JP2024008018A - Tagging support device, program and content search device - Google Patents

Abstract

To provide a tag provision support device, a program, and a content search device that can add a tag suitable for a content through simpler processing.SOLUTION: A tag provision support server 1 includes: a character string extraction processing unit 12 that extracts some character strings in a content having a text from the content; a tag provision unit 16 that tags the content with the character strings extracted by the character string extraction processing unit 12; and a tagged content registration unit 17 that causes a search DB 3 to store the tagged content tagged by the tag provision unit 16.SELECTED DRAWING: Figure 2

Description

The present invention relates to a tagging support device, a program, and a content search device.

BACKGROUND ART Conventionally, some content on SNS (Social Networking Service) and the like has a hashtag added by the poster. A hash tag is a search tag for searching for content, and is a hash symbol (#) added to the beginning of a word or phrase. By adding a hashtag, you can display a list of posts by other posters with the same hashtag, allowing you to efficiently view posts on a specific topic or by users with the same interests.
Hashtags can be added freely by the poster, but there is a problem that they are inconsistent.

Under such circumstances, for example, an optimal tag suggestion device that proposes tags to be inserted into content transmitted by a sending device, for each content in which a specific word appears, For each specific word, the tags collected from the content in which the specific word appears are clustered, and for each cluster, a representative tag is selected from among the tags belonging to the cluster according to the number of collected tags. When a request for inserting a tag into content to be transmitted is received from the transmission device, each time the specific word appears in the content to be transmitted, a cluster of the specific word is collected, and a cluster of the specific word is collected. Determine candidate tags from among the representative tags according to the number of collected clusters and return them to the transmitting device, and during clustering, create a network by connecting tags inserted in the same content, An optimal tag proposal device that uses each network as a cluster is disclosed (for example, Patent Document 1).

Patent No. 5252593

The technology described in Patent Document 1 mentioned above registers words that appear frequently in content in a word DB in advance, and collects tags that have already been inserted into the content for each word registered in the word DB. , create an optimal tag list DB. Then, as a tag for the new content, a representative tag in the optimal tag list DB is returned as a candidate tag based on the words included in the content and the optimal tag list DB.
Therefore, it uses the tags of existing content, and is based on the assumption that the existing content has been tagged. Further, the task of creating the optimal tag list DB was complicated.

SUMMARY OF THE INVENTION Therefore, an object of the present invention is to provide a tagging support device, a program, and a content search device that can add tags suitable for content through simpler processing.

The present invention solves the above problems by the following solving means.
A first invention includes a character string extraction means for extracting a part of character strings in a content having text from the content, and a tag for tagging the content with the character string extracted by the character string extraction means. and content registration means for storing tagged content tagged by the tagging means in a search database.
A second invention is the tagging support device according to the first invention, which includes a keyword storage unit storing keywords, and the character string extraction means is arranged such that the keyword stored in the keyword storage unit is included in the content. This is a tagging support device that extracts the keyword as the character string.
A third invention is the tagging support device according to the first invention or the second invention, further comprising a noun extracting means for analyzing the text of the content to extract a noun, and the character string extracting means is configured to extract a noun from the text of the content. The tagging support device extracts a predetermined noun from among the nouns extracted by the extraction means as the character string.
In a fourth invention, in the tagging support device according to the third invention, the character string extraction means is configured such that, among the nouns extracted by the noun extraction means, the number of occurrences of the nouns in the text is equal to or greater than a threshold value. The tagging support device extracts the predetermined noun as the character string.
In a fifth invention, in the tagging support device according to the third invention, the character string extraction means uses the tagged content registered in the search database to add the noun to the noun extracted by the noun extraction means. The tagging support device assigns a score indicating importance to the noun, and extracts the predetermined noun having the score equal to or higher than a threshold value as the character string.
A sixth invention is the tagging support device according to any one of the first to fifth inventions, wherein the character string extraction means extracts proper nouns from the content using a learning model that extracts proper nouns from the context of the text. This is a tagging support device that extracts the character string that is a proper noun.
A seventh invention is the tagging support device according to any one of the first to sixth inventions, wherein a plurality of related words related to the character string extracted by the character string extraction means are stored. The tagging support device further includes a related word acquisition means that acquires the related word from the related word storage section, and the tagging means further tags the content with the related word acquired by the related word acquisition means.
An eighth invention is the tagging support device according to any one of the first to seventh inventions, including a character string output means for outputting the character string extracted by the character string extraction means, and a character string output means for outputting the character string extracted by the character string extraction means. specified character string receiving means for receiving a specified character string specified by a user from among the character strings outputted by the means; This is a tagging support device that tags the content.
A ninth invention is a program for causing a computer to function as the tagging support device according to any one of the first invention to the eighth invention.
A tenth invention is provided that the content is communicably connected to the search database in which the tagged content tagged by the tagging support device according to any one of the first to eighth inventions is stored. A content search device comprising: a search word receiving means for accepting a search word; and a related word related to the search word accepted by the search word receiving means from a related word storage unit storing a plurality of related words. a search related word acquisition means, and the tagged content having a tag that matches either the search word accepted by the search word reception means or the related word acquired by the search related word acquisition means is stored in the search database. The present invention is a content search device comprising: a content extracting means for extracting content from the content; and a tag list outputting means for generating and outputting a tag list for each of the tags based on the tagged content extracted by the content extracting means.
An eleventh invention is the content search device according to the tenth invention, wherein the tag selection receiving means receives a selection of one of the tags from the tag list outputted by the tag list outputting means; content list output means for outputting a list of the tagged contents to which the tags have been added, the content list output means to output a list of the tagged contents including the tags added to each tagged content. This is a content search device that outputs.

