Information processing device, information processing method, and information processing program

Abstract

To provide an information processing device capable of extracting an unpredictable word in a relationship with a specific keyword, an information processing method, and an information processing program.SOLUTION: An information processing device comprises a category extraction unit, a word extraction unit, and an information output unit. The category extraction unit extracts a category of a posting content including a specific word. The word extraction unit extracts a word included in a posting content not including a specific word among posting contents of the category extracted by the category extraction unit as a target word. The information output unit outputs information including the target word extracted by the work extraction unit.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, natural language processing for extracting words from content including sentences has been known. For example, Patent Document 1 discloses a technique for classifying a document into one or more categories from among a plurality of categories, and for each of one or more words extracted from the document, extracting words that appear less frequently within a category as highly unexpected words within the category based on the frequency of appearance of each word within the one or more categories. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2011-095905 Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the above-mentioned conventional technology, although words that appear infrequently within a category are extracted as words that are highly unexpected within the category, it may be difficult to extract words that are unexpected in relation to a specific word.

[0005] The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can extract unexpected words in relation to specific keywords. [Means for solving the problem]

[0006] The information processing device according to the present application includes a category extraction unit, a word extraction unit, and an information output unit. The category extraction unit extracts categories of posted content that include a specific word. The word extraction unit extracts, as target words, words included in posted content that does not include the specific word from among the posted content of the category extracted by the category extraction unit. The information output unit outputs information that includes the target words extracted by the word extraction unit. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to extract unexpected words in relation to a specific keyword. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a user information table stored in a user information storage unit according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a content table stored in the content storage unit according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of list information that is output as information related to target words by the information output unit of the information processing apparatus according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of document information that is output as information related to target words by the information output unit of the information processing apparatus according to the embodiment. [Figure 8] FIG. 8 is a flowchart showing an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 9]FIG. 9 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, modes for implementing an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the respective embodiments can be appropriately combined within the scope of not causing any contradiction in the processing content. Furthermore, the same components in the following embodiments will be assigned the same reference numerals, and redundant explanations will be omitted.

[0010] [1. An example of information processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment.

[0011] 1, an information processing device 1 according to an embodiment stores a group of posted contents including a plurality of posted contents. The posted contents are contents posted from a terminal device (not shown) or the like, such as Q&A content, word-of-mouth content, or news content, but are not limited to these examples as long as they are posted content.

[0012] Q&A content is question content and answer content posted to an online service that accepts questions and answers by category. Word-of-mouth content is, for example, word-of-mouth content posted to an online service that accepts word-of-mouth about review subjects. Review subjects are, for example, trading objects such as products and services, and are classified by category.

[0013] The information processing device 1 performs a reception process to receive input of a specific word (step S1). The specific word is a word input by a user of the information processing device 1, and is, for example, a word about which the user of the information processing device 1 wants to know the unexpected relationship. When the user of the information processing device 1 wants to know the unexpected word in relation to "lotion," the user inputs "lotion" into the information processing device 1 as the specific word.

[0014] When the information processing device 1 receives the input of the specific word, it performs a category extraction process to extract relevant categories that are categories of posted content that includes the specific word (step S2). For example, the information processing device 1 extracts posted content that includes the specific word as relevant content, and extracts one or more categories from the categories of the extracted relevant content as relevant categories.

[0015] The information processing device 1 extracts a predetermined number of categories as relevant categories from among the extracted categories of relevant content, for example, in descending order of the number of relevant contents or the ratio. The ratio of relevant contents in a category is the ratio of the number of relevant contents to the total number of contents in the category.

[0016] For example, if the number of contents included in a category is Na and the number of relevant contents included in the category is Nb, the ratio R of relevant contents in the category is expressed as, for example, R=Nb / Na. Furthermore, the predetermined number is, for example, 2 or more, but may also be 1.

[0017] For example, suppose the predetermined number is 3, and the top three categories in descending order of the number or ratio of content including the specific word "lotion" are "skin care," "acne care," and "makeup, cosmetics." In this case, the information processing device 1 extracts the categories "skin care," "acne care," and "makeup, cosmetics" as the relevant categories.

[0018] Categories of posted content are defined in a hierarchical structure, with the size of the posted content category increasing the higher in the hierarchical structure and decreasing the lower in the hierarchical structure. The information processing device 1 extracts the relevant category from, for example, the lowest-level categories. For example, the above-mentioned categories "skin care," "acne care," and "makeup and cosmetics" are lowest-level categories.

