of relevance between the starting keyword and the related keyword and the interest of the target. Therefore, it is possible to extract a plurality of related keywords having common items of interest of various general users as compared with the conventional analysis based on the experience and behavior history of general users such as readers and customers. Therefore, it becomes possible to grasp the tendency of related keywords starting from the starting keyword, and it becomes information that can be used as a reference for setting a theme that easily attracts the interest of the target, including access to related keywords that the target user does not anticipate. obtain.

After step S7, the mapping unit 138 records the information about the generated map in the map DB 122.

The transmission unit 139 transmits the generated map to the creator terminal 30 which is the transmission source of the starting keyword (step S8: transmission step). As a result, the creator terminal 30 displays the map on the display (step S23).

In the creator terminal 30 on which the map as shown in FIG. 4 is displayed, the target is designated (changed) by operating the second area A2 described above by the target user. The creator terminal 30 determines whether or not the target has been changed (step S24), and if YES in step S24, transmits information indicating the acquired target to the server device 10 (step S25). .. On the other hand, if NO is determined in step S24, the process proceeds to step S26, which will be described later. The creator terminal 30 determines whether or not an operation to end the display of the map has been performed (step S26). If NO is determined in step S26, the process returns to step S24.

When the server device 10 receives the information indicating the changed target, the server device 10 executes the processes after step S7 described above.
FIG. 5 illustrates a map generated when the target of the map is “men and women in their 40s and 50s”. In FIG. 5, points corresponding to each related keyword are plotted in the first area A1, and the target of the map, more specifically, the attribute of a general user who is the target of calculating the keyword feature value is in the second area A2. It is shown to be "men and women in their 40s and 50s". The names of the related keywords (keyword X) in FIG. 5 are the same as those in FIG.
“Keyword A” and “keyword B” having a relatively high degree of relevance in FIG. 4 are keywords having a relatively high degree of relevance in FIG. 5 and having a high relevance to the starting keyword. Further, in FIG. 4, "keyword C" and "keyword D" having relatively small feature values have a high ratio of the number of searches by "men and women in their 40s and 50s" to the total number of searches in FIG. 5, and ""Men and women in their 40s and 50s" is a more characteristic search keyword. On the contrary, "keyword F" having a relatively large feature value in FIG. 4 is a keyword in which the ratio of the number of searches by "men and women in their 40s and 50s" to the total number of searches is low in FIG. Further, for "keyword G" and "keyword H" having relatively large feature values in FIG. 4, points are not plotted in FIG. 5, and points are not plotted in FIG. 4, "keyword I" and "keyword J". However, in FIG. 5, the ratio of the number of searches by "men and women in their 40s and 50s" to the total number of searches is high, and "men and women in their 40s and 50s" are plotted as keywords to be searched more characteristically.

In this way, the second area A2 is used for changing the target of the map and inputting for narrowing down the user attributes of the general user who input the starting point keyword. Then, when the target of the map is changed, different maps that reflect the characteristics of each target attribute are generated for the same starting keyword. That is, the map can be switched by changing the target of the map.
For example, even if the starting keywords are the same, many related keywords related to their own problems are mapped to the area on the right side of the map in young people such as teens to 20s. On the other hand, in middle-aged people in their 40s and 50s, many related keywords related to problems as parents or bosses are mapped to the area on the right side of the map.
Therefore, by comparing and examining the maps for each target, it is possible to grasp the tendency along the target, and it is possible to support the theme setting that easily attracts the interest of the target. On the contrary, it is also possible to support the review and identification of the target.
After step S10, the mapping unit 138 records the information about the generated map in the map DB 122.