According to the present invention, it is possible to provide a tagging support device, a program, and a content search device that can add tags suitable for content through simpler processing.

1 is a diagram showing the overall configuration of a content search support system according to the present embodiment. It is a diagram showing functional blocks of a tagging support server and a content search server according to the present embodiment. FIG. 2 is a diagram illustrating an example of content to which tags are added by the tagging support server according to the present embodiment. It is a flowchart which shows the content tagging process of the tagging support server based on this embodiment. It is a flowchart which shows the content search process of the content search server based on this embodiment. FIG. 3 is a diagram showing an example of display on a terminal according to the present embodiment. FIG. 3 is a diagram showing an example of display on a terminal according to the present embodiment.

Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings. Note that this is just an example, and the technical scope of the present invention is not limited to this.
(Embodiment)
<Overall configuration of content search support system 100>
FIG. 1 is a diagram showing the overall configuration of a content search support system 100 according to this embodiment.
FIG. 2 is a diagram showing functional blocks of the tagging support server 1 and content search server 5 according to this embodiment.

In the content search support system 100 shown in FIG. 1, a tagging support server 1 (tagging support device) tags untagged content stored in a search database (DB) 3. . Further, in the content search support system 100, the tagging support server 1 tags the content received from the terminal 7 and registers the tag in the search DB 3. Further, in the content search support system 100, when the content search server 5 (content search device) receives a search term from the terminal 8, it transmits to the terminal 8 a list of contents having the search term as a tag.

The content search support system 100 includes a tagging support server 1, a search DB 3, a related word dictionary 4 (related word storage unit), a content search server 5, a terminal 7, and a terminal 8, each of which has a communication network. Connected via N.
The communication network N is a network between the tagging support server 1, the search DB 3, the related word dictionary 4, the content search server 5, the terminals 7, and the terminals 8, and includes, for example, communication such as an Internet line. It's a net. Furthermore, the communication network N may be wired or wireless.

<Tagging support server 1>
The tagging support server 1 is a server that performs a process of adding a tag suitable for the content to the content.
FIG. 2(A) shows functional blocks of the tagging support server 1.
As shown in FIG. 2(A), the tagging support server 1 includes a control section 10, a storage section 20, and a communication interface section 29.

The control unit 10 is a central processing unit (CPU) that controls the entire tagging support server 1. The control unit 10 cooperates with the above-mentioned hardware and executes various functions by appropriately reading and executing the operating system (OS) and various application programs stored in the storage unit 20.
The control unit 10 includes a content acquisition unit 11, a character string extraction processing unit 12 (noun extraction means, character string extraction means), a related word acquisition unit 13 (related word acquisition means), and a character string output unit 14 (character string extraction means). (output means), a designated character string receiving section 15 (designated character string receiving means), a tagging section 16 (tagging means), and a tagged content registration section 17 (content registration means).