[0019] The category immediately above the categories "skin care" and "makeup, cosmetics" is the category "cosmetics, beauty," and the category immediately above the category "cosmetics, beauty" is the category "health, beauty, fashion." The category immediately above the category "acne care" is the category "health, illness, hospital," and the category immediately above the category "health, illness, hospital" is the category "health, beauty, fashion."

[0020] The information processing device 1 can also extract a relevant category from a category higher than the lowest category. The information processing device 1 can also accept a designation of a higher category from the user of the information processing device 1, and extract a relevant category from a category lower than the accepted upper category.

[0021] Furthermore, in addition to the specific word, the information processing device 1 can also receive input of a hierarchy of categories to be extracted as relevant categories from the user of the information processing device 1. In this case, the information processing device 1 extracts relevant categories from the hierarchy of categories received from the user of the information processing device 1. In this way, the hierarchy of categories to be extracted as relevant categories may be determined in advance or may be specified by the user of the information processing device 1.

[0022] Furthermore, the information processing device 1 can exclude a specific category from the categories of posted content that includes a specific word. The specific category is, for example, a category that is preset for the specific word or a category that is input by the user of the information processing device 1.

[0023] Next, the information processing device 1 performs a word extraction process to extract, as target words, words included in target content, which is posted content that does not include the specific word from posted content included in the category extracted in step S2 (step S3). The information processing device 1, for example, divides the target content into multiple morphemes by morphological analysis, and extracts specific parts of speech (e.g., nouns) included in the multiple divided morphemes as target words. This allows the information processing device 1 to extract words that are unexpected in relation to the specific word as target words.

[0024] For example, suppose the specific word is "lotion" and the corresponding categories are "skin care," "acne care," and "makeup, cosmetics." In this case, the information processing device 1 extracts, as target content, posted content that does not contain the specific word "lotion" from among posted content included in any of the categories "skin care," "acne care," and "makeup, cosmetics." Then, the information processing device 1 extracts, as target words, words included in the target content.

[0025] Next, the information processing device 1 generates target word information including the target words extracted in step S3 and outputs the generated target word information (step S4). For example, the information processing device 1 generates and outputs list information including a target word list in which the target words extracted in step S3 are arranged according to a predetermined rule as the target word information.

[0026] For example, the information processing device 1 can generate, as target word information, list information including a target word list in which the target words extracted in step S3 are arranged in order of their similarity to a specific word, or can generate, as target word information, list information including a target word list in which the target words are arranged in order of the number of times they are included in the target content.

[0027] If there are multiple applicable categories, the list information is a target word list for each applicable category, but there may be one target word list for multiple applicable categories. Also, the list information may include specific words, but may not include specific words.

[0028] Furthermore, the information processing device 1 can also generate, as target word information, document information that is information on a sentence containing the target word extracted in step S3 and the specific word received in step S1. For example, the information processing device 1 can generate, as target word information, sentence information containing the target word and the specific word by replacing some words other than the specific word among multiple words contained in the relevant content with the target word.

[0029] In addition, the information processing device 1 can also generate text information containing a target word and a specific word as target word information, for example, by replacing a first word contained in a predetermined template text with a specific word and replacing a second word contained in the template text with a target word.

[0030] The information processing device 1 can also generate text information including the target word and the specific word as target word information using a natural language processing technology. For example, the information processing device 1 generates text information including the target word and the specific word as target word information using a natural language processing model that can generate text from keywords as target word information. The natural language processing model is, for example, a model using well-known BERT (Bidirectional Encoder Representations from Transformers) or GPT-3 (Generative Pre-Training-3).

[0031] In this way, the information processing device 1 extracts a category of posted content that includes the specific word, and extracts, as target words, words included in posted content that does not include the specific word among the posted content of the extracted category. This allows the information processing device 1 to extract, as information on the target word, words that are unexpected in relation to the specific word.

[0032] The configuration of an information processing system including the information processing device 1 that performs such processing will be described in detail below.

[0033] [2. Information Processing System Configuration] 2 is a diagram illustrating an example of a configuration of an information processing system according to an embodiment. As illustrated in FIG. 2, the information processing system 100 according to the embodiment includes an information processing device 1, a plurality of terminal devices 2, and a terminal device 3.

[0034] The information processing device 1, the multiple terminal devices 2, and the terminal device 3 are connected to each other via a network N so as to be able to communicate with each other via wired or wireless means. The information processing system 100 shown in Fig. 2 may include multiple information processing devices 1. The network N is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network) such as the Internet.

