JP7388617B2 - Calculation device, calculation method and calculation program - Google Patents

Description

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

Conventionally, an information processing device that aggregates and outputs queries entered by users has been used to provide users with popular queries whose search frequency is rapidly increasing, for users who wish to search based on queries entered by other users. Output is being done.

As a method for extracting a query of interest, for example, a technique is known that can extract a query whose search frequency has suddenly increased, and also extract the reason why the search frequency has suddenly increased.

Japanese Patent Application Publication No. 2013-37404 International Publication No. 2012/127968

However, with the above-mentioned conventional technology, it is not always possible to calculate the degree of association between keyword information with high accuracy. For example, the above-mentioned conventional technology only extracts queries whose search frequency has suddenly increased, and also extracts the reason why the search frequency has suddenly increased. It is not always possible to calculate

The present application has been made in view of the above, and aims to provide a calculation device, a calculation method, and a calculation program that can calculate the degree of association between keyword information with high accuracy.

The calculation device according to the present application includes an acquisition unit that acquires posted information posted by a user, and a first keyword information and a second keyword information related to the first keyword information based on the posted information acquired by the acquisition unit. A calculation unit that calculates the degree of association with keyword information.

According to one aspect of the embodiment, it is possible to calculate the degree of association between keyword information with high accuracy.

FIG. 1 is a diagram illustrating an example of calculation processing according to the first embodiment. FIG. 2 is a conceptual diagram illustrating the positional relationship between a person's name and related words in the calculation process according to the first embodiment. FIG. 3 is a diagram illustrating a configuration example of a calculation device according to the first embodiment. FIG. 4 is a diagram illustrating an example of a posted information storage unit according to the first embodiment. FIG. 5 is a diagram illustrating an example of a relevance information storage unit according to the first embodiment. FIG. 6 is a diagram illustrating an example of a summary information storage unit according to the first embodiment. FIG. 7 is a flowchart showing a calculation processing procedure by the calculation device according to the first embodiment. FIG. 8 is a diagram illustrating an example of calculation processing according to the second embodiment. FIG. 9 is a diagram illustrating a configuration example of a calculation device according to the second embodiment. FIG. 10 is a diagram illustrating an example of a posted information storage unit according to the second embodiment. FIG. 11 is a flowchart showing the calculation processing procedure by the calculation device according to the second embodiment. FIG. 12 is a diagram illustrating an example of a process for selecting posted information in a calculation process according to a modification. FIG. 13 is a hardware configuration diagram showing an example of a computer that implements the functions of the calculation device.

Embodiments of a calculation device, a calculation method, and a calculation program according to the present application will be described in detail below with reference to the drawings. Note that this embodiment does not limit the calculation device, calculation method, and calculation program according to the present application.

[1. First embodiment]
[1-1. Example of information processing of calculation device]
An example of the calculation process according to the first embodiment will be described using FIG. 1. FIG. 1 is a diagram illustrating an example of calculation processing according to the first embodiment. FIG. 1 shows an example in which calculation processing is executed by the calculation device 100.

As shown in FIG. 1, the calculation system 1 includes an external device 10, a terminal device 20, and a calculation device 100. The external device 10, the terminal device 20, and the calculation device 100 are communicably connected by wire or wirelessly via a predetermined communication network (not shown). Note that the calculation system 1 shown in FIG. 1 may include a plurality of external devices 10, a plurality of terminal devices 20, and a plurality of calculation devices 100.

The external device 10 according to the first embodiment is an SNS server, and, for example, receives posted information such as articles and profile images posted from users who are registered as members, and stores the received posted information. The external device 10 then provides posted information posted by the user to the calculation device 100. In the example shown in FIG. 1, a case will be described in which the external device 10 is an SNS server device that provides posted information posted by a user. Further, in the example shown in FIG. 1, it is assumed that the storage unit of the external device 10 stores posted information posted by a user.

The terminal device 20 according to the first embodiment is an information processing device used by a user who accesses web content such as a web page displayed on a browser or content displayed on an application. For example, the terminal device 20 is a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), or the like.

The calculation device 100 according to the first embodiment extracts buzzwords, which are keywords that attract attention in news articles, blogs, etc., as first keyword information, and extracts buzzwords that co-occur with the first keyword information in news articles, blogs, etc. Keywords that appear frequently or keywords that appear frequently are extracted as second keyword information (hereinafter referred to as related words) related to the first keyword information. Then, the calculation device 100 selects posted information based on the proximity of the first keyword information and the related word from among the posted information posted by the user. Then, the calculation device 100 generates the posted information as a summary. Hereinafter, an example will be described in which the calculation device 100 executes a process of calculating the degree of association between first keyword information, which is a person's name, and a related word, which is a sa-hen noun.