The content acquisition unit 11 acquires content to be tagged. More specifically, the content acquisition unit 11 acquires content to be tagged by extracting untagged content from the search DB 3. Further, the content acquisition unit 11 receives the content to be tagged from the terminal 7 .
Here, the content acquired by the content acquisition unit 11 is, for example, a web page. A web page includes, for example, text written in a markup language such as HTML (Hypertext Markup Language).

The character string extraction processing unit 12 extracts character strings from the content acquired by the content acquisition unit 11. Here, the character string extracted by the character string extraction processing unit 12 is a part of the character string in the content having text, and is, for example, a keyword or key phrase that directly represents the content of the content.
When the content includes a keyword stored in the keyword dictionary 22 (keyword storage unit) (described later), the character string extraction processing unit 12 may extract the keyword as a character string.
Further, the character string extraction processing unit 12 may analyze the text of the content to extract nouns, and extract a predetermined noun from among the extracted nouns as a character string. Here, the predetermined noun refers to, for example, a compound noun or a proper noun.
Further, the character string extraction processing unit 12 may analyze the text of the content to extract nouns, and extract, as a character string, nouns whose number in the text is equal to or greater than a threshold value among the extracted nouns.

In addition, the character string extraction processing unit 12 uses the tagged content registered in the search DB 3 to assign a score indicating importance to the extracted noun, and selects a noun with a score equal to or higher than a threshold value using the tagged content registered in the search DB 3. You can also extract it as Here, the scoring indicating the degree of importance can be given using, for example, TF-IDF.
Further, the character string extraction processing unit 12 may extract a character string that is a proper noun from the content using a learning model that extracts a proper noun from the context of a text, which is stored in the learning model storage unit 23.
The related word acquisition unit 13 acquires related words related to the character string extracted by the character string extraction processing unit 12 from the related word dictionary 4. Here, the related words are words that include synonyms, synonyms, and the like.

The character string output unit 14 outputs the character string extracted by the character string extraction processing unit 12 to the terminal 7. Further, the character string output unit 14 outputs the related words acquired by the related word acquisition unit 13 to the terminal 7.
The designated character string receiving unit 15 receives from the terminal 7 a designated character string designated by the user of the terminal 7 from among the character strings and related words output by the character string output unit 14 .
Note that the processing by the character string output unit 14 and specified character string reception unit 15 is arbitrary. For example, when the content acquisition unit 11 acquires content from the terminal 7, the control unit 10 may cause the character string output unit 14 and the designated character string reception unit 15 to perform processing. On the other hand, when the content acquisition unit 11 acquires the content from the search DB 3, the control unit 10 may not perform the processing by the character string output unit 14 and the designated character string reception unit 15.

The tagging unit 16 adds the character string extracted by the character string extraction processing unit 12 to the corresponding content. Furthermore, the tagging unit 16 adds the related words acquired by the related word acquisition unit 13 to the corresponding content. Furthermore, when the character string output unit 14 performs processing, the tagging unit 16 adds the designated character string received by the designated character string receiving unit 15 to the corresponding content.
The tagged content registration unit 17 registers the tagged content to which the tag is attached by the tagging unit 16 in the search DB 3. Here, if the content is stored in the search DB 3, the tagged content registration unit 17 may update the content stored in the search DB 3 to the tagged content.
Details of each of these functions will be described later.

The storage unit 20 is a storage device such as a hard disk or a semiconductor memory device for storing programs, data, etc. necessary for the operation of the tagging support server 1.
The storage unit 20 includes a program storage unit 21, a keyword dictionary 22, and a learning model storage unit 23.
The program storage unit 21 is a storage area that stores various programs for functioning as the tagging support server 1. The program storage unit 21 stores a tagging support program 21a. The tagging support program 21a is a program for executing each function of the control unit 10 described above.

