Information processing apparatus, information processing method, and information processing program

Abstract

To provide an information processing apparatus, an information processing method, and an information processing program configured to improve convenience for users.SOLUTION: An information processing apparatus includes: a generation unit which generates a question based on a search query used for retrieving web content; a receiving unit which receives an answer to the question generated by the generation unit; and a providing unit which provides information including the question generated by the generation unit and the answer received by the receiving 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] In recent years, information sharing services between users via networks such as the Internet have become popular. In this type of service, for example, a user (questioner) posts a question, and other users (answerers) post answers, thereby sharing knowledge and wisdom among users (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-125146 Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the conventional technology, it may be difficult for users to obtain the information they desire, for example, in areas where there are few questions, and there is room for improvement in terms of improving user convenience.

[0005] The present application has been made in view of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can improve user convenience. [Means for solving the problem]

[0006] The information processing device of the present application includes a generation unit that generates a question based on a search query used to search web content, a reception unit that receives an answer from a user to the question generated by the generation unit, and a provision unit that provides information including the question generated by the generation unit and the answer received by the reception unit. [Effects of the Invention]

[0007] According to one aspect of the embodiment, an effect is achieved in that it is possible to improve convenience for users. [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 the user information storage unit of the information processing device according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a question history table stored in the question history information storage unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of an answer history table stored in the answer history information storage unit of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram showing an example of question generation information that is provided by a providing processing unit of a providing unit in the processing unit of the information processing device according to the embodiment, transmitted to a terminal, and displayed on the terminal device. [Figure 8] FIG. 8 is a diagram showing an example of answer input information that is provided by a providing processing unit of a providing unit in a processing unit of the information processing device according to the embodiment, transmitted to the terminal, and displayed on the terminal device. [Figure 9] FIG. 9 is a flowchart showing an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 10] FIG. 10 is a hardware configuration diagram showing 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. Fig. 1 shows an example of operation of an information processing system 100 including an information processing device 1 according to the embodiment.

[0011] As shown in Fig. 1, an information processing system 100 according to the embodiment includes an information processing device 1 and a plurality of terminal devices 2. Each terminal device 2 is a terminal device of a user U to which various contents are provided from the information processing device 1. The various contents transmitted from the information processing device 1 include search results for web content in a web search service and content for a Q&A (question and answer) service. The following description will focus on the web search service and the Q&A service as services provided by the information processing device 1.

[0012] For example, an application program for using the Q&A service (hereinafter, sometimes referred to as a Q&A app) is installed on the terminal device 2, and a user U of the terminal device 2 can use the Q&A service by launching the Q&A app.

[0013] The Q&A app can transmit and receive information related to the Q&A service to and from the information processing device 1 via an interface such as an API (Application Programming Interface). For example, the Q&A app can transmit information input to the terminal device 2 to the information processing device 1 and receive information from the information processing device 1.

[0014] 1, the information processing device 1 collects information on search queries used to search for web content in a web search service (step S1). For example, the information processing device 1 collects the information on search queries from an internal storage unit or a search server.

[0015] The search query information includes the search query, information about the user U who sent the search query, information indicating the date and time of the search query, etc. The search query includes words and phrases entered by the user U. The information about the user U includes information indicating the attributes of the user U.

[0016] Next, the information processing device 1 selects one or more pieces of search query information from the pieces of search query information collected in step S1 (step S2). For example, the information processing device 1 classifies the pieces of search query information into categories (step S2-1). The categories in the Q&A service are classified into a combination of major categories, medium categories, and minor categories.

[0017] The major categories include, but are not limited to, the categories "Region, Travel, Outings," "Entertainment and Hobbies," "Health, Beauty and Fashion," "Childcare and School," "Business, Economy and Money," "Occupations and Careers," and "Computer Technology."

[0018] If the major category is "region, travel, outings," the intermediate categories are categories such as "domestic," "overseas," and "transportation, maps." If the major category is "entertainment and hobbies," the intermediate categories are categories such as "celebrities," "television, radio," "music," "movies," "theatre, musicals," "anime, comics," "games," and "books, magazines," but are not limited to these examples.

[0019] If the major category is "region, travel, outings" and the medium category is "domestic," the minor categories include, but are not limited to, the category "tourist spots, recreational areas," the category "zoos, aquariums," the category "hotels, inns," the category "hot springs," the category "events, festivals," and the category "gourmet outings." If the major category is "entertainment and hobbies" and the medium category is "movies," the minor categories include the category "Japanese movies" and the category "foreign movies."

[0020] In step S2-1, the information processing device 1 classifies a plurality of search queries into categories, for example, by rule-based classification or classification using a machine learning model. For example, the information processing device 1 has a keyword list in which a plurality of keywords are associated with each category, and can classify the category that includes the largest number of keywords in the keyword list among the words included in the search query as the category of the search query.

[0021] The information processing device 1 can also classify multiple search queries into categories using a classification model trained using multiple pieces of training data (pairs of search queries and categories). The classification model is generated, for example, by converting each search query in the training data into a feature and learning using the feature.