Specifically, the calculation device 100 acquires posted information posted by a user from the external device 10. Then, when the posted information acquired from the external device 10 includes a person's name and a related word related to the person's name, the calculation device 100 selects the posted information based on the proximity of the person's name and the related word. . Subsequently, the calculation device 100 calculates the degree of association between the person's name and the related word in the posted information in which the person's name and the related word are closest in position. Then, the calculation device 100 generates posted information in which the position of the person's name and the related word is closest to each other as a summary.

For example, assume that a person's name is "XXXX" and the related word related to the person's name is the sa-bun noun "election." In this case, the calculation device 100 acquires posted information posted by the user from the external device 10. Then, when the posted information acquired from the external device 10 includes "XXXX" and "winning", the calculation device 100 selects the posted information in which "XXXX" and "winning" are closest in position. select. Subsequently, the calculation device 100 calculates the degree of association between "XXXX" and "winning" in posted information in which "XXXX" and "winning" are located close to each other. Then, the calculation device 100 generates the posted information that is closest in position to “XXXX” and “winning” as a summary.

Hereinafter, an example of a process of calculating the degree of association between a person's name and a related word based on posted information posted by a user by the calculation device 100 will be explained along the flow using FIG.

First, as shown in FIG. 1, the calculation device 100 acquires posted information ST11 to ST16 posted by the user from the external device 10 (step S1). Then, when the posted information posted by the user includes a person's name and a related word, the calculation device 100 selects posted information ST14 based on the proximity of the person's name and the related word (step S2). .

Here, with reference to FIG. 2, a process of selecting posted information ST22 from posted information ST21 to ST24 posted by a user based on the proximity of a person's name and a related word will be described. FIG. 2 is a conceptual diagram illustrating the positional relationship between a person's name and related words in the calculation process according to the first embodiment. As shown in FIG. 2, in posted information ST21 "XXXXAAAAAAAAAAAAAAAAAAAAAAAAWIN", the space between the person's name "XXXX" and the related word "WIN" is occupied by the arbitrary character "A", and in this case, the character "A" is The number of characters is 20. In the posted information ST22, the number of characters of "A" between the person's name and the related word is 5 characters, and in the posted information ST23, the number of characters of "A" between the person's name and the related word is 7 characters, and the number of characters of "A" between the person's name and the related word is 7 characters, and the posted information In ST24, the number of characters "A" between the person's name and the related word is nine. Then, the calculation device 100 selects the posted information ST22 having the smallest number of characters "A" between the person's name and the related word from among the posted information ST21 to ST24. That is, the calculation device 100 selects posted information ST22 that has the closest positional proximity between the person's name and the related word.

Returning to FIG. 1, an example of the calculation process according to the first embodiment will be described. The calculation device 100 calculates the degree of association between the person's name and the related word in posted information ST14 in which the position of the person's name and the related word is closest (step S3). For example, the calculation device 100 uses dependency analysis such as KNP and CaboCha (pumpkin) to determine the degree of association between the person name "XXXX" and the related word "elect" in posted information ST14 "XXXX wins the presidential election" by 90. Calculated as %.

Subsequently, the calculation device 100 provides the posted information ST14 as a summary to the user (step S4). For example, the calculation device 100 provides a summary to the user using techniques such as push notification and real-time search. Note that the calculation device 100 may provide the posted information ST14 to the user as a summary when the degree of association is greater than or equal to a predetermined threshold.

In this way, the calculation device 100 according to the first embodiment calculates the positions of a person's name and related words based on the proximity of the positions of the person's name and related words included in the posted information acquired from the external device 10. Select the closest post information. Then, the calculation device 100 calculates the degree of association between the person's name and the related word included in the posted information. Thereby, the calculation device 100 according to the first embodiment uses the keyword The degree of association between pieces of information can be calculated with high accuracy.

[1-2. Configuration of calculation device]
Next, the configuration of the calculation device 100 according to the first embodiment will be described using FIG. 3. FIG. 3 is a diagram showing a configuration example of the calculation device 100 according to the first embodiment. As shown in FIG. 3, the calculation device 100 includes a communication section 110, a storage section 120, and a control section 130.

The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information between the external device 10 and the terminal device 20.

The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes a posted information storage unit 121 , a relevance information storage unit 122 , and a summary information storage unit 123 .

The posted information storage unit 121 according to the first embodiment stores posted information posted by a user. Here, FIG. 4 shows an example of the posted information storage unit 121 according to the first embodiment. In the example shown in FIG. 4, the posted information storage unit 121 has items such as "user ID", "posted information ID", and "posted information".

"User ID" indicates identification information for identifying a user. "Posted information ID" indicates identification information for identifying posted information posted by a user. "Posted information" indicates posted content posted by a user. For example, FIG. 4 shows that the user identified by the user ID "U1" posted the posted information identified by the posted information ID "PO1", "XXXX defeats YYY and wins the presidential election". . Note that, hereinafter, the posted information identified by the posted information ID "PON (N is an arbitrary number)" may be referred to as "posted information PON."