The keyword dictionary 22 is a storage area that stores keywords. The keyword dictionary 22 stores in advance a plurality of keywords (words) to be used as tags. Note that the keyword dictionary 22 may store not only keywords but also key phrases.
The learning model storage unit 23 is a storage area for storing various learning models. The learning model storage unit 23 may store, for example, a learning model for extracting proper nouns from the context of a text.
The communication interface unit 29 is an interface for communicating with the search DB 3, the related word dictionary 4, and the terminal 7.

<Search DB3>
The search DB 3 is a database that stores content. Before the tagging support server 1 of the content search support system 100 performs processing, the search DB 3 may store content that has not been tagged. Contents stored in the search DB 3 that are not tagged are tagged by the tagging support server 1 and stored in the search DB 3 as tagged content.
Further, the search DB 3 is used when the content search server 5 searches for content.
<Related word dictionary 4>
The related word dictionary 4 is, for example, a dictionary listing general related words. The related word dictionary 4 stores a plurality of related words having the same or similar meanings in association with each other. The related word dictionary 4 may be, for example, a thesaurus.

<Content search server 5>
The content search server 5 is a server that performs a process of searching and extracting content having a tag based on a search word from the search DB 3 in which tagged content is stored.
FIG. 2(B) shows functional blocks of the content search server 5.
The content search server 5 shown in FIG. 2(B) includes a control section 50, a storage section 60, and a communication interface section 69.

The control unit 50 is a CPU that controls the entire content search server 5. The control unit 50 cooperates with the above-mentioned hardware and executes various functions by appropriately reading and executing the OS and various application programs stored in the storage unit 60.
The control unit 50 includes a search term reception unit 51 (search term reception unit), a search related term acquisition unit 52 (search related term acquisition unit), a content extraction unit 53 (content extraction unit), and a list generation processing unit 54 ( tag list output means) and a tag selection processing section 55 (tag selection reception means, content list output means).

The search term accepting unit 51 accepts search terms from the terminal 8 .
The search related word acquisition unit 52 acquires related words related to the search word accepted by the search word reception unit 51 from the related word dictionary 4.
The content extraction unit 53 extracts tagged content having a tag that matches either the search term accepted by the search term acceptance unit 51 or the related term acquired by the search related term acquisition unit 52 from the search DB 3.

The list generation processing unit 54 generates a tag list for each tag based on the tagged content extracted by the content extraction unit 53 and outputs it to the terminal 8.
The tag selection processing unit 55 receives the selection of one tag from the tag list, generates a list of tagged contents to which the accepted tag is added, and outputs the list to the terminal 8.
Details of each of these functions will be described later.

The storage unit 60 is a storage device such as a hard disk or a semiconductor memory device for storing programs, data, etc. necessary for the operation of the content search server 5.
The storage unit 60 includes a program storage unit 61.
The program storage unit 61 is a storage area that stores various programs for functioning as the content search server 5. The program storage unit 61 stores a content search program 61a. The content search program 61a is a program for executing each function of the control unit 50 described above.
The communication interface section 69 is an interface for communicating with the search DB 3, the related word dictionary 4, and the terminal 8.

Note that a computer refers to an information processing device equipped with a control section, a storage device, etc., and the tagging support server 1 and the content search server 5 are both information processing devices equipped with a control section, a storage section, etc. included in the concept of
Further, the tagging support server 1 and the content search server 5 are not limited to one server each. It may be composed of a plurality of servers, and there is no limit to the number of hardware that constitutes the tagging support server 1 and the content search server 5.

For example, the hardware of the tagging support server 1 and the content search server 5 may be configured to include various servers such as a Web server, a DB (database) server, and an application server, as necessary. It may be configured with , or each may be configured with separate servers. Further, the tagging support server 1 and the content search server 5 may be, for example, a cloud.
Furthermore, it may be realized by one server having the functions of the tagging support server 1 and the content search server 5.

<Terminal 7, 8>
The terminal 7 shown in FIG. 1 is, for example, a terminal used by a user who creates content or a user who tags content.
Further, the terminal 8 is, for example, a terminal used by a user who wants to search for content stored in the search DB 3.
The terminal 7 and the terminal 8 can each be configured with, for example, a personal computer (PC), a tablet terminal, or the like. Although not shown, each of the terminals 7 and 8 includes a control section, a storage section, a display section, an input section, a communication interface section, and the like.
Note that the terminal 7 and the terminal 8 may not be separate terminals, but may be the same terminal that performs both functions.