[0022] Examples of feature quantities include, but are not limited to, TF-IDF (Term Frequency-Inverse Document Frequency), Bow (Bag of Words), etc. Examples of classification models include, but are not limited to, regression models, support vector machines, gradient boosting decision trees, convolutional neural networks, etc.

[0023] The information processing device 1 extracts information about one or more search queries for each category based on information about a plurality of search queries classified by category (step S2-2). For example, the information processing device 1 extracts one or more search queries that satisfy a predetermined first condition for each category.

[0024] The first condition is, for example, a condition that the search query contains one or more trending words in the top m places (m is an integer greater than or equal to 1), or a condition that the search query is from a user U whose frequency of posting questions on the Q&A service is greater than or equal to a threshold, but is not limited to such examples.

[0025] A trending word is a word that is increasingly appearing in search queries. For example, a trending word is a word that is included in a plurality of search queries during a predetermined period and whose occurrence frequency per unit time is increasing at a rate equal to or greater than a threshold, and whose most recent occurrence frequency is equal to or greater than the threshold.

[0026] The information processing device 1 selects information on a search query that satisfies a predetermined second condition from among the one or more search queries for each category extracted in step S2-3 (step S2-3). The second condition is, but is not limited to, a condition that the search query contains a combination of multiple terms that were not included in questions posted within a predetermined period of time, or a condition that the search query contains a combination of multiple terms that were included in questions posted within a predetermined period of time but were posted infrequently.

[0027] At least one of the first and second conditions may be different for each category. For example, if the search query is in a category whose major classification is "area, travel, outing," the second condition may be a condition that the search query contains information indicating a location, a condition that the search query contains information indicating a location and information indicating a purpose at that location, or a condition that the combination of the above-mentioned multiple terms is a combination of information indicating a location and information indicating a purpose at that location.

[0028] The information processing device 1 can also perform the process of step S2-2 and the process of step S2-3 together. In addition, in step S2-3, the information processing device 1 can also select information on a search query that is randomly selected from one or more search queries for each category extracted in step S2-2.

[0029] In addition, the information processing device 1 can also randomly select one or more pieces of search query information for each category in the processing of step S2-2, without performing the processing of step S2-3, based on the information of multiple search queries classified by category.

[0030] Next, the information processing device 1 generates a question based on information of one or more search queries for each category selected in step S2 (step S3). For example, the information processing device 1 generates a question for each category that includes multiple terms included in the search queries.

[0031] The questions generated by the information processing device 1 are generated by a generation method selected by the operator of the information processing device 1 from, for example, a rule-based generation method or a generation method using generation AI (Artificial Intelligence).

[0032] Rule-based question generation is performed, for example, by extracting multiple types of terms corresponding to a category from a search query using a category term list containing a list of multiple types of terms for each category, and then applying the extracted multiple types of terms to template sentences for each category.

[0033] For example, if the category of the search query is a category that includes the major classification items "region, travel, outings," the category term list includes a list of terms that indicate locations and a list of terms that indicate purposes. The information processing device 1 uses the category term list to extract terms that indicate locations and terms that indicate purposes at those locations from the search query. The search query that extracts terms that indicate locations and the search query that includes terms that indicate purposes may be the same search query or may be different search queries.

[0034] Then, the information processing device 1 generates a question by applying terms indicating a location extracted from the search query and terms indicating the purpose at that location to specific parts of a sentence in a template for a category that includes the major classification items "region, travel, outings."

[0035] For example, a template may be, but is not limited to, the following string: "I'd like to do {target term} in {region term}. Any recommendations?" The {region term} is filled in with a term indicating a location extracted from the search query, and the {target term} is filled in with a term indicating a purpose extracted from the search query.

[0036] {Regional terms} are terms that indicate the names of regions such as Kyoto, Awaji Island, and Kanazawa, and {destination terms} are terms that indicate purposes such as travel, sightseeing, eating and drinking, and accommodation, but are not limited to these examples.

[0037] The templates may differ depending on the combination of the major classification and the medium classification, or may differ depending on the combination of the major classification, the medium classification, and the small classification.

[0038] Furthermore, the search query information includes the search query and information about the user U of the terminal device 2 that sent the search query. The information processing device 1 can generate a question using the information about the user U in addition to the search query.

[0039] The information about user U includes, for example, information indicating the attributes of user U. The attributes of user U are demographic attributes such as gender, generation (age), address, family structure, occupation, and annual income, but may also be psychographic attributes such as user U's interests, lifestyle, thoughts, and ideological tendencies, or may be a combination of demographic attributes and psychographic attributes.

[0040] For example, the information processing device 1 can generate a question using a template including information such as the string "I want to search for {target term} in {regional term}. Do you have any recommendations?\n\nParticipant: {family structure}." {Family structure} is assigned a family structure based on information indicating the attributes of the search query. For example, the information may be the string "1 man in his 40s, 1 woman in her 40s, 1 male junior high school student." In this way, the information processing device 1 can generate a question based on the search query and information indicating the attributes of the user U of the terminal device 2 that sent the search query.