[Action and effect of this embodiment]
The server device 10 of the present embodiment includes a storage unit 12 and a processor 13, and the processor 13 reads the information processing program stored in the storage unit 12 to read the keyword acquisition unit 131, the volume calculation unit 132, and the starting point. It functions as a keyword acquisition unit 133, a relevance degree calculation unit 135 (index calculation unit), a related keyword extraction unit 136, a feature value calculation unit 137 (index calculation unit), and a mapping unit 138. The keyword acquisition unit 131 acquires the keyword input by the terminal device 20 in association with the attribute of the keyword input person. The volume calculation unit 132 calculates the number of acquisitions of each keyword. The starting point keyword acquisition unit 133 acquires the starting point keyword specified by the user. The relevance calculation unit 135, which is an index calculation unit, calculates the relevance degree as a second index value based on the relevance between the starting keyword and the related keyword. The related keyword extraction unit 136 extracts a plurality of related keywords that are related to the starting keyword from the plurality of keywords. The feature value calculation unit 137, which is an index calculation unit, calculates the keyword feature value as the first index value based on the correlation between the attribute and the number of acquisitions. The mapping unit 138 plots points corresponding to a plurality of related keywords on the two-axis coordinates with the first index value as the first axis and the second index value as the second axis.

As a result, related keywords can be extracted from the starting keyword and mapped, so that a plurality of related keywords and the relationship between the starting keyword and the related keyword are preferably displayed at the time of planning and setting the theme at the time of information creation. be able to.

In the server device 10 of the present embodiment, the processor 13 functions as a target acquisition unit for acquiring the target of the input person designated by the target user, and the feature value calculation unit 137, which is the index calculation unit, is the target of the designated target. Calculate the keyword feature value based on the correlation between the attribute and the number of acquisitions.
This makes it possible to generate different maps that reflect the characteristics of each target attribute for the same starting keyword.

In the present embodiment, the keyword feature value, which is the first index value, is the ratio of the number of acquisitions for each attribute to the total number of acquisitions of related keywords.
This makes it possible to grasp the amount of input by a general user having the attribute for each related keyword.

In the present embodiment, the second index value is the degree of association between the starting keyword and the related keyword.
This makes it possible to easily grasp the relationship between each related keyword and the starting keyword for each related keyword.

In the server device 10 of the present embodiment, the keyword acquisition unit 131 acquires, as a keyword, a search keyword acquired when the search process is performed by the terminal device 20.
Such search keywords are often keywords in the field that each general user is interested in, and by accumulating keywords related to the keyword, what is of interest to many general users, that is, the tendency of general users can be determined. It can be preferably visualized.

In this embodiment, the attribute includes at least one of demographic data and psychographic data.
As a result, the feature value corresponding to at least one of the demographic data and the psychographic data can be calculated, so that the tendency according to at least one of the demographic data and the psychographic data can be preferably visualized. ..

[Modification example]
The present invention is not limited to the above-described embodiment, but also includes the modifications shown below to the extent that the object of the present invention can be achieved.

[Modification 1]
In the above embodiment, an example is shown in which the mapping unit 138 generates a map and the transmission unit 139 transmits the map from the server device 10 to the creator terminal 30, but the information corresponding to the map is transmitted without generating the map. May be good. In addition to the map, information corresponding to the map may be transmitted.

For example, in the above embodiment, the transmission unit 139 associates the plurality of related keywords extracted by the related keyword extraction unit 136 with the degree of relevance to each related keyword and the keyword feature value from the server device 10 to the creator terminal 30. May be sent to.
In this case, the target user who manages the creator terminal 30 can refer to the planning and theme setting at the time of information creation by examining a plurality of related keywords based on the degree of relevance and the keyword feature value. Therefore, it is possible to preferably support planning and theme setting at the time of information creation, as in the case of generating and transmitting a map.

Further, for example, in the above embodiment, the degree of relevance and the keyword feature value are evaluated and ranked, and the transmission unit 139 has a plurality of related keywords extracted by the related keyword extraction unit 136 and the degree of relevance to each related keyword. And the rank of the keyword feature value may be associated with each other and transmitted from the server device 10 to the creator terminal 30.
In this case, the target user who manages the creator terminal 30 can use a plurality of related keywords as a reference for planning and setting the theme at the time of information creation by examining a plurality of related keywords based on the degree of relevance and the rank of the keyword feature value. can. Therefore, it is possible to preferably support planning and theme setting at the time of information creation, as in the case of generating and transmitting a map.