<Content description>
Next, an example of content handled by the content search support system 100 will be explained.
FIG. 3 is a diagram showing an example of content 30 to which tags are added by the tagging support server 1 according to the present embodiment.
Content 30 shown in FIG. 3 is a web page regarding merchandise of a certain company. The content 30 includes a text document explaining the merchandise.
Content 30 includes various information regarding merchandise. In particular, the "Summary" and "Features" sections contain content that directly represents the contents of the content 30.
In the following example, the content 30 stored in the search DB 3 will be described as a web page related to products of a company that has introduced the content search support system 100, as illustrated in FIG. Furthermore, when processing related to tagging, processing is performed on the "Summary" and "Features" portions of the content 30.

<Processing explanation>
Next, the processing of the tagging support server 1 will be explained.
FIG. 4 is a flowchart showing the content tagging process of the tagging support server 1 according to the present embodiment.
As a premise of this process, the search DB 3 stores at least content that is not tagged. Note that tagged content may be stored in the search DB 3.

In step S (hereinafter simply referred to as "S") 11 in FIG. 4, the control unit 10 (content acquisition unit 11) extracts untagged content from the search DB 3. Here, if a plurality of untagged contents are extracted, the control unit 10 performs the processes from S12 onwards for each content.
In S12, the control unit 10 (character string extraction processing unit 12) performs character string extraction processing to extract some character strings in the content from the content. A plurality of methods can be assumed for the process of extracting a part of character strings from the content, and any of the methods may be used.

Here, the process of extracting a character string will be explained based on an example.
(Example 1)
In the first embodiment, a keyword dictionary 22 is used.
The control unit 10 refers to the keyword dictionary 22 and checks for each keyword whether the keyword registered in the keyword dictionary 22 is included in the content.
Then, the control unit 10 acquires a keyword included in the content, which is a keyword from the keyword dictionary 22, as a character string to be tagged.
For example, if the keywords "microwave oven,""heattreatment,""heat-resistantspecifications," and "pouch" are registered in the keyword dictionary 22, all of the above keywords are acquired in the content 30 shown in FIG. be done.

(Example 2)
In the second embodiment, nouns are extracted from content, and predetermined nouns are extracted as keywords.
The control unit 10 performs, for example, morphological analysis on the text of the content to extract nouns.
Then, the control unit 10 acquires, for example, a compound noun or a proper noun from among the extracted nouns as a character string to be tagged. Furthermore, the control unit 10 may acquire frequently appearing nouns whose number of appearances is equal to or greater than a threshold value among the extracted nouns, as character strings to be tagged.
In the content 30 shown in FIG. 3, as compound nouns and proper nouns, for example, "microwave oven,""heattreatment,""heat-resistantspecifications," and "○○ (proper noun)" are acquired as character strings. Furthermore, in the content 30, for example, "range" is acquired as a character string as a frequently occurring noun.

(Example 3)
In the third embodiment, nouns are extracted from content and keywords are extracted using statistical values.
The control unit 10 uses the content (which may or may not be tagged) registered in the search DB 3 to assign a score indicating importance to the extracted noun.
This scoring can be done using, for example, TF-IDF.
Here, TF-IDF is a value used when extracting the characteristic words of the document, and when there are several documents, the important words for a certain document are determined from the words that appear in them and their frequency. It is something that quantifies what something is. TF (Term Frequency) represents the number of occurrences in a document, and the more times a word appears in a document, the more likely it is to be important. IDF (Inversed Document Frequency) is the number of documents in which a word appears, and indicates that a word that appears in many documents is unlikely to become a feature word.
Then, the control unit 10 extracts nouns having scores equal to or higher than the threshold value calculated using TF-IDF as character strings.

(Example 4)
Example 4 uses a learning model to extract proper nouns from the context of a text.
Here, as the learning model, for example, deep learning such as BERT (Bidirectional Encoder Representations from Transformers) and CRF (Conditional Random Fields) can be used for learning.