The relevance information storage unit 122 according to the first embodiment stores information regarding a person's name and related words related to the person's name included in the posted content posted by the user. Here, FIG. 5 shows an example of the relevance information storage unit 122 according to the first embodiment. In the example shown in FIG. 5, the relevance information storage unit 122 has items such as "posted information ID", "person name", "related word", and "relevance".

"Posted information ID" indicates identification information for identifying posted information posted by a user. "Person's name" indicates a person's name included in the posted information posted by the user. "Related word" indicates a related word related to a person's name included in posted information posted by a user. The “degree of association” indicates the degree of association (for example, in %) between a person's name and a related word included in posted information posted by a user. For example, in FIG. 5, the person's name in posted information PO1 is "XXXX", the related word related to the person's name "XXXX" is "winning", and the relationship between the person's name "XXXX" and the related word "winning" The degree indicates 90%.

The summary information storage unit 123 according to the first embodiment stores information related to summaries of posted contents posted by users. Here, FIG. 6 shows an example of the summary information storage unit 123 according to the first embodiment. In the example shown in FIG. 6, the summary information storage unit 123 has items such as "summary information ID", "posted information ID", and "summary information".

"Summary information ID" indicates identification information for identifying summary information that summarizes posted information posted by a user. "Posted information ID" indicates identification information for identifying posted information posted by a user. "Summary information" indicates summary content that summarizes the posted information posted by the user. For example, in FIG. 6, the summary information ID "SU1" is a summary corresponding to the posted information PO1, and the content of the summary indicates that the summary information "XXXX wins the presidential election."

The control unit 130 is a controller, and for example, uses a CPU (Central Processing Unit), an MPU (Micro Processing Unit), etc. to execute various programs (an example of a calculation program) stored in a storage device inside the calculation device 100. This is realized by executing using RAM as a work area. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the control unit 130 includes an acquisition unit 131, a selection unit 132, a calculation unit 133, a generation unit 134, and a provision unit 135, and has information processing functions and operations described below. to realize or carry out. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3, and may be any other configuration as long as it performs information processing to be described later. Further, the connection relationship between the respective processing units included in the control unit 130 is not limited to the connection relationship shown in FIG. 3, and may be other connection relationships.

The acquisition unit 131 acquires posted information posted by a user from the external device 10. For example, the acquisition unit 131 acquires posted information including a person's name and related words. The acquisition unit 131 then stores the posted information in the posted information storage unit 121.

The selection unit 132 selects the positions of the person's name and the related word among the posted information that includes both the first keyword information (corresponding to the person's name) and the second keyword information (corresponding to the related word) acquired by the acquisition unit 131. Select posting information based on proximity to.

For example, assume that a person's name is "XXXX" and the related word related to the person's name is the sa-bun noun "election." In this case, in the example of FIG. 4, when the posted information acquired by the acquisition unit 131 includes “XXXX” and “winning”, the selection unit 132 selects The posted information PO5 is selected based on the information.

The calculation unit 133 calculates the degree of association between a person's name and a related word related to the person's name based on the posted information acquired by the acquisition unit 131. Specifically, the calculation unit 133 calculates the degree of association between a person's name and a related word based on posted information that includes both a person's name and a related word, out of the posted information acquired by the acquisition unit 131. For example, in the example of FIG. 5, the calculation unit 133 uses dependency analysis such as KNP and CaboCha to calculate the person name “XXXX” and related words in the posted information that includes the person name and related words selected by the selection unit 132. The degree of relevance with "winning" is calculated as 90%. Then, the calculation unit 133 stores the degree of association in the degree of association information storage unit 122.

The generation unit 134 generates a summary based on posted information selected according to a predetermined criterion from among the posted information acquired by the acquisition unit 131. Specifically, the generation unit 134 generates the posted information selected by the selection unit 132 as a summary. For example, in the example of FIG. 6, the generation unit 134 generates the posted information “XXXX wins the presidential election” selected by the selection unit 132 as a summary. Note that the generation unit 134 may generate the summary by appropriately editing the posted information selected by the selection unit 132. For example, the person's name "XXXX" and the related word "winning" are left, and other characters are shortened.

The providing unit 135 provides the summary generated by the generating unit 134 to the user. For example, the providing unit 135 provides the user with the summary generated by the generating unit 134 using techniques such as push notifications and real-time search when the degree of association calculated by the calculating unit 133 is greater than or equal to a predetermined threshold. Further, the providing unit 135 may provide the user with the summary having the highest relevance calculated by the calculating unit 133 among the summaries generated by the generating unit 134. Note that the providing unit 135 may provide the user with the summary generated by the generating unit 134 when the degree of association calculated by the calculating unit 133 is greater than or equal to a predetermined threshold.