[Modification 2]
In the above embodiment, the related keyword extraction unit 136 has extracted a plurality of related keywords having a relation with the starting keyword from the keywords stored in the keyword DB 121.
On the other hand, the related keyword extraction unit 136 may extract a plurality of related keywords having a relationship between the starting keyword and the co-occurrence keyword input together with the starting keyword from the keywords stored in the keyword DB 121. .. The co-occurrence keyword indicates a word used together with the origin keyword when the origin keyword appears. For example, the co-occurrence keyword corresponds to a word posted as a search query together with a starting keyword on a search site. The co-occurrence keyword also corresponds to a word or the like that appears together with the starting keyword in one short sentence on a short sentence posting site.
In this case, the related keyword extraction unit 136 can extract more diverse related keywords while maintaining the relevance with the starting keyword.

[Modification 3]
In the above embodiment, the number of starting points keywords that the related keyword extraction unit 136 uses as a starting point at the time of extraction is not particularly mentioned, but the starting point keywords may be one or a plurality.
As described in the above-described modification 2, the related keyword extraction unit 136 may extract a plurality of related keywords starting from the starting keyword and one or more co-occurrence keywords. For example, the starting keyword acquisition unit may be used. 133 may acquire a plurality of origin keywords from the creator terminal 30, and the related keyword extraction unit 136 may extract a plurality of related keywords having a relationship with the plurality of origin keywords from the keywords stored in the keyword DB 121. .. Further, a plurality of related keywords may be extracted starting from a plurality of origin keywords acquired by the origin keyword acquisition unit 133 and one or more co-occurrence keywords.
More specifically, for example, when the starting keyword acquisition unit 133 acquires the starting keyword indicating the plan and theme at the time of information creation and the starting keyword indicating the name of the creator of the information, the related keyword extraction unit 136 Related keywords can be extracted based on both the plan and theme and the creator of the information. Similarly, when the starting keyword acquisition unit 133 acquires the starting keyword indicating the plan and theme at the time of information creation and the starting keyword indicating the specialty of the creator of the information, the related keyword extraction unit 136 determines the planning and theme. And related keywords based on both the expertise of the creator of the information and the expertise of the creator of the information can be extracted. Therefore, it is also useful for identifying the strengths of the information creator.

[Modification example 4]
In the above embodiment, the processor 13 may further function as a keyword recommendation unit that extracts recommended keywords recommended for the target user from the related keywords for the attributes. In this case, the transmission unit 139 may transmit the extracted recommended keyword to the creator terminal 30.
For example, the keyword recommendation unit extracts one or more recommended keywords from a plurality of related keywords extracted by the related keyword extraction unit 136 based on the degree of relevance to each related keyword and the keyword feature value, and the transmission unit 139 extracts the recommended keywords. The recommended keyword may be transmitted from the server device 10 to the creator terminal 30.
When extracting recommended keywords, the keyword recommendation section extracts, for example, related keywords having a keyword feature value for each attribute equal to or higher than a predetermined first threshold value and a degree of relevance equal to or lower than the second threshold value as recommended keywords. May be good.
In this case, the target user who manages the creator terminal 30 can use the recommended keyword itself as a reference for planning and setting the theme at the time of information creation. Therefore, it is possible to preferably support planning and theme setting at the time of information creation, as in the case of generating and transmitting a map.
Alternatively, in the map, a region in which the keyword feature value is equal to or higher than the predetermined first threshold value and the degree of relevance is equal to or lower than the second threshold value may be surrounded by a frame image, and the keyword feature value is equal to or higher than the predetermined first threshold value. Related keywords included in the area where the degree of relevance is equal to or less than the second threshold value may be highlighted.

[Modification 5]
The map described in the above embodiment is an example, and the present invention is not limited to the above embodiment.
For example, the mapping unit 138 generated a map with the keyword feature value calculated by the feature value calculation unit 137 as the horizontal axis, but generated a map with the number of searches calculated by the volume calculation unit 132 for each related keyword as the horizontal axis. You may.
Further, for example, when plotting the points corresponding to each related keyword extracted by the related keyword extraction unit 136, the mapping unit 138 displays the points to be plotted according to the acquisition number (search number) of the related keyword. The form may be changed. As the display form, for example, the color, size, etc. of the dots may be changed. As a result, in addition to the correlation between the degree of relevance between the starting keyword and the related keyword and the interest of the target, the volume of each related keyword can be visualized.