Note that the control unit 10 may use any of the methods in the embodiments described above, or may use a plurality of methods, in extracting the character string.
For example, the control unit 10 may not use all of the keywords acquired in the first embodiment as character strings, but may use keywords that appear a plurality of times as character strings.

In S13 of FIG. 4, the control unit 10 acquires related words related to the character string extracted in the process of S12 from the related word dictionary 4.
For example, when extracting "telework" as a character string, the control unit 10 refers to the related word dictionary 4 and selects "telework" as a synonym, and "online system" as a related word, for example. , respectively.
In S14, the control unit 10 (tagging unit 16) adds the character string extracted in the process of S12 and the related word acquired in the process of S13 as a tag to the content.
In S15, the control unit 10 (tagged content registration unit 17) replaces the tagged content with the tag with the content extracted in the process of S11, so that the tagged content with the tag is stored in the search DB 3. Register. After that, the control unit 10 ends this process.

Note that in the above description, tags are added to content already registered in the search DB 3. When this content search support system 100 is introduced, tags can be added to content stored in the search DB 3 that has not been tagged by performing the processing.

Also, for example, when registering content from the terminal 7 to the search DB 3, the tagging support server 1 can perform content tagging processing. In that case, the control unit 10 (content acquisition unit 11) acquires the content from the terminal 7 instead of the process in S11 of FIG. 4, for example. Then, for example, after the process of S13, the control unit 10 (character string output unit 14) outputs the extracted character string and related words to the terminal 7, and the user of the terminal 7 inputs the character string that becomes a tag candidate. It may be possible to confirm it. Then, the control unit 10 (specified character string receiving unit 15) receives the specified character string specified by the user from the terminal 7, and in S14, the control unit 10 (tagging unit 16) receives the specified character string specified by the user from the terminal 7. Add a character string as a tag to the content.
In this way, the tagging support server 1 can add the tag specified by the user from the tag candidates confirmed by the user to the content.

Next, the processing of the content search server 5 will be explained.
FIG. 5 is a flowchart showing content search processing by the content search server 5 according to this embodiment.
6 and 7 are diagrams showing display examples on the terminal 8 according to the present embodiment.
In S51 of FIG. 5, the control unit 50 (search term accepting unit 51) accepts a search term for searching for content from the terminal 8. The search word is a keyword specified by the user of the terminal 8.

In S52, the control unit 50 (search related term acquisition unit 52) acquires related terms related to the search term accepted in S51 from the related term dictionary 4.
In S53, the control unit 50 (content extraction unit 53) extracts, from the search DB 3, tagged content having a tag that matches either the search term accepted in S51 or the related term acquired in the process of S52. .
In S54, the control unit 50 (list generation processing unit 54) generates a tag list for each tag based on the extracted tagged content, and outputs the generated tag list to the terminal 8.

In S55, the control unit 50 (tag selection processing unit 55) determines whether or not the user's selection of one tag from the tag list is received from the terminal 8. If the selection of one tag is accepted (S55: YES), the control unit 50 moves the process to S56. On the other hand, if the selection of one tag has not been accepted (S55: NO), the control unit 50 ends this process.
In S56, the control unit 50 (tag selection processing unit 55) generates a list of tagged contents to which the accepted tags have been added, and outputs the generated list of contents to the terminal 8. After that, the control unit 50 ends this process.

FIG. 6 shows an example of a tag list screen 80 output to the terminal 8.
Only the search condition area 81 is displayed on the tag list screen 80 when searching. Then, on the terminal 8, when the user specifies a search term in the search term input area 81a in the search condition area 81 and selects the search button 81b, the tag list screen 80 is displayed below the search condition area 81. The list area 82 is changed to include the list area 82.
The tag list screen 80 shown in FIG. 6 is a search result screen when keyword search is specified as a condition in the search condition area 81 and "security" is specified in the search term input area 81a. The control unit 50 acquires tagged content having a tag containing either the search word "security" or a related word of "security" from the search DB 3. Then, the control unit 50 totals the number of tagged contents for each tag attached to the acquired tagged content, generates and outputs a tag list including the tags and the total number.