[1-3. Flowchart showing an example of calculation processing procedure by calculation device]
Next, an example of a calculation processing procedure by the calculation device 100 according to the first embodiment will be described using FIG. 7. FIG. 7 is a flowchart showing a calculation processing procedure by the calculation device 100 according to the first embodiment.

As shown in FIG. 7, the acquisition unit 131 acquires posted information posted by a user from the external device 10 (step S101). Then, when the posted information acquired by the acquisition unit 131 includes both a person's name and a related word, the selection unit 132 selects the posted information based on the proximity of the position of the person's name and the related word (step S102 ). Then, the calculation unit 133 calculates the degree of association between a person's name and a related word in the posted information selected by the selection unit 132 (step S103). Then, the generation unit 134 generates posted information in which the position of the person's name selected by the selection unit 132 and the related word are closest to each other as a summary (step S104). Then, when the degree of association calculated by the calculation unit 133 is greater than or equal to a predetermined threshold (step S105; Yes), the provision unit 135 provides the user with the summary generated by the generation unit 134 (step S106). On the other hand, if the degree of association calculated by the calculation unit 133 is smaller than the predetermined threshold (step S105; No), the providing unit 135 returns to the process before step S102.

In this way, the calculation device 100 according to the first embodiment calculates the positions of a person's name and related words based on the proximity of the positions of the person's name and related words included in the posted information acquired from the external device 10. Select the closest post information. Then, the calculation device 100 calculates the degree of association between the person's name and the related word included in the posted information. Thereby, the calculation device 100 according to the first embodiment uses the keyword The degree of association between pieces of information can be calculated with high accuracy.

[2. Second embodiment]
[2-1. Example of information processing of calculation device]
Next, a second embodiment will be described. In the first embodiment described above, the calculation device 100 has explained an example of calculation processing for posted information that includes both a person's name and a related word. In the second embodiment, an example is shown in which the calculation device 200 performs calculation processing on posted information that does not include both a person's name and a related word. Note that, in the second embodiment, the same components as those in the first embodiment are given the same reference numerals, and the description thereof will be omitted.

An example of the calculation process according to the second embodiment will be described using FIG. 8. FIG. 8 is a diagram illustrating an example of calculation processing according to the second embodiment. FIG. 8 shows an example in which calculation processing is executed by the calculation device 200.

As shown in FIG. 8, the calculation system 2 includes an external device 10, a terminal device 20, and a calculation device 200. The external device 10, the terminal device 20, and the calculation device 200 are communicably connected by wire or wirelessly via a predetermined communication network (not shown). Note that the calculation system 2 shown in FIG. 8 may include a plurality of external devices 10, a plurality of terminal devices 20, and a plurality of calculation devices 200.

The external device 10 according to the second embodiment has the same configuration as the external device 10 according to the first embodiment, so a description thereof will be omitted.

The terminal device 20 according to the second embodiment has the same configuration as the terminal device 20 according to the first embodiment, so a description thereof will be omitted.

The calculation device 200 according to the second embodiment calculates posted information that only includes a person's name based on sentence length information and appearance frequency when the posted information acquired from the external device 10 does not include a person's name and related words. and post information that includes only related words. Then, the calculation device 200 calculates the degree of association between a person's name and a related word in posted information that is a combination of posted information that includes only a person's name and posted information that includes only a related word. The calculation device 200 then generates, as a summary, posted information that is a combination of posted information that includes only a person's name and posted information that only includes related words.

For example, assume that a person's name is "XXXX" and the related word related to the person's name is the sa-bun noun "election." In this case, when the posted information acquired from the external device 10 does not include "XXXX" and "winning", the calculation device 200 calculates a post that includes only "XXXX" based on the sentence length information and the appearance frequency. Select information and posted information that only includes "winning". Subsequently, the calculation device 200 calculates the degree of association between "XXXX" and "winning" in posted information that is a combination of posted information containing only "XXXX" and posted information containing only "winning". Then, the calculation device 200 generates posted information as a summary, which is a combination of posted information containing only “XXXX” and posted information containing only “winning”.

Hereinafter, using FIG. 8, posted information that combines posted information containing only a person's name and posted information containing only related words based on sentence length information and appearance frequency in posted information posted by a user by the calculation device 200. An example of calculation processing for generating a summary will be explained along the flow.

First, as shown in FIG. 8, the calculation device 200 acquires posted information posted by a user from the external device 10 (step S21). Then, when the posted information posted by the user does not include a person's name and related words, the calculation device 200 calculates a post that includes only the person's name and only related words based on the sentence length information and the appearance frequency. information (step S22).

For example, in the example of FIG. 8, the sentence length information of posted information ST34 is 11 characters, the sentence length information of posted information ST35 is 12 characters, and the sentence length information of posted information ST36 is 20 characters. The appearance frequency of the person's name "XXXX" in posted information ST34 is once, the appearance frequency of the person's name "XXXX" in posted information ST35 is once, and the appearance frequency of the person's name "XXXX" in posted information ST36 is once. It is. From this, the calculation device 200 calculates the score SC using the following equation (1).