[0041] Question generation using a generation AI involves using a generation AI that can generate text, and inputting information including the search query information selected in step S2 into the generation AI as input information, causing the generation AI to output a question.

[0042] The generation AI is, for example, a text generation AI. The text generation AI is, for example, a large-scale language model trained to estimate and output the next token from an input token sequence, such as a transformer-based model or an RNN (recurrent neural network)-based model, but may also be a hybrid model of these. The text generation AI may also be a composite system combined with an identifier to prevent fraudulent use.

[0043] Examples of the transformer-based model include, but are not limited to, GPT (Generative Pre-trained Transformer) (registered trademark), PaLM2 (Pathways Language Model Version 2), and LLaMA (Large Language Model Meta AI). Examples of the RNN-based model include, but are not limited to, RWKV (Receptance Weighted Key Value).

[0044] It is desirable that the generation AI be trained so as not to include personal information in the generated results. The generation AI is placed in an external information processing device, and the information processing device 1 uses the generation AI via an API, but the generation AI may also be placed within the information processing device 1.

[0045] The information processing device 1 inputs information including search query information and instruction information that instructs the generation of a question using the search query information to the generation AI, and can cause the generation AI to generate a question according to the search query information.

[0046] The instruction information may be, for example, a string of characters such as "You are a person with high-level questioning skills. Please create a question that many people will find useful based on the given keywords." However, the instruction information is not limited to such an example.

[0047] The instruction information may also include constraints. Constraints include, for example, an upper limit on the number of characters, a format of expression, and limitations on the type of each item to be included in the output content, and are set, for example, for each category. The format of expression may be, for example, a formal formal expression, or a polite formal expression. Items to be included in the output content include, for example, "participants" and "season" for a question about tourism, and "participants," "purpose of use," "planned drinking," and "budget" for a question about food, but are not limited to these examples. "Participants" includes, for example, age, gender, and number of people.

[0048] The generative AI may be a multimodal generative AI, etc. The multimodal generative AI is, for example, a generative AI that can generate text and images from text and images, etc. Examples of the multimodal generative AI include, but are not limited to, GPT-4 Turbo with vision, Gemini, and CM3Leon (Chameleon Multimodal Model).

[0049] Furthermore, in the case of categories related to sightseeing or gourmet food, the information processing device 1 may include, in the instruction information, information indicating an instruction to include information indicating the attributes of all family members, including the user U who sent the search query, as "participants" in the question, in the information indicating the constraints. Furthermore, the instruction information may include, in the information indicating the constraints, information indicating an instruction to include "participants" in the question as virtual personas to increase realism. In this way, the information processing device 1 can generate a question based on the search query and the attributes of the user U of the terminal device 2 who sent the search query.

[0050] If the search query information does not include information indicating the attributes of a family member including the user U of the terminal device 2 that sent the search query, the information processing device 1 can also estimate the attributes of a family member including the user U of the terminal device 2 that sent the search query.

[0051] For example, the information processing device 1 has a keyword list that is a list of keywords for each attribute (gender, generation (age), family composition, etc.), and estimates the attributes of user U based on the attribute in the keyword list that is included most frequently among the multiple words included in user U's multiple search queries.

[0052] The information processing device 1 can also estimate the attributes of the user U using an attribute estimation model. The attribute estimation model is generated by machine learning using a dataset of multiple words included in multiple search queries sent by the same user U from the terminal device 2 and the attributes of that user U. The attribute estimation model is, for example, a regression model, a GBDT (Gradient Boosting Decision Tree), a neural network, or the like, but is not limited to these examples.

[0053] The attribute estimation model is, for example, a model that uses the number of occurrences of words included in a search query as a feature, and the information processing device 1 inputs the number of occurrences of multiple words included in multiple search queries sent from the terminal device 2 of the user U to be estimated into the attribute estimation model, and estimates the attribute with the highest score for each attribute output from the attribute estimation model as the attribute of user U.

[0054] The information processing device 1 can also use, for example, a generation AI to estimate the attributes of the user U. For example, the information processing device 1 inputs to the generation AI a plurality of search queries transmitted from the terminal device 2 of the user U to be estimated and instruction information including information indicating an instruction to estimate the attributes of the user U from the plurality of search queries, thereby causing the generation AI to estimate the attributes of the user U.

[0055] Furthermore, when the search query does not include information indicating a purpose, the information processing device 1 can instruct the generation AI to estimate a purpose at a location whose information is included in the search query. Furthermore, the information processing device 1 can have, for example, a purpose list in which purposes are listed for each location, and can estimate a purpose at a location whose information is included in the search query from the purpose list.

[0056] The instruction information may also include information indicating search query information and example questions based on the search query information. For example, the instruction information may include a string such as "# Example\n\n# Search query example\n Yokosuka sightseeing\n# Question example\nPlease tell me some tourist spots in Yokosuka that are fun for families.\n\n·Participants: Family of 3 (1 man in his 30s, 1 woman in her 30s, 1 teenage woman)\n·Time: Summer vacation (July to August)\n\nWe are particularly interested in interactive attractions that children can enjoy and educational tourist spots. We would also like to know about delicious local gourmet spots. Thank you in advance."