[0035] The information processing device 1 is an information processing device that cooperates with terminal devices 2 and 3 of each user and provides each user with various types of information online, and is realized by, for example, one or more servers or a cloud system.

[0036] The information processing device 1 provides online services such as a Q&A site, a word-of-mouth site, a news site, a shopping site, an auction site, a flea market site, a restaurant introduction site, or an SNS site.

[0037] The terminal device 2 is a terminal device of a user UA who posts content provided by the information processing device 1, and the terminal device 3 is a terminal device of a user UB who uses the target word providing service provided by the information processing device 1.

[0038] The user UA operates the terminal device 2 to transmit posted content from the terminal device 2 to the information processing device 1. The posted content is content for an online service provided by the information processing device 1, and is classified into a corresponding category from among multiple categories. The category of the posted content is a category specified by the user UA or a category classified by the information processing device 1 according to words contained in the posted content.

[0039] For example, on a Q&A site, it is question content and answer content, on a review site, it is review content, and on a news site, it is news content. Also, on a shopping site, auction site, or flea market site, posted content is content for buying and selling items (e.g., a purchase page).

[0040] The terminal devices 2 and 3 are, for example, desktop PCs (Personal Computers), notebook PCs, tablet terminals, smartphones, mobile phones, or PDAs (Personal Digital Assistants). The multiple terminal devices 2 are operated by different users UA, and the terminal device 3 is operated by a user UB. Note that the terminal devices 2 and 3 are not limited to the above-mentioned examples and may be, for example, smart watches or wearable devices.

[0041] In addition, the terminal devices 2 and 3 can connect to the network N via wireless communication networks such as LTE (Long Term Evolution), 4G (4th Generation), and 5G (5th Generation: 5th generation mobile communication system), or via short-range wireless communication such as Bluetooth (registered trademark) and wireless LAN, and communicate with the information processing device 1.

[0042] 3. Configuration of Information Processing Device 1 The following describes an example of the functional configuration of the information processing device 1. Fig. 3 is a diagram showing an example of the configuration of the information processing device 1 according to an embodiment. As shown in Fig. 3, the information processing device 1 has a communication unit 10, a storage unit 11, and a processing unit 12.

[0043] [3.1. Communication Unit 10] The communication unit 10 is realized by, for example, a network interface card (NIC). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from terminal devices 2 and 3 via the network N.

[0044] [3.2. Storage section 11] The storage unit 11 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 11 also has a user information storage unit 20 and a content storage unit 21.

[0045] 3.2.1. User Information Storage Unit 20 The user information storage unit 20 stores various types of information related to users UA and UB. Fig. 4 is a diagram showing an example of a user information table stored in the user information storage unit 20 according to the embodiment. In the example shown in Fig. 4, the user information table stored in the user information storage unit 20 includes information on items such as "user ID," "attribute information," and "history information."

[0046] "User ID" is an identifier that identifies user UA, UB. "Attribute information" is attribute information related to the attributes of user UA, UB associated with "user ID." Attributes of user UA, UB include, for example, demographic attributes and psychographic attributes. Demographic attributes are demographic attributes such as age, gender, occupation, place of residence, annual income, and family composition. Psychographic attributes are psychological attributes such as lifestyle, values, and interests.

[0047] "History information" is history information that includes information such as the service usage history of users UA and UB associated with the "user ID," and includes, for example, search history information of users UA and UB, browsing history information of users UA and UB, and payment history information of users UA and UB.

[0048] The search history information of the users UA and UB is, for example, information on the search history of web content on search sites, information on the search history of various websites, etc. The browsing history information of the users UA and UB is information on the browsing history of web content of the users UA and UB.

[0049] The payment history information of users UA and UB includes purchase history information regarding products purchased by users UA and UB online, at physical stores, or at physical facilities using payment services, and service usage history information regarding services used by users UA and UB for a fee online, at physical stores, or at physical facilities using payment services.

[0050] The purchase history information includes information on products purchased by the users UA and UB, information on the purchase cost, purchase date and time, information on the store where the purchase was made, etc. The service usage history information includes information on services used by the users UA and UB, information on the usage cost, purchase date and time, information on the store where the service was used, etc.

[0051] The information stored in the user information storage unit 20 is not limited to the above and may include various information depending on the purpose. For example, the information stored in the user information storage unit 20 may include information indicating the context history of the users UA and UB.