Score SC = w1*x+w2*y... (1)

In the above formula (1), "w1" indicates an arbitrary weight, "x" indicates a function related to sentence length information, "w2" indicates an arbitrary weight, and "y" indicates a function related to appearance frequency. Indicates a function. Then, the calculation device 200 selects posted information ST36 with the highest score SC as posted information containing only a person's name.

The calculation device 200 calculates the degree of association between a person's name and a related word in posted information that is a combination of posted information that includes only a person's name and posted information that includes only a related word (step S23). For example, the calculation device 200 uses dependency analysis such as KNP and CaboCha to combine posted information ST36 "XXXX ran for president from the AA party and won the presidency" and posted information ST33 "Won as president of ZZZ country". The degree of association between the person's name "XXXX" and the related word "elect" in the posted information "XXXX ran for president from the AA party, won for president, and was elected president of ZZZ country" is calculated as 90%.

Then, when the degree of association is greater than or equal to a predetermined threshold, the calculation device 200 provides the user with a summary of posted information that is a combination of posted information that only includes a person's name and posted information that only includes related words (step S24). .

In this way, the calculation device 200 selects posted information including a person's name and posted information including a related word based on sentence length information and appearance frequency. Then, the calculation device 200 calculates the degree of association between a person's name and a related word in posted information that is a combination of posted information that includes only a person's name and posted information that includes only a related word. Thereby, the calculation device 200 calculates the degree of association between the person's name and related words included in posted information that is a combination of posted information selected based on sentence length information and frequency of appearance. can be calculated with high precision.

[2-2. Configuration of decision device]
Next, the configuration of the calculation device 200 according to the second embodiment will be described using FIG. 9. FIG. 9 is a diagram illustrating a configuration example of a calculation device 200 according to the second embodiment. As shown in FIG. 9, the calculation device 200 includes a communication section 110, a storage section 220, and a control section 230.

The storage unit 220 is realized by, for example, a semiconductor memory device such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 220 includes a posted information storage unit 221 , a relevance information storage unit 122 , and a summary information storage unit 123 .

The posted information storage unit 221 according to the second embodiment stores posted information posted by a user. Here, FIG. 10 shows an example of the posted information storage unit 221 according to the second embodiment. In the example shown in FIG. 10, the posted information storage unit 221 has items such as "rank", "posted information", "sentence length information", "frequency of appearance", and "score".

"Ranking" indicates the ranking of posted information based on sentence length information and frequency of appearance. "Posted information" indicates posted content posted by a user. "Sentence length information" indicates the length of the posted information in characters. "Frequency of appearance" indicates the frequency with which a person's name or related word appears in posted information. "Score" indicates a score calculated based on sentence length information and appearance frequency using equation (1). For example, the example in FIG. 10 shows the ranking of posted information that includes only "XXXX". As shown in FIG. 10, the posted information PO1 posted by user U1, "XXXX ran for president from the AA party," has the largest score of 92 calculated by formula (1). , indicates that the rank is "1".

The control unit 230 is a controller, and is realized by, for example, a CPU, an MPU, or the like executing various programs stored in a storage device inside the calculation device 200 using the RAM as a work area. Further, the control unit 230 is a controller, and is realized by, for example, an integrated circuit such as an ASIC or an FPGA.

As shown in FIG. 9, the control unit 230 includes an acquisition unit 131, a selection unit 232, a calculation unit 233, a generation unit 234, and a provision unit 135, and has information processing functions and operations described below. to realize or carry out. Note that the internal configuration of the control unit 230 is not limited to the configuration shown in FIG. 9, and may be any other configuration as long as it performs information processing to be described later. Furthermore, the connection relationship between the respective processing units included in the control unit 230 is not limited to the connection relationship shown in FIG. 9, and may be other connection relationships.

The selection unit 232 selects posted information that includes a person's name based on the number of characters from the first posted information (corresponding to posted information that includes a person's name) acquired by the acquisition unit 131, and selects posted information that includes a person's name based on the number of characters, and selects the second posted information (posts that include related words). Select posted information that includes related words based on the number of characters (equivalent to information). Further, the selection unit 232 selects posted information including a person's name based on the frequency of appearance of the person's name among the posted information including the person's name acquired by the acquisition unit 131, and selects posted information including a person's name from among the posted information including a related term. Select posts that contain related terms based on their frequency. Specifically, when the posted information acquired by the acquisition unit 131 includes only a person's name or only related words, the selection unit 232 selects posted information containing only the person's name and only related words based on sentence length information and appearance frequency. Select post information including.

For example, in the example of FIG. 10, when the posted information acquired by the acquisition unit 131 includes only “XXXX”, the selection unit 232 selects a post that includes only “XXXX” based on the sentence length information and the appearance frequency. Select the posted information ``XXXX ran for president from the AA party and won for president'' as the information.