[0057] The instruction information may also include, for example, other questions that satisfy a predetermined condition as example questions. Examples of other questions that satisfy the predetermined condition include, but are not limited to, other questions with a threshold or more of answers, other questions for which the time period from the question until the predetermined number of answers is received is within a threshold, other questions with the top m number of answers, and other questions with the top n number of answers for which the time period from the question until the predetermined number of answers is received is shortest.

[0058] Furthermore, the information processing device 1 generates questions to which answers from the candidate answerers are accepted, based on the behavioral history of the users U who are candidate answerers. The candidate answerers are, for example, users U whose frequency of answering questions is equal to or greater than a threshold, and are selected for each category, but are not limited to this example. For example, the candidate answerers may be users U whose frequency of being selected as the best answer is equal to or greater than a threshold, or users U whose frequency of answering questions is equal to or greater than a threshold and whose frequency of being selected as the best answer is equal to or greater than a threshold.

[0059] The behavioral history of user U, who is a candidate answerer, is, for example, a history of behavior including keywords included in the search query, such as a history of behavior including locations indicated by keywords included in the search query and the purpose of those locations. The behavioral history of user U can also be rephrased as a history of user U's experiences.

[0060] The information processing device 1 generates questions that are easy for the answer candidate to answer based on the behavioral history of the user U who is the answer candidate. The behavioral history of the user U includes a history of answers given by the answer candidate in the past, and the information processing device 1 generates questions that are easy for the answer candidate to answer based on, for example, questions corresponding to answers given by the answer candidate in the past.

[0061] For example, the information processing device 1 sets as instruction information information further including the information of the string "Answerers who answer questions should create questions taking into consideration how easy it will be to answer the given example questions.", and inputs as input information to the generation AI information including such instruction information and a question corresponding to an answer given in the past by the answer candidate.

[0062] Next, the information processing device 1 provides information including the question generated in step S3 (step S4). For example, the information processing device 1 provides the information including the question generated in step S3 to the answer candidate by transmitting the information including the question generated in step S3 to the terminal device 2 of the answer candidate. The information processing device 1 provides the question generated in step S3 to the user U, for example, via a Q&A service.

[0063] The terminal device 2 displays the question generated in step S3 that is provided by the information processing device 1. For example, the terminal device 2 displays the question generated in step S3 by displaying the screen shown in FIG. 1(a).

[0064] When the user U operates the answer button on the screen shown in Fig. 1(a), the terminal device 2 displays a screen for inputting an answer, and the user U inputs an answer to the question generated in step S3, as shown in Fig. 1(b). Thereafter, the user U can post an answer to the question generated in step S3 by selecting the post button shown in Fig. 1(b).

[0065] Next, the information processing device 1 accepts a posted answer to the question generated in step S3 (step S5). For example, the information processing device 1 accepts information in which an answer candidate answers the question generated in step S3 and which is transmitted from the terminal device 2 of the answer candidate as a posted answer to the question generated in step S3.

[0066] In addition, the information processing device 1 can also accept information in which a person other than the answer candidate answers the question generated in step S3 and which is sent from a terminal device 2 other than the answer candidate as a posted answer to the question generated in step S3.

[0067] In the Q&A service, the information processing device 1 provides the user U with information including the question generated in step S3 and the answer received in step S5 (step S6). For example, the information processing device 1 provides the user U with information including the question generated in step S3, which includes the search word specified by the user U, and the answer to the question received in step S5.

[0068] Furthermore, the information processing device 1 can also provide the user U with information including the question generated in step S3 and the answer to the question received in step S5 on a web page for each category in the Q&A service.

[0069] The information processing device 1 also receives a search query for information in a web search service (step S7). The information processing device 1 receives the search query transmitted from the terminal device 2 in response to an operation of the terminal device 2 by the user U, for example.

[0070] Based on the answer received in step S5, the information processing device 1 performs a search process according to the search query received in step S7 (step S8). For example, if the search query received in step S7 is the same as the search query used to generate the question in step S3, the information processing device 1 performs a search process based on the answer received in step S5.

[0071] For example, the information processing device 1 performs search processing using a ranking model that increases the weight of features corresponding to keywords included in the answer received in step S5, so that the display ranking of web content related to the answer received in step S5 is increased in search results. The ranking model is a neural network-based model, but may also be a model using logistic regression, a decision tree, or the like.

[0072] For example, in response to a question generated from search query #1, if there are many posts containing information such as the string "I recommend Cafe XXX," and if the search query received in step S6 is search query #1, the information processing device 1 performs search processing so that web content related to "Cafe XXX" is displayed higher in the search results. Search query #1 includes, for example, the string "Please tell me about a recommended cafe in Nishi-ku, Fukuoka City," but is not limited to this example.

[0073] For example, by using a ranking model in which the weight of the feature amount corresponding to "cafe XXX" is increased, the information processing device 1 can perform search processing so that the display ranking of web content related to "cafe XXX" in the search results is higher.