[0052] 3.2.2. Content Storage Unit 21 The content storage unit 21 stores information related to content. Fig. 5 is a diagram showing an example of a content table stored in the content storage unit 21 according to the embodiment. In the example shown in Fig. 5, the content table stored in the content storage unit 21 has information on items such as "content ID," "content," and "category."

[0053] "Content ID" is an identifier that identifies posted content. "Content" is information about posted content associated with "Content ID." Posted content is content posted by online services on one or more sites, such as Q&A sites, review sites, news sites, shopping sites, auction sites, flea market sites, restaurant introduction sites, and SNS sites.

[0054] "Category" is information indicating the category to which the posted content belongs. The categories of posted content are defined, for example, in a hierarchical structure, and the size of the category of posted content increases as the category increases in the hierarchy and decreases as the category decreases in the hierarchy.

[0055] For example, top-level categories include "health, beauty, fashion," "lifestyle and lifestyle guide," and "entertainment and hobbies." Categories directly below the top-level category "health, beauty, fashion" include "cosmetics, beauty" and "health, illness, hospital."

[0056] Categories directly below the category "cosmetics, beauty" include "skin care," "makeup, cosmetics," and "hairstyles." Categories directly below the category "health, illness, hospital" include "acne care," "dental care," and "eye diseases."

[0057] In FIG. 5, the content with the content ID “C1” is content CNT1, and the category is category C. A1 The content of content ID "C2" is content CNT2, and the category is category C. B3 The content with the content ID "C3" is content CNT3, and the category is category C. D2 is.

[0058] Although not shown, the content storage unit 21 also includes information about the site where the posted content is posted. In the example shown in FIG. 5, the content is expressed as a character string including an abstract code such as "content CNT1," but the content may be, for example, data in a file format including various information such as specific numerical values ​​and specific character strings, or information indicating the storage location of such data. The content may be information in a format other than the above. The content storage unit 21 may store various types of information according to the purpose, without being limited to the above.

[0059] [3.3. Processing Unit 12] The processing unit 12 is a controller, and is realized by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) using RAM as a work area to execute various programs (one example of an information processing program) stored in a storage device inside the information processing device 1. The processing unit 12 is also a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0060] 3, the processing unit 12 has an acquisition unit 30, a reception unit 31, a provision unit 32, a category extraction unit 33, a word extraction unit 34, an information generation unit 35, and an information output unit 36, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may have any other configuration as long as it performs the information processing described below.

[0061] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various types of information. The acquisition unit 30 acquires various types of information from the storage unit 11. The acquisition unit 30 acquires various types of information from the user information storage unit 20, the content storage unit 21, and the like.

[0062] The acquisition unit 30 receives various types of information from an external information processing device via the communication unit 10. The acquisition unit 30 receives various types of information from the terminal device 2. For example, the acquisition unit 30 acquires information about the user UA from the terminal device 2, stores the acquired information about the user UA in the user information storage unit 20, and updates the user information table. The acquisition unit 30 also acquires posted content from the terminal device 2 or other external devices, and stores the acquired posted content in the content storage unit 21, updating the content table.

[0063] [3.3.2. Reception Unit 31] The reception unit 31 receives various requests. The reception unit 31 receives various requests from external information processing devices. The reception unit 31 receives information indicating the various requests from the external information processing devices via the communication unit 10. For example, the reception unit 31 receives requests from the terminal devices 2 and 3.

[0064] For example, the reception unit 31 receives a posting request, a viewing request, etc. from the terminal device 2. The posting request includes information such as posted content, and when the reception unit 31 receives a posting request from the terminal device 2, the reception unit 31 adds the information such as the posted content included in the posting request to a content table in the content storage unit 21.

[0065] The receiving unit 31 receives, for example, a target word information request from the terminal device 2 or the terminal device 3. The target word information request includes, for example, information such as the user ID of the user UB and specific words. The target word information request may also include information such as a designated site, a designated content type, a designated category, and an excluded category. A designated category is a category that is within the extraction range of the relevant category, and an excluded category is a category that is not extracted as the relevant category.

[0066] [3.3.3.Providing Department 32] The providing unit 32 provides various online services to users UA and UB of the terminal devices 2 and 3. The online services provided by the providing unit 32 are, for example, online services provided by one or more sites such as a Q&A site, a word-of-mouth site, a news site, a shopping site, an auction site, a flea market site, a restaurant introduction site, and a social networking site.