[Modification 6]
In the above embodiment, the number of acquisitions of each keyword is calculated based on the number of searches related to each keyword, but the present invention is not limited to this.
For example, the number of acquisitions may be calculated based on the number of contents searched by the search engine for each keyword or the number of articles posted on SNS or the like.

10 ... Server device (information processing device), 12 ... Storage unit, 13 ... Processor, 20 ... Terminal device, 30 ... Creator terminal, 121 ... Keyword DB, 122 ... Map DB, 123 ... User DB, 131 ... Keyword acquisition unit, 132 ... Volume calculation unit, 133 ... Origin keyword acquisition unit, 134 ... Target acquisition unit, 135 ... Relevance calculation unit (index calculation unit), 136 ... Related keyword extraction unit, 137 ... Feature value calculation unit (index calculation unit), 138 ... Mapping unit, 139 ... Transmission unit.

Claims (9)

A keyword acquisition unit that acquires a keyword input by the terminal device in association with the attribute of the person who input the keyword,
A volume calculation unit that calculates the number of acquisitions of each of the above keywords,
The starting keyword acquisition unit that acquires the starting keyword specified by the user,
A related keyword extraction unit that extracts a plurality of related keywords that are related to the starting keyword from the plurality of the keywords, and a related keyword extraction unit.
An index calculation unit that calculates a first index value based on the correlation between the attribute and the number of acquisitions, and a second index value based on the relationship.
It is characterized by including a mapping unit that plots points corresponding to the plurality of related keywords on two-axis coordinates with the first index value as the first axis and the second index value as the second axis. Information processing device. In the information processing apparatus according to claim 1,
The mapping unit is an information processing apparatus characterized in that the display form of the points to be plotted is changed according to the number of acquisitions. In the information processing apparatus according to claim 1 or 2.
A target acquisition unit for acquiring the target of the input person specified by the user is provided.
The information processing device is characterized in that the index calculation unit calculates the first index value based on the correlation between the attribute of the designated target and the acquisition number. In the information processing apparatus according to any one of claims 1 to 3.
The information processing apparatus, characterized in that the first index value is the ratio of the number of acquisitions for each attribute to the total number of acquisitions of the related keywords. In the information processing apparatus according to any one of claims 1 to 4.
The information processing apparatus, characterized in that the second index value is the degree of relevance between the starting point keyword and the related keyword. The information processing apparatus according to any one of claims 1 to 5.
The information processing device is characterized in that the keyword acquisition unit acquires, as the keyword, a search keyword acquired when a search process is performed by the terminal device. The information processing apparatus according to any one of claims 1 to 6.
An information processing device characterized in that the attribute includes at least one of demographic data and psychographic data. It is an information processing method that generates a map by a computer.
The computer includes a keyword acquisition unit, a volume calculation unit, a starting keyword acquisition unit, a related keyword extraction unit, an index calculation unit, and a mapping unit.
A keyword acquisition step in which the keyword acquisition unit acquires a keyword input by the terminal device in association with the attribute of the keyword inputter, and a volume calculation step in which the volume calculation unit calculates the number of acquisitions of each of the keywords. ,
The starting point keyword acquisition unit obtains the starting point keyword specified by the user, and the starting point keyword acquisition step.
A related keyword extraction step in which the related keyword extraction unit extracts a plurality of related keywords related to the starting keyword from the plurality of the keywords.
The index calculation unit
An index calculation step in which the index calculation unit calculates a first index value based on the correlation between the attribute and the number of acquisitions, and a second index value based on the relationship.
A mapping step in which the mapping unit plots points corresponding to the plurality of related keywords on two-axis coordinates with the first index value as the first axis and the second index value as the second axis. An information processing method characterized by implementation. An information processing program that can be read and executed by a computer.
An information processing program characterized in that the computer functions as the information processing device according to any one of claims 1 to 7.

Images