The calculation unit 233 calculates the degree of association between a person's name and a related word related to the person's name, based on the posted information acquired by the acquisition unit 131. Specifically, when the posted information acquired by the acquiring unit 131 does not include a person's name and a related word, the calculation unit 233 divides the posted information containing only the person's name and the posted information containing only the related word. Calculate the degree of relevance between a person's name and related words in the combined posted information. For example, in the example of FIG. 8, the calculation unit 233 uses dependency analysis such as KNP and CaboCha to convert the person's name " The degree of association between "XXXX" and the related word "winning" is calculated as 90%.

The generation unit 234 generates posted information as a summary, which is a combination of posted information including the person's name selected by the selection unit 232 and posted information including related terms. For example, in the example of FIG. 8, the generation unit 234 generates a post that combines the posted information “XXXX ran for president from the AA party and won for president” selected by the selection unit 232 and the posted information “elected president of ZZZ country”. The information ``XXXX ran for president from the AA party, won the presidency, and was elected president of ZZZ country'' is generated as a summary. Note that the generation unit 234 may generate the summary by appropriately editing posted information that is a combination of posted information that includes the person's name selected by the selection unit 232 and posted information that includes related words.

[2-3. Flowchart showing an example of calculation processing procedure by calculation device]
Next, an example of a calculation processing procedure by the calculation device 200 according to the second embodiment will be described using FIG. 11. FIG. 11 is a flowchart showing a calculation processing procedure by the calculation device 200 according to the second embodiment.

As shown in FIG. 11, the acquisition unit 131 acquires posted information posted by a user from the external device 10 (step S201). When the posted information acquired by the acquiring unit 131 does not include a person's name and related words, the selection unit 232 selects posted information that includes only the person's name and posts that only include related words based on sentence length information and appearance frequency. information (step S202). Then, the calculation unit 233 calculates the degree of association between the person's name and the related word in the posted information that is a combination of the posted information that includes only the person's name selected by the selection unit 232 and the posted information that includes only the related word (step S203). . Then, the generating unit 234 generates posted information as a summary, which is a combination of the posted information including only the person's name selected by the selecting unit 232 and the posted information including only related words (step S204). Then, when the degree of association calculated by the calculation unit 233 is greater than or equal to a predetermined threshold (step S205; Yes), the providing unit 135 provides the user with the summary generated by the generation unit 234 (step S206). On the other hand, if the degree of association calculated by the calculation unit 233 is smaller than the predetermined threshold (step S205; No), the providing unit 135 returns to the process before step S202.

In this way, the calculation device 200 selects posted information including a person's name and posted information including a related word based on sentence length information and appearance frequency. Then, the calculation device 200 calculates the degree of association between a person's name and a related word in posted information that is a combination of posted information that includes only a person's name and posted information that includes only a related word. Thereby, the calculation device 200 calculates the degree of association between the person's name and related words included in posted information that is a combination of posted information selected based on sentence length information and frequency of appearance. can be calculated with high precision.

[3. Modified example]
The calculation device 100 or 200 described above may be implemented in various different forms other than the above embodiment. Therefore, other embodiments of the calculation device 100 or 200 will be described below.

[3-1. Calculation device]
Each component of each device shown in the drawings is functionally conceptual, and does not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distributing and integrating each device is not limited to what is shown in the diagram, and all or part of the devices can be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured. For example, the calculation device 100 according to the first embodiment performs the calculation process described in the second embodiment, and the calculation device 200 according to the second embodiment performs the calculation process described in the first embodiment. You may go.

[3-2. Keyword information〕
In the above embodiment, it has been explained above that the selection unit 132 or 232 of the calculation device 100 or 200 selects posted information that includes a person's name and related words related to the person's name. You may choose. For example, the selection unit 132 or 232 may select posted information that includes a proper noun that is not a person's name (for example, the name of a game or a sport) and a related word related to the proper noun.

[3-3. Related words〕
In the embodiment described above, it has been explained that the selection unit 132 or 232 of the calculation device 100 or 200 selects posted information that includes a person's name and a sa-hen noun as a related word related to the person's name. You may also select a noun or the like. For example, the selection unit 132 or 232 may select posted information that includes a person's name and a verb that is not a saber noun (for example, do, choose, etc.).

[3-4. Selection process]
In the embodiment described above, the selection unit 232 of the calculation device 200 selects posted information including a person's name and a related term in which third keyword information (equivalent to a common term) other than the person's name and related term acquired by the acquiring unit 131 appears together. Posted information including a person's name and posted information including related words may be selected based on the posted information including the person's name. Specifically, the selection unit 232 of the calculation device 200 selects the sentence length information, the appearance frequency, the posted information including the person's name, and the related words in the posted information including the person's name and related words acquired by the acquisition unit 131. Posted information including a person's name and posted information including a related word may be selected based on the posted information and a common word indicating keyword information commonly included in the posted information.