[0074] The information processing device 1 transmits search results indicating the results of the search processing performed in step S8 to the terminal device 2 that transmitted the search query (step S9). This allows the information processing device 1 to provide the user U with the results of the search processing corresponding to the search query received in step S7 based on the response received in step S5.

[0075] In this way, the information processing device 1 generates a question based on a search query used to search for web content, receives an answer to the question from the user U, and provides information including the generated question and the received answer. In this way, the information processing device 1 can improve convenience for the user U.

[0076] The configuration of an information processing system 100 including an information processing device 1 that performs such processing and a plurality of terminal devices 2 will be described in detail below.

[0077] 2. Configuration of Information Processing System 100 2 is a diagram showing an example of the configuration of an information processing system 100 according to the embodiment. As shown in FIG. 2, the information processing system 100 according to the embodiment includes an information processing device 1 and a plurality of terminal devices 2.

[0078] The multiple terminal devices 2 are used by different users U. Each terminal device 2 is, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, a tablet PC, or a wearable device. Examples of wearable devices include, but are not limited to, smart glasses or a smart watch.

[0079] The information processing device 1 and the terminal device 2 are connected to each other so as to be able to communicate with each other by wire or wirelessly via a network N. Note that the information processing system 100 shown in Fig. 2 may include a plurality of information processing devices 1 and the like.

[0080] The network N includes, for example, a WAN (Wide Area Network) such as the Internet and a mobile communication network such as LTE (Long Term Evolution), 4G (4th Generation), and 5G (5th Generation: 5th generation mobile communication system).

[0081] Each terminal device 2 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or wireless LAN (Local Area Network), and communicate with the information processing device 1.

[0082] 3. Configuration of Information Processing Device 1 3 is a diagram showing an example of the configuration of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

[0083] [3.1. Communication Unit 10] The communication unit 10 is realized by, for example, a communication module or 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 the terminal device 2 via the network N.

[0084] [3.2. Storage section 11] The storage unit 11 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 11 has a user information storage unit 20, a question history information storage unit 21, an answer history information storage unit 22, and a web content information storage unit 23.

[0085] 3.2.1. User Information Storage Unit 20 The user information storage unit 20 stores various types of information related to the user U. Fig. 4 is a diagram showing an example of a user information table stored in the user information storage unit 20 of the information processing device 1 according to the embodiment.

[0086] 4, the user information table stored in the user information storage unit 20 includes information items such as "user ID (identifier)," "attribute information," and "history information." The "user ID" is an identifier that identifies a user U, and is information assigned to each user U.

[0087] "Attribute information" is attribute information indicating the attributes of user U associated with "user ID." The attributes of user U are, for example, demographic attributes, psychographic attributes, etc. Demographic attributes are demographic attributes, and include multiple attribute items such as generation (age), gender, occupation, place of residence, annual income, and family structure.

[0088] Psychographic attributes are psychological attributes and include, for example, multiple attribute items related to lifestyle, values, interests, etc. For example, each of the multiple attribute items in the psychographic attributes is an object of interest to the user U, such as travel, fashion, science, books, art, technology, music, sports, music, movies, etc.

[0089] The "history information" includes information on the behavior history of the user U associated with the "user ID." The behavior history of the user U includes, for example, search history information, browsing history information, and transaction history information.

[0090] The search history information of the user U includes, for example, information on the search history of the user U in a web search service. The browsing history information of the user U includes, for example, information on the browsing history of content by the user U in an online service. The transaction history information includes, for example, information on the transaction history of goods by the user U in an online service.

[0091] 3.2.2. Question History Information Storage Unit 21 The question history information storage unit 21 stores various types of information related to questions. Fig. 5 is a diagram showing an example of a question history table stored in the question history information storage unit 21 of the information processing device 1 according to the embodiment.

[0092] 5, the question history table stored in the question history information storage unit 21 includes information items such as "Question ID," "Questioner ID," "Question," and "Date and Time." The "Question ID" is an identifier that identifies a question, and is information assigned to each question.

[0093] The "questioner ID" is the user ID of user U when the question associated with the "question ID" is posted by that user U as the questioner, and is the ID of the generating AI when the question associated with the "question ID" is generated by a generating AI. In the example shown in Figure 5, the ID of the generating AI is "GAI", but is not limited to this example.

[0094] "Question" is a question associated with "Question ID" and is a question text expressed as a string, but may also include an image. "Date and time" is information on the date and time the question associated with "Question ID" was asked.

[0095] 3.2.3. Answer History Information Storage Unit 22 The answer history information storage unit 22 stores various information related to answers to questions by the user U. Fig. 6 is a diagram showing an example of an answer history table stored in the answer history information storage unit 22 of the information processing device 1 according to the embodiment.

[0096] 6, the answer history table stored in the answer history information storage unit 22 includes information on items such as "answer ID," "question ID," "answerer ID," "answer," and "date and time." The "answer ID" is an identifier that identifies an answer, and is information assigned to each answer.

[0097] The "Question ID" is the question ID of the question to which the answer associated with the "Answer ID" is directed. The "Answer ID" is the user ID of the user U who posted the answer to the question associated with the "Question ID."