[0067] For example, when a viewing request from the terminal device 2 is accepted by the accepting unit 31, the providing unit 32 transmits the posted content corresponding to the viewing request and acquired by the acquiring unit 30 to the terminal device 2 via the communication unit 10 and the network N.

[0068] [3.3.4. Category Extraction Unit 33] When the receiving unit 31 receives a target word information request, the category extraction unit 33 acquires the specific words included in the target word information request and extracts the category of the posted content that includes the acquired specific words as the relevant category.

[0069] The category extraction unit 33 extracts, for example, posted content that includes a specific word as relevant content, and extracts a category that includes the extracted relevant content as a relevant category.

[0070] When the target word information request includes information on a specified site, a specified content type, and a specified category, the category extraction unit 33 extracts the relevant category based on the information on the specified site, the specified content type, and the specified category included in the target word information request.

[0071] Specifically, the category extraction unit 33 extracts posted content of a specified content type from posted content included in a specified category of a specified site as relevant content, and extracts a category from the specified category of the specified site that includes the relevant content as the relevant category.

[0072] Furthermore, when the target word information request includes information on excluded sites, the category extraction unit 33 extracts, as the relevant categories, categories of posted content that includes the specific word, excluding the excluded categories. The excluded categories are an example of preset categories.

[0073] For example, suppose the specified site is a Q&A site, the specified content type is "Questions," the specified category is "Cosmetics, Beauty," and the excluded categories are "Nail Care" and "Cosmetic Surgery." The categories below the "Cosmetics, Beauty" category are "Makeup, Cosmetics," "Skin Care," "Perfume," "Beauty Salons, Hair Removal," "Hair Care," "Hairstyles," "Nail Care," and "Cosmetic Surgery."

[0074] In this case, the category extraction unit 33 extracts the posted content of the question included in the category "cosmetics, beauty" of the Q&A site as the relevant content. Then, the category extraction unit 33 extracts the categories below the category "cosmetics, beauty" that include the relevant content and are other than the excluded categories "nail care" and "cosmetic surgery" as the relevant categories.

[0075] In addition, if the target word information request does not include information on the specified site, specified content type, specified category, and excluded category, the category extraction unit 33 can also extract the relevant category based on information on at least one of the predetermined specified site, specified content type, specified category, and excluded category.

[0076] For example, the category extraction unit 33 may have an excluded category table that associates specific words with excluded categories for each specific word, and in this case, the excluded category associated with the specific word included in the target word information request is extracted from the excluded category table.

[0077] The category extraction unit 33 extracts a predetermined number of categories as relevant categories from among the extracted categories of relevant content, for example, in descending order of the number of relevant contents or the ratio. The ratio of relevant contents in a category is the ratio of the number of relevant contents to the total number of contents in the category.

[0078] For example, if the number of contents included in a category is Na and the number of relevant contents included in the category is Nb, the ratio R of relevant contents in the category is expressed as, for example, R=Nb / Na. Furthermore, the predetermined number is, for example, 2 or more, but may also be 1.

[0079] For example, suppose the predetermined number is 3, and the top three categories in order of the number or ratio of content including the specific word "lotion" are the category "skin care," the category "acne care," and the category "makeup, cosmetics." In this case, the category extraction unit 33 extracts the category "skin care," the category "acne care," and the category "makeup, cosmetics" as the relevant categories.

[0080] The category extraction unit 33 can also extract relevant categories from categories higher in the hierarchy than the lowest-level category. The category extraction unit 33 can also receive, in addition to the specific word, an input from the user UB of the hierarchy of categories to be extracted as relevant categories. In this case, the category extraction unit 33 extracts relevant categories from the hierarchy of categories received from the user UB. In this way, the hierarchy of categories to be extracted as relevant categories may be predetermined or may be specified by the user UB.

[0081] [3.3.5. Word Extraction Unit 34] The word extraction unit 34 extracts, as target words, words contained in posted content that does not contain the specific word from the posted content in the relevant category extracted by the category extraction unit 33.

[0082] For example, the word extraction unit 34 extracts, as target content, posted content that does not contain a specific word from posted content in the category extracted by the category extraction unit 33. Then, the word extraction unit 34 extracts, as target words, words that are included in the target content.

[0083] For example, suppose the specific word is "lotion" and the corresponding categories are "skin care," "acne care," and "makeup, cosmetics." In this case, the word extraction unit 34 extracts, as target content, posted content that does not contain the specific word "lotion" from among multiple posted content items included in any of the categories "skin care," "acne care," and "makeup, cosmetics." Then, the word extraction unit 34 extracts, as target words, words included in the target content items.