In the example of the tag list screen 80 shown in FIG. 6, the list described as topic is created by the content search process described above. On the other hand, the list described as the target field or technical field is created based on a predetermined portion of the tagged content.
Then, when the user performs an operation to select one topic (select operation for one tag), the control unit 50 outputs a content list screen 90 shown in FIG. 7 to the terminal 8.

The content list screen 90 includes a summary area 91 and outputs a summary of each content.
Summary area 91 includes a tag area 91a. The tag area 91a is an area for outputting tags added to the content output in the summary area 91. Each tag includes a character string and a number in parentheses. The number in parentheses indicates the number of tagged contents stored in the search DB 3 to which the character string is tagged.
When the user selects a tag in the tag area 91a, the selected tag is output to the input area of the search area 92 at the top of the content list screen 90, so that the user can further search for content to which the tag is attached. It is also possible to output the

As described above, according to this embodiment, the content search support system 100 has the following effects.
(1) The tagging support server 1 extracts some character strings from the content, tags the extracted character strings to the content, and stores the tagged content in the search DB 3.
Therefore, the tagging support server 1 can add tags suitable for the content to the content.

(2) When the keyword stored in the keyword dictionary 22 is included in the content, the tagging support server 1 extracts the keyword as a character string.
Therefore, the keywords stored in the keyword dictionary 22 can be acquired as tags, so tags suitable for the content can be added to the content through simpler processing. Furthermore, since tags can be added depending on the keyword dictionary 22, variations in tags to be added can be suppressed.

(3) The tagging support server 1 analyzes the text of the content to extract nouns, and extracts predetermined nouns from among the extracted nouns as character strings.
Further, among the extracted nouns, a predetermined noun whose appearance count in the content is equal to or greater than a threshold is extracted as a character string.
Furthermore, using the tagged content registered in the search DB 3, a score indicating importance is assigned to the extracted noun, and a predetermined noun having a score equal to or higher than a threshold value is extracted as a character string.
Therefore, for example, a compound noun, a proper noun, or the like can be added as a tag, and the added tag can represent the characteristics of the content.
Further, nouns that appear frequently can be added as tags, and the added tags can represent characteristics of the content.
Furthermore, a noun whose score indicating importance is equal to or higher than a threshold value can be added as a tag, and the added tag can represent a feature of the content.

(4) The tagging support server 1 extracts character strings that are proper nouns from the content using a learning model that is stored in the learning model storage unit 23 and that extracts proper nouns from text.
Therefore, proper nouns extracted through simpler processing can be added as tags, and the added tags can represent the characteristics of the content.

(5) The tagging support server 1 obtains related words related to the extracted character string from the related word dictionary 4, and further tags the content with the obtained related words.
Therefore, tags added to content can be expanded.

(6) The tagging support server 1 outputs the extracted character strings, receives a designated character string designated by the user from among the outputted character strings, and tags the content with the received designated character string.
Therefore, candidates for tags to be added to content can be presented to the user. Then, the tag specified by the user among the tag candidates can be added to the content. As a result, tags that the user considers inappropriate can be prevented from being added.

(7) The content search server 5 acquires related words related to the received search word from the related word dictionary 4, and stores tagged content having a tag that matches either the search word or the related word in the search DB 3. Based on the extracted tagged content, a tag list for each tag is generated and output.
Therefore, content that has been tagged by the tagging support server 1 can be searched using the tag. At this time, not only content tagged with a tag matching the search term but also a tag matching a word related to the search term is extracted, so the range of content extracted by the search can be expanded.

(8) The content search server 5 accepts the selection of one tag from the tag list, and outputs a content list of tagged content to which the accepted tag has been added. The content list includes tags added to tagged content.
Therefore, using the tag, it is possible to further search for tagged content to which the tag has been added.

Although the embodiments of the present invention have been described above, the present invention is not limited to the embodiments described above. Further, the effects described in the embodiments are merely a list of the most preferable effects resulting from the present invention, and the effects of the present invention are not limited to those described in the embodiments. In addition, although the embodiment mentioned above and the modification mentioned later can be used in combination suitably, detailed description is abbreviate|omitted.

(Deformed form)
(1) In the present embodiment, an example has been described in which a character string to be added as a tag is extracted from the description of a predetermined portion of the content, but the present invention is not limited to this. The target for extracting character strings may be another location or all descriptions of the content. However, it is more desirable to extract a character string that includes a portion where the characteristics of the content are described.