[0098] "Answer" is an answer associated with "Answer ID" and is an answer text expressed as a string, but may also include an image. "Date and time" is information on the date and time when the answer associated with "Answer ID" was made.

[0099] 3.2.4. Web Content Information Storage Unit 23 Various types of information related to each web content are stored in web content information storage unit 23. The information related to the web content stored in web content information storage unit 23 is information used in search processing, such as, but not limited to, the title, URL (Uniform Resource Locator), main text, and metadata of the web content.

[0100] [3.3. Processing Unit 12] The processing unit 12 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing device 1 using RAM as a working area.

[0101] The processing unit 12 may be partially or entirely realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0102] 3, the processing unit 12 has an acquisition unit 30, a reception unit 31, a selection unit 32, a generation unit 33, and a provision unit 34, 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 be any other configuration that performs the information processing described below.

[0103] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various pieces of information from an external information processing device or the terminal device 2 via the communication unit 10, and stores the acquired information in the storage unit 11.

[0104] For example, the acquisition unit 30 acquires user information, which is information about the user U, from an external information processing device or terminal device 2 via the communication unit 10, and adds the acquired user information to the user information table in the user information storage unit 20.

[0105] The acquisition unit 30 also acquires various types of information from the storage unit 11. For example, the acquisition unit 30 acquires user information, which is information about the user U, from the user information storage unit 20 or the like. The acquisition unit 30 also acquires question history information from the question history information storage unit 21 or the like, and acquires answer history information from the answer history information storage unit 22 or the like.

[0106] The acquisition unit 30 also functions as a collection unit that collects information on search queries used in searching for web content. For example, the acquisition unit 30 collects the information on search queries from the storage unit 11, a search server, or the like. The search queries are transmitted from the terminal device 2 to the information processing device 1, a search server, or the like, by a user U of the terminal device 2 operating the terminal device 2.

[0107] The search query information includes the search query, information about the user U who sent the search query, information indicating the date and time of the search query, etc. The search query includes words and phrases entered by the user U. The information about the user U includes information indicating the attributes of the user U.

[0108] [3.3.2. Reception Unit 31] The reception unit 31 receives various requests and information from the terminal device 2 via the communication unit 10.

[0109] For example, the reception unit 31 receives a question posted by the user U. For example, when the reception unit 31 receives question information transmitted from the terminal device 2, the reception unit 31 receives the question posted by the user U based on the received question information.

[0110] The reception unit 31 also receives answers posted to questions by users U. For example, when the reception unit 31 receives answer information transmitted from the terminal device 2, the reception unit 31 receives answers posted to questions by other users U based on the received answer information.

[0111] The reception unit 31 also receives an answer from the user U to the question generated by the generation unit 33. For example, when the reception unit 31 receives answer information transmitted from the terminal device 2, the reception unit 31 receives a post of an answer from the user U to the question generated by the generation unit 33 based on the received answer information.

[0112] For example, the receiving unit 31 receives information in which an answer candidate answers a question generated by the generation unit 33 and which is sent from the answer candidate's terminal device 2 as a post of an answer to the question generated by the generation unit 33.

[0113] The answer candidate is, for example, a user U whose frequency of answering questions is equal to or greater than a threshold, and is selected for each category, but is not limited to this example. For example, the answer candidate may be a user U whose rate of being selected as the best answer is equal to or greater than a threshold, or may be a user U whose frequency of answering questions is equal to or greater than a threshold and whose rate of being selected as the best answer is equal to or greater than a threshold.

[0114] In addition, the receiving unit 31 can also receive information in which a person other than an answer candidate answers a question generated by the generating unit 33 and which is sent from a terminal device 2 other than the answer candidate as a posted answer to the question generated by the generating unit 33.

[0115] The receiving unit 31 also receives a search query for a web content search service, which is transmitted from the terminal device 2 of the user U. Such a search query is a search query for searching for web content.

[0116] 3.3.3. Selection unit 32 The selection unit 32 performs various selections. For example, the selection unit 32 selects one or more pieces of search query information from the plurality of pieces of search query information collected by the acquisition unit 30.

[0117] For example, the selection unit 32 categorizes, by category, information on a plurality of search queries collected by the acquisition unit 30. As described above, categories in the Q&A service are classified into a combination of major categories, medium categories, and minor categories, but are not limited to such an example.

[0118] For example, the selection unit 32 classifies a plurality of search queries into categories by rule-based classification or classification using a machine learning model. The selection unit 32 has, for example, a keyword list in which a plurality of keywords are associated with each category, and can classify the category that includes the largest number of keywords in the keyword list among the words included in the search query as the category of the search query.

[0119] The selection unit 32 can also classify multiple search queries into categories using a classification model trained using multiple pieces of training data (pairs of search queries and categories). The classification model is generated, for example, by converting each search query in the training data into a feature and learning using the feature.

[0120] Examples of the feature include, but are not limited to, TF-IDF, Bow, etc. Examples of the classification model include, but are not limited to, a regression model, a support vector machine, a gradient boosting decision tree, a convolutional neural network, etc.