[0084] The word extraction unit 34, for example, divides the target content into a plurality of morphemes by morphological analysis, and extracts specific parts of speech (e.g., nouns) included in the plurality of divided morphemes as target words. Note that the word extraction unit 34 may have, for example, a word list including a plurality of words, and may extract, from among the words included in the target content, words included in the word list as target words.

[0085] [3.3.6. Information generation unit 35] The information generating unit 35 generates target word information including the target words extracted by the word extracting unit 34.

[0086] For example, the information generating unit 35 generates, as the target word information, list information including a target word list, which is a list of target words extracted by the word extracting unit 34. When there are multiple applicable categories, the list information is a target word list for each applicable category, but there may be one target word list for multiple applicable categories. Furthermore, the list information may include specific words, but may not include specific words.

[0087] For example, the information generating unit 35 generates, as the target word information, list information including a target word list in which the target words extracted by the word extracting unit 34 are arranged in descending order of similarity to the specific word. The information generating unit 35 can also generate, as the target word information, list information including a target word list in which the target words are arranged in descending order of the number of times they are included in the target content.

[0088] The information generation unit 35 converts words, such as words or phrases, included in multiple pieces of posted content into vectors, such as distributed representations, using a conversion model that converts words with similar meanings into similar vectors, such as W2V (Word2Vec).The information generation unit 35 then calculates the cosine similarity between the vector of the target word and the vector of the specific word as the similarity between the target word and the specific word.The information generation unit 35 can also identify the vector of the target word using, for example, a conversion table that associates words with vectors for each word.

[0089] In addition, the information generation unit 35 generates, as target word information, sentence information that is information on a sentence containing the target word extracted by the word extraction unit 34 and the specific word included in the target word information request received by the reception unit 31.

[0090] For example, the information generation unit 35 can generate sentence information containing the target word and the specific word as target word information by replacing some of the words other than the specific word among the multiple words contained in the relevant content with the target word.

[0091] In addition, the information generation unit 35 can also generate text information containing a target word and a specific word as target word information, for example, by replacing a first word contained in a predetermined template text with a specific word and replacing a second word contained in the template text with a target word.

[0092] The information generation unit 35 can also generate text information including the target word and the specific word as target word information using natural language processing technology. For example, the information generation unit 35 generates text information including the target word and the specific word as target word information using a natural language processing model that can generate text information from keywords as target word information. The natural language processing model is, for example, a model using the well-known BERT or GPT-3.

[0093] The information generation unit 35 can generate, for example, as target word information, sentence information including two or more target words and a specific word from among the target words extracted by the word extraction unit 34. The two or more target words are target words randomly selected from the target words extracted by the word extraction unit 34 or target words selected based on a predetermined rule.

[0094] The information generating unit 35 can also generate, as target word information, sentence information including one or more target words selected by the user UB from the target words extracted by the word extracting unit 34 and a specific word.

[0095] [3.3.7. Information Output Unit 36] The information output unit 36 ​​outputs information about the target words extracted by the word extraction unit 34. For example, the information output unit 36 ​​transmits information about the target words extracted by the word extraction unit 34 to the terminal device 3 that sent the target word information request accepted by the acceptance unit 31, via the communication unit 10 and the network N.

[0096] The information output unit 36 ​​transmits the target word information generated by the information generation unit 35 as information about the target word via the communication unit 10 and the network N to the terminal device 3 that sent the target word information request received by the reception unit 31.

[0097] For example, the information output unit 36 ​​can output list information including a target word list in which target words extracted by the word extraction unit 34 are arranged in order of their similarity to a specific word as information about the target word, or output list information including a target word list, which is a list in which target words are arranged in order of the number of times they are included in the target content, as information about the target word.

[0098] In addition, the information output unit 36 ​​can also output sentence information including the target word extracted by the word extraction unit 34 and the specific word included in the target word information request received by the reception unit 31 as information related to the target word.

[0099] 6 is a diagram showing an example of list information output by the information output unit 36 ​​of the information processing device 1 according to the embodiment as information related to a target word. The list information shown in Fig. 6 includes information on a list in which the target word is "lotion" and target words with cosine similarity of 0.5 or more are sorted by category in descending order of cosine similarity.

[0100] For example, the list information shown in Figure 6 shows a target word list in which the target words in the relevant category "skin care" are listed as "cleansing gel," "shower gel," "training," "barley tea," and "far infrared rays."