For example, assume that a person's name is "XXXX" and the related word related to the person's name is the sa-noun "sho". In this case, the selection unit 232 selects the posted information including the person's name and the posted information including the related word based on the sentence length information, the frequency of appearance, and the common word. In the example of FIG. 12, the posted information table T1 shows posted information that includes only the person's name "XXXX" and is ranked based on sentence length information and appearance frequency. Further, the posted information table T2 shows posted information that includes only the related word "victory" and is ranked based on sentence length information and frequency of appearance. As shown in FIG. 12, the selection unit 232 selects posted information "XXXX is running for president from the AA Party" that includes the common word "AA Party" from the posted information table T1 as the posted information that includes a person's name. . Further, the selection unit 232 selects the posted information "AA party wins the presidential election" from the posted information table T2 as the posted information including the related term.

In this manner, the selection unit 232 selects posted information including a person's name and posted information including a related word based on sentence length information, frequency of appearance, and common words. Thereby, the calculation device 200 calculates the degree of association between a person's name and related words included in posted information that is a combination of posted information selected based on sentence length information, frequency of appearance, and common words. Even if keywords are not included in the same posted information, the degree of association between keyword information can be calculated with high accuracy.

[4. Hardware configuration]
Further, the external device 10, the terminal device 20, and the calculation device 100 or 200 according to the embodiments described above are realized, for example, by a computer 1000 having a configuration as shown in FIG. The calculation device 100 will be described below as an example. FIG. 13 is a hardware configuration diagram showing an example of a computer 1000 that implements the functions of the calculation device 100. Computer 1000 has CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I/F) 1500, input/output interface (I/F) 1600, and media interface (I/F) 1700.

CPU 1100 operates based on a program stored in ROM 1300 or HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, programs depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. Communication interface 1500 receives data from other devices via network N and sends it to CPU 1100, and sends data generated by CPU 1100 to other devices via network N.

The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and mouse via an input/output interface 1600. CPU 1100 obtains data from an input device via input/output interface 1600. Further, CPU 1100 outputs the generated data to an output device via input/output interface 1600.

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200. CPU 1100 loads this program from recording medium 1800 onto RAM 1200 via media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 1000 functions as the calculation device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded onto the RAM 1200. Furthermore, data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via the network N.

[5. effect〕
As described above, the calculation device 100 according to the embodiment includes the acquisition section 131 and the calculation section 133. The acquisition unit 131 acquires posted information posted by a user. The calculation unit 133 calculates the degree of association between the first keyword information (corresponding to a person's name) and the second keyword information (corresponding to a related word) related to the first keyword information, based on the posted information acquired by the acquisition unit 131. Calculate.

Thereby, the calculation device 100 according to the embodiment can calculate the degree of association between the name of the person of interest and the related word associated with the name of the person with high accuracy based on posted information posted by the user.

In addition, in the calculation device 100 according to the embodiment, the calculation unit 133 calculates a The degree of association between the first keyword information and the second keyword information is calculated.

In addition, in the calculation device 100 according to the embodiment, the calculation unit 133 calculates whether the first keyword information and the second keyword information are close to each other in the posted information that includes both the first keyword information and the second keyword information. The degree of association between the first keyword information and the second keyword information is calculated based on the posted information selected based on the quality.

As a result, the calculation device 100 according to the embodiment can calculate the degree of association between a person's name of interest and a related word associated with the person's name with high accuracy in posted information that includes both a person's name and a related word.

In addition, in the calculation device 100 according to the embodiment, the calculation unit 133 calculates, from among the posted information acquired by the acquisition unit 131, first posted information including first keyword information (posted information including only a person's name) and a second keyword. The degree of association between the first keyword information and the second keyword information is calculated based on the second posted information including the information (posted information including only related words).

In addition, in the calculation device 100 according to the embodiment, the calculation unit 133 includes first posted information selected based on the number of characters among the first posted information, and second posted information selected based on the number of characters among the second posted information. The degree of association between the first keyword information and the second keyword information is calculated based on the posted information.

In addition, in the calculation device 100 according to the embodiment, the calculation unit 133 selects the first posted information selected based on the frequency of appearance of the first keyword information among the first posted information, and the second posted information selected based on the frequency of appearance of the first keyword information among the first posted information. The degree of association between the first keyword information and the second keyword information is calculated based on the second posted information selected based on the frequency with which the keyword information appears.

Further, in the calculation device 100 according to the embodiment, the calculation unit 133 calculates the first posted information and the second posted information in which third keyword information other than the first keyword information and the second keyword information both appear. The degree of association between the first keyword information and the second keyword information is calculated.

As a result, the calculation device 100 according to the embodiment can calculate the degree of association between a person's name of interest and a related word associated with the person's name with high accuracy in posted information that does not include both a person's name and a related word.