[0121] The selection unit 32 extracts information about one or more search queries for each category based on information about a plurality of search queries categorized as described above. For example, the selection unit 32 extracts, for each category, one or more search queries that satisfy a predetermined first condition.

[0122] The first condition is, for example, a condition that the search query contains one or more trending words in the top m places (m is an integer greater than or equal to 1), or a condition that the search query is from a user U whose frequency of posting questions on the Q&A service is greater than or equal to a threshold, but is not limited to such examples.

[0123] A trending word is a word that is increasingly appearing in search queries. For example, a trending word is a word that is included in a plurality of search queries during a predetermined period and whose occurrence frequency per unit time is increasing at a rate equal to or greater than a threshold, and whose most recent occurrence frequency is equal to or greater than the threshold.

[0124] As described above, the selection unit 32 selects information on a search query that satisfies a predetermined second condition from among one or more search queries extracted for each category. The second condition is, but is not limited to, a condition that the search query contains a combination of multiple terms that were not included in questions posted within a predetermined period of time, or a condition that the search query contains a combination of multiple terms that were included in questions posted within a predetermined period of time but were posted infrequently.

[0125] At least one of the first and second conditions may be different for each category. For example, if the search query is in a category whose major classification is "area, travel, outing," the second condition may be a condition that the search query contains information indicating a location, a condition that the search query contains information indicating a location and information indicating a purpose at that location, or a condition that the combination of the above-mentioned multiple terms is a combination of information indicating a location and information indicating a purpose at that location.

[0126] The selection unit 32 can also select information on a search query that is randomly selected from one or more search queries for each category extracted as described above. The selection unit 32 can also randomly select information on one or more search queries for each category based on information on a plurality of search queries classified by category.

[0127] [3.3.4. Generation unit 33] The generation unit 33 generates various types of information. The generation unit 33 generates a question based on a search query used to search for web content in a web search service. For example, the generation unit 33 generates a question based on the search query using a generation AI.

[0128] For example, the generation unit 33 generates a question based on information on one or more search queries for each category selected by the selection unit 32. For example, the generation unit 33 generates a question for each category that includes multiple terms included in the search queries selected by the selection unit 32.

[0129] Furthermore, the generation unit 33 generates a question based on the search query selected by the selection unit 32 and the attributes of the user U of the terminal device 2 that sent the search query. The information indicating the attributes of the user U used by the generation unit 33 is information acquired by the acquisition unit 30 or information estimated by the generation unit 33.

[0130] Furthermore, the generation unit 33 can generate questions to which answers from answer candidates are accepted, based on the behavioral history of the answer candidates. An answer candidate is, for example, a user U whose frequency of answering questions per unit time is equal to or greater than a threshold, but is not limited to this example. For example, an answer candidate is a user U whose average value of the questioner's evaluation of the answer is equal to or greater than a threshold, or a user U whose frequency of answering questions per unit time is equal to or greater than a threshold and whose average value of the questioner's evaluation of the answer is equal to or greater than a threshold.

[0131] The generation unit 33 includes an estimation processing unit 40 that performs various estimations and a generation processing unit 41 that generates a question based on the search query. The estimation processing unit 40 estimates, for example, the attributes of the user U of the terminal device 2 that sent the search query selected by the selection unit 32.

[0132] 3.3.4.1. Estimation Processing Unit 40 If the information on the search query selected by the selection unit 32 does not include information indicating the attributes of a family including the user U of the terminal device 2 that sent the search query, the estimation processing unit 40 estimates the attributes of a family including the user U of the terminal device 2 that sent the search query selected by the selection unit 32.

[0133] For example, the estimation processing unit 40 has a keyword list, which is a list of keywords for each attribute (gender, generation (age), family composition, etc.), and estimates the attribute of user U based on the attribute in the keyword list that is included most frequently among the multiple words included in user U's multiple search queries.

[0134] The estimation processing unit 40 can also estimate the attributes of the user U using an attribute estimation model. The attribute estimation model is generated by machine learning using a dataset of multiple words included in multiple search queries sent from the terminal device 2 by the same user U and the attributes of that user U. The attribute estimation model is, for example, a regression model, GBDT, neural network, etc., but is not limited to these examples.

[0135] The attribute estimation model is, for example, a model that uses the number of occurrences of words included in a search query as a feature, and the estimation processing unit 40 inputs the number of occurrences of multiple words included in multiple search queries sent from the terminal device 2 of the user U to be estimated into the attribute estimation model, and estimates the attribute with the highest score for each attribute output from the attribute estimation model as the attribute of user U.

[0136] The estimation processing unit 40 can also use, for example, a generation AI to estimate the attributes of the user U. For example, the estimation processing unit 40 causes the generation AI to estimate the attributes of the user U by inputting, to the generation AI, a plurality of search queries transmitted from the terminal device 2 of the user U to be estimated and instruction information including information indicating an instruction to estimate the attributes of the user U from these plurality of search queries.

[0137] In addition, if the search query selected by the selection unit 32 does not include information indicating the purpose, the estimation processing unit 40 estimates the purpose at a location where information is included in the search query selected by the selection unit 32.