[0101] Also, a target word list is shown in which "upper arms," ​​"mold," "wellhead skin," "mask," and "thighs" are listed as target words in the corresponding category "acne care." Furthermore, the target word list in the corresponding category "makeup, cosmetics" does not include any target words, and it is shown that there are no target words with a cosine similarity of 0.5 or more.

[0102] In this way, the list information shows multiple target words that are highly similar to the specific word but do not appear in the posted content that includes the specific word, allowing the user UB to understand words in the posted content that are unexpected in relation to the specific word.

[0103] Furthermore, instead of the information in which the target words are arranged in order of similarity to the specific word as described above, the list information may be information in which the target words are arranged in order of the number of times they are included in posted content that does not include the specific word. Even in this case, the user UB can grasp words in the posted content that are unexpected in relation to the specific word.

[0104] 7 is a diagram showing an example of text information output by the information output unit 36 ​​of the information processing device 1 according to the embodiment as information related to a target word. The text information shown in FIG. 7 is text information in the case where the specific word is "lotion" and the target word is "far-infrared rays."

[0105] The text information shown in Figure 7 includes the title "A lotion that blocks far-infrared rays?" and the text "Lotions that block far-infrared rays are attracting attention. Far-infrared rays penetrate deep into the skin and destroy collagen and elastin. For this reason, lotions containing ingredients that absorb far-infrared rays are attracting attention."

[0106] In this way, since the document information includes information on sentences that contain specific words and target words, user UB can, for example, gain new insights into the relationship between specific words and target words, and can come up with new development ideas or article ideas, for example.

[0107] [4. Processing Procedure] Next, a procedure for information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Fig. 8 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment. The processing shown in Fig. 8 is processing performed when a target word information request from the terminal device 3 is accepted by the processing unit 12.

[0108] As shown in FIG. 8, when the processing unit 12 of the information processing device 1 receives a target word information request from the terminal device 3, it extracts the relevant content that is the specific word posted content identified by the received target word information request (step S20).

[0109] Next, the processing unit 12 extracts a category that includes the relevant content extracted in step S20 as a relevant category (step S21).Then, the processing unit 12 extracts posted content that does not include the specific word from among the multiple posted contents included in the relevant category extracted in step S21 as target content (step S22).

[0110] Next, the processing unit 12 extracts the words included in the target content extracted in step S22 as target words (step S23). Then, the processing unit 12 generates target word information, which is information related to the target words extracted in step S23 (step S24), outputs the generated target word information (step S25), and ends the processing shown in FIG.

[0111] [5. Modifications] In the above-described example, the information generation unit 35 outputs, as list information, either information including a list in which target words are arranged in order of their similarity to a specific word, or information including a list in which target words are arranged in order of the number of times they are included in the target content, but is not limited to such examples.

[0112] For example, the information generating unit 35 can generate, as list information, information including a target word list in which target words are arranged in descending order of the value obtained by weighting and adding the similarity to a specific word and the number of times the words are included in the target content.

[0113] The target word information request may also include user-specified information that specifies information about the user UA who posted the posted content. In this case, the category extraction unit 33 extracts at least one of the relevant content and the target content from the posted content posted by the user UA who has the information specified in the user-specified information. The user-specified information is information that specifies one or more pieces of information included in the attribute information and history information of the user UA, such as information that specifies the gender and age of the user UA.

[0114] In addition, the category extraction unit 33 can also extract at least one of the relevant content and the target content from the posted content posted by a user UA who has information that matches or is similar to the information of user UB whose user ID is included in the target word information request.

[0115] Furthermore, the information output unit 36 ​​can also output information on the target words corresponding to the information on the user UB of the user ID included in the target word information request, out of the information on the plurality of target words described above.

[0116] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by, for example, a computer 80 configured as shown in Fig. 9. Fig. 9 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, an HDD (Hard Disk Drive) 84, a communication interface (I / F) 85, an input / output interface (I / F) 86, and a media interface (I / F) 87.

[0117] The CPU 81 operates and controls each part based on programs stored in the ROM 83 or the HDD 84. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 starts up, programs that depend on the hardware of the computer 80, and the like.

[0118] The HDD 84 stores programs executed by the CPU 81, data used by such programs, etc. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.

[0119] The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 86. The CPU 81 acquires data from the input devices via the input / output interface 86. The CPU 81 also outputs generated data to the output devices via the input / output interface 86.