(2) In the present embodiment, an example has been described in which tags are added to content that is not tagged, but the present invention is not limited to this. It may be content that has already been tagged using another method. In that case, the tags assigned by the tag assignment support server and the tags that have already been assigned may be managed separately. In this way, content that is used in an existing system can be searched for by processing by the content search server as a new search process. In particular, data migration processing and the like can be easily performed.

1 Tagging support server 3 Search DB
4 Related word dictionary 5 Content search server 7, 8 Terminal 10, 50 Control section 11 Content acquisition section 12 Character string extraction processing section 13 Related word acquisition section 14 Character string output section 15 Specified character string reception section 16 Tagging section 17 Tagged Content registration section 20, 60 Storage section 21a Tagging support program 22 Keyword dictionary 23 Learning model storage section 30 Content 51 Search word reception section 52 Search related word acquisition section 53 Content extraction section 54 List generation processing section 55 Tag selection processing section 61a Content Search program 80 Tag list screen 90 Content list screen 100 Content search support system N Communication network

Claims (11)

Character string extraction means for extracting a part of character strings in content having text from the content;
tagging means for tagging the content with the character string extracted by the character string extraction means;
Content registration means for storing the tagged content tagged by the tagging means in a search database;
A tagging support device comprising: The tagging support device according to claim 1,
Equipped with a keyword storage unit that stores keywords,
The character string extraction means is a tagging support device that extracts the keyword as the character string when the keyword stored in the keyword storage unit is included in the content. The tagging support device according to claim 1,
comprising noun extraction means for analyzing the text of the content and extracting nouns,
The character string extraction means is a tagging support device that extracts a predetermined noun from among the nouns extracted by the noun extraction means as the character string. In the tagging support device according to claim 3,
The character string extraction means is a tagging support device that extracts, as the character string, the predetermined noun, of which the number of occurrences of the noun in the text is equal to or greater than a threshold value, from among the nouns extracted by the noun extraction means. . In the tagging support device according to claim 3,
The character string extraction means uses the tagged content registered in the search database to assign a score indicating importance to the noun extracted by the noun extraction means, and assigns a score that is equal to or higher than a threshold. A tagging support device that extracts the predetermined noun having the character string as the character string. The tagging support device according to claim 1,
The character string extraction means is a tagging support device that extracts the character string that is a proper noun from the content using a learning model that extracts a proper noun from the context of a text. In the tagging support device according to any one of claims 1 to 6,
comprising a related word acquisition means for acquiring a related word related to the character string extracted by the character string extraction means from a related word storage unit storing a plurality of related words;
The tagging device further tags the content with the related word acquired by the related word acquiring device. In the tagging support device according to any one of claims 1 to 6,
a character string output means for outputting the character string extracted by the character string extraction means;
specified character string receiving means for receiving a specified character string specified by a user from among the character strings output by the character string output means;
Equipped with
The tagging means is a tagging support device for tagging the content with the designated character string received by the designated character string receiving means. computer,
Character string extraction means for extracting a part of character strings in content having text from the content;
tagging means for tagging the content with the character string extracted by the character string extraction means;
Content registration means for storing the tagged content tagged by the tagging means in a search database;
A program to function as A content search device communicably connected to the search database in which the tagged content tagged by the tagging support device according to claim 1 is stored,
a search term reception means for accepting a search term;
Search related word acquisition means for acquiring related words related to the search word accepted by the search word reception means from a related word storage unit storing a plurality of related words;
Content extracting means for extracting the tagged content having a tag that matches either the search word accepted by the search word receiving means or the related word obtained by the search related word obtaining means from the search database; ,
tag list output means for generating and outputting a tag list for each of the tags based on the tagged content extracted by the content extraction means;
A content search device comprising: The content search device according to claim 10,
tag selection reception means for accepting selection of one of the tags from the tag list output by the tag list output means;
content list output means for outputting a list of the tagged contents to which the tags received by the tag selection reception means are attached;
Equipped with
The content list output means is a content search device that outputs a list of the tagged content including the tag attached to each tagged content.

Images