[0138] For example, the estimation processing unit 40 instructs the generation AI to estimate a purpose at a location whose information is included in the search query selected by the selection unit 32. The estimation processing unit 40 inputs, as input information, instruction information including, for example, the information of a character string "Please estimate a purpose at a location indicated by a given search query," and information including information in the search query, to the generation AI, and causes the generation AI to output information indicating a purpose at a location whose information is included in the search query.

[0139] The search query information included in the input information input to the generation AI is a search query, but may also include one or more of the following information: information indicating the attributes of the user U of the terminal device 2 that sent the search query; information indicating the location of the terminal device 2 that sent the search query; and information indicating the time the search query was sent.

[0140] Furthermore, the estimation processing unit 40 may have a destination list that lists destinations for each location, and may estimate the destination at a location whose information is included in the search query from the destination list. The destination list may be information that lists the destination for each combination of a location and an attribute of the user U, or may be information that lists the destination for each combination of a location, an attribute of the user U, and a search time period.

[0141] [3.3.4.2. Generation Processing Unit 41] The generation processing unit 41 generates a question based on the search query. For example, the generation processing unit 41 generates a question based on the search query selected by the selection unit 32.

[0142] The question generated by the generation processing unit 41 is generated by a generation method selected by the operator of the information processing device 1 from, for example, a rule-based generation method or a generation method using a generation AI.

[0143] Rule-based question generation is performed, for example, by extracting multiple types of terms corresponding to a category from a search query using a category term list containing a list of multiple types of terms for each category, and then applying the extracted multiple types of terms to template sentences for each category.

[0144] For example, if the category of the search query is a category that includes the major classification items "region, travel, outings," the category term list includes a list of terms indicating locations and a list of terms indicating purposes. The generation processing unit 41 uses the category term list to extract terms indicating locations and terms indicating purposes at those locations from the search query. The search query that extracts terms indicating locations and the search query that includes terms indicating purposes may be the same search query or may be different search queries.

[0145] Then, the generation processing unit 41 generates a question by applying the terms indicating the location extracted from the search query and the terms indicating the purpose at that location to specific parts of the sentences in the template for the category that includes the major classification items "region, travel, outings."

[0146] For example, a template may be, but is not limited to, the following string: "I'd like to do {target term} in {region term}. Any recommendations?" The {region term} is filled in with a term indicating a location extracted from the search query, and the {target term} is filled in with a term indicating a purpose extracted from the search query.

[0147] {Regional terms} are terms that indicate the names of regions such as Kyoto, Awaji Island, and Kanazawa, and {destination terms} are terms that indicate purposes such as travel, sightseeing, eating and drinking, and accommodation, but are not limited to these examples.

[0148] In cases where a term indicating a location can be extracted from a search query but a term indicating a purpose at that location cannot be extracted from the search query, the generation processing unit 41 can generate a question on a rule basis using the term indicating the purpose estimated by the estimation processing unit 40. This also enables the generation processing unit 41 to generate a question including information indicating a location and information indicating a purpose at the location.

[0149] The templates may differ depending on the combination of the major classification and the medium classification, or may differ depending on the combination of the major classification, the medium classification, and the small classification.

[0150] Furthermore, the search query information includes the search query and information about the user U of the terminal device 2 that sent the search query. The generation processing unit 41 can generate a question using the information about the user U in addition to the search query.

[0151] The information about user U includes, for example, information indicating the attributes of user U. The attributes of user U are demographic attributes such as gender, generation (age), address, family structure, occupation, and annual income, but may also be psychographic attributes such as user U's interests, lifestyle, thoughts, and ideological tendencies, or may be a combination of demographic attributes and psychographic attributes.

[0152] For example, the generation processing unit 41 can generate a question using a template including information on the character string "I'd like to search for {target term} in {regional term}. Please let me know if you have any recommendations.\n\nParticipant: {family structure}." {family structure} is assigned a family structure based on information indicating the attributes of the search query. For example, the information may be the character string "1 man in his 40s, 1 woman in her 40s, 1 male junior high school student."

[0153] In this way, the generation processing unit 41 can generate a question based on the search query and information indicating the attributes of the user U of the terminal device 2 that sent the search query. The information indicating the attributes of the user U is the attribute information of the user U stored in the storage unit 11 or the attributes of the user U estimated by the estimation processing unit 40.

[0154] Generating a question using a generation AI is generation using a generation AI that can generate text, and information including information on the search query selected by the selection unit 32 is input to the generation AI as input information, and the generation AI is caused to output a question.

[0155] The generative AI is, for example, a text generation AI. The text generation AI is, for example, a large-scale language model trained to estimate and output the next token from an input token sequence, such as a transformer-based model or an RNN-based model, but may also be a hybrid model of these. The text generation AI may also be a composite system combined with an identifier to prevent fraudulent use.

[0156] Examples of the transformer-based model include, but are not limited to, GPT, PaLM2, and LLaMA, and examples of the RNN-based model include, but are not limited to, RWKV.

[0157] When a term indicating a location and a term indicating a purpose at that location can be extracted from a search query, the generation processing unit 41 can cause the generation AI to