The calculation device 100 according to the embodiment further includes a generation unit 134 that generates a summary based on posted information selected according to a predetermined criterion from among the posted information acquired by the acquisition unit 131.

As a result, the calculation device 100 according to the embodiment generates a summary based on the posted information selected according to a predetermined criterion from among the posted information posted by the user, so that the calculation device 100 can explain to the user the reason why the name of a person of interest has increased. can be provided accurately.

In addition, in the calculation device 100 according to the embodiment, the generation unit 134 generates information that is close to the position of the first keyword information and the second keyword information among posted information that includes both the first keyword information and the second keyword information. Generate summaries based on posted information selected based on quality.

As a result, the calculation device 100 according to the embodiment generates a summary including the name of the person of interest and related words associated with the name of the person in posted information that includes both a person's name and related words. It is possible to accurately provide the user with the reason why the person's name has increased.

In addition, in the calculation device 100 according to the embodiment, the generation unit 134 generates first posted information selected based on the number of characters from among the first posted information, and second posted information selected based on the number of characters from among the second posted information. Generate a summary based on the posted information.

In addition, in the calculation device 100 according to the embodiment, the generation unit 134 generates first posted information selected based on the frequency of appearance of the first keyword information among the first posted information, and second posted information selected based on the frequency of appearance of the first keyword information among the first posted information. A summary is generated based on the second posted information selected based on the frequency with which the keyword information appears.

As a result, the calculation device 100 according to the embodiment generates a summary that includes the name of the person of interest and the related words associated with the name of the person in posted information that does not include both the name of the person and the related word. It is possible to accurately provide the user with the reason why the person's name has increased.

As described above, the calculation device 100 according to the embodiment includes the acquisition section 131 and the generation section 134. The acquisition unit 131 acquires posted information posted by a user. The calculation unit 133 generates a summary including first keyword information and second keyword information related to the first keyword information, based on the posted information acquired by the acquisition unit 131.

As a result, the calculation device 100 according to the embodiment generates a summary including the name of the person of interest and related words related to the name of the person based on the posted information posted by the user, thereby explaining the reason why the name of the person of interest has increased. can be accurately provided to the user.

Some of the embodiments of the present application have been described above in detail based on the drawings, but these are merely examples, and various modifications and variations may be made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. It is possible to carry out the invention in other forms with modifications.

1 Calculation system 2 Calculation system 10 External device 20 Terminal device 100 Calculation device 110 Communication unit 120 Storage unit 121 Posted information storage unit 122 Relevance information storage unit 123 Summary information storage unit 130 Control unit 131 Acquisition unit 132 Selection unit 133 Calculation unit 134 Generation unit 135 Providing unit 200 Calculation device 220 Storage unit 221 Posted information storage unit 230 Control unit 232 Selection unit 233 Calculation unit 234 Generation unit

Claims (3)

an acquisition unit that acquires a plurality of posted information posted by users, including both first keyword information and second keyword information related to the first keyword information;
a selection unit that selects posted information in which the first keyword information and the second keyword information are closest in position from among the plurality of posted information based on the proximity of the positions of the first keyword information and the second keyword information; and,
a calculation unit that calculates a degree of association based on a dependency relationship between a first keyword indicated by the first keyword information included in the selected posted information and a second keyword indicated by the second keyword information;
a generation unit that generates a summary based on the selected posted information;
A calculation device comprising: a provision unit that provides the generated summary to a user when the degree of association calculated by the calculation unit is equal to or greater than a predetermined threshold. A calculation method performed by a computer,
an acquisition step of acquiring a plurality of pieces of posted information posted by users, including both first keyword information and second keyword information related to the first keyword information;
a selection step of selecting posted information in which the first keyword information and the second keyword information are closest in position from among the plurality of posted information based on the proximity of the positions of the first keyword information and the second keyword information; and,
a calculation step of calculating a degree of association based on a dependency relationship between a first keyword indicated by the first keyword information included in the selected posted information and a second keyword indicated by the second keyword information;
a generation step of generating a summary based on the selected posted information ;
and a providing step of providing the generated summary to a user when the degree of association calculated in the calculating step is equal to or greater than a predetermined threshold. an acquisition procedure of acquiring a plurality of posted information posted by users, including both first keyword information and second keyword information related to the first keyword information;
A selection procedure of selecting posted information in which the first keyword information and the second keyword information are closest in position from among the plurality of posted information based on the proximity of the positions of the first keyword information and the second keyword information. and,
a calculation step of calculating a degree of association based on a dependency relationship between a first keyword indicated by the first keyword information included in the selected posted information and a second keyword indicated by the second keyword information;
a generation step of generating a summary based on the selected posted information;
A calculation program that causes a computer to execute a providing step of providing the generated summary to a user when the degree of association calculated by the calculation step is greater than or equal to a predetermined threshold.

Images