[0120] The media interface 87 reads a program or data stored in a recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program or data from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0121] For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 executes programs loaded onto the RAM 82 to realize the functions of the processing unit 12. In addition, the HDD 84 stores data in the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from a recording medium 88, but as another example, the CPU 81 may obtain these programs from another device via the network N.

[0122] [7. Other] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0123] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0124] For example, the information processing device 1 described above may be realized by a plurality of server computers, and depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API or network computing.

[0125] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0126] [8. Effects] As described above, the information processing device 1 according to the embodiment includes the category extraction unit 33, the word extraction unit 34, and the information output unit 36. The category extraction unit 33 extracts a category of posted content that includes a specific word. The word extraction unit 34 extracts, as target words, words included in posted content that does not include the specific word from among the posted content of the category extracted by the category extraction unit 33. The information output unit 36 ​​outputs information including the target word extracted by the word extraction unit 34. This allows the information processing device 1 to extract words that are unexpected in relation to a specific keyword.

[0127] Furthermore, the category extraction unit 33 extracts a predetermined number of categories from among categories of posted content containing the specific word in order of the number or ratio of posted content containing the specific word. This allows the information processing device 1 to appropriately extract words that are unexpected in relation to the specific keyword.

[0128] Furthermore, the information output unit 36 ​​outputs information including a list in which the target words extracted by the word extraction unit 34 are arranged in descending order of similarity to the specific word. This allows the information processing device 1 to appropriately extract unexpected words in relation to the specific keyword.

[0129] Furthermore, the information output unit 36 ​​outputs information including a list of target words arranged in descending order of frequency in posted content that does not include the specific word among posted content in the category extracted by the category extraction unit 33. This allows the information processing device 1 to appropriately extract unexpected words in relation to the specific keyword.

[0130] Furthermore, the information output unit 36 ​​outputs information about a sentence that includes the target word and the specific word extracted by the word extraction unit 34. This enables the information processing device 1 to provide a sentence that includes a word that is unexpected in relation to the specific keyword.

[0131] The posted content is a question posted to an online service that accepts questions and answers by category, which allows the information processing device 1 to appropriately extract unexpected words in relation to specific keywords from the question content.

[0132] Furthermore, the category extraction unit 33 excludes the specific category from the categories of posted content that includes the specific word, which allows the information processing device 1 to appropriately extract unexpected words in relation to the specific keyword.

[0133] The above describes the embodiments of the present application in detail based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have been modified and improved in various ways based on the knowledge of those skilled in the art.

[0134] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0135] 1. Information processing equipment 2,3 Terminal equipment 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Content storage unit 30 Acquisition Department 31 Reception 32 Providing Department 33 Category Extraction Unit 34 Word Extraction Unit 35 Information generation section 36 Information output section 100 Information Processing Systems

Claims

1. a category extraction unit that extracts categories of posted content that include specific words; a word extraction unit that extracts, as target words, words included in posted content that does not include the specific word from posted content in the category extracted by the category extraction unit; an information output unit that outputs information including the target words extracted by the word extraction unit; 1. An information processing device comprising:

2. The category extraction unit A predetermined number of categories are extracted from the categories of posted content containing the specific word in descending order of the number or ratio of posted content containing the specific word.

2. The information processing apparatus according to claim 1, wherein:

3. The information output unit Output information including a list in which the target words extracted by the word extraction unit are sorted in descending order of similarity to the specific word.

3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

4. The information output unit outputting information including a list of the target words in descending order of the number of times they are included in posted content that does not include the specific word among posted content in the category extracted by the category extraction unit; 3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

5. The information output unit Outputting information about sentences containing the target word and the specific word extracted by the word extraction unit 3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

6. The posted content is: The content is a question posted to an online service that accepts questions and answers by category.

3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

7. The category extraction unit A specific category of posted content that includes the specific word is excluded from the extraction target.

3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

8. 1. A computer-implemented information processing method, comprising: a category extraction step of extracting categories of posted content containing specific words; a word extraction step of extracting, as target words, words included in posted content that does not include the specific word from posted content in the category extracted by the category extraction step; an information output step of outputting information including the target words extracted by the word extraction step. An information processing method comprising:

9. A category extraction procedure for extracting categories of posted content containing specific words; a word extraction step of extracting, as target words, words included in posted content that does not include the specific word from posted content in the category extracted by the category extraction step; an information output step of outputting information including the target words extracted by the word extraction step, An information processing program characterized by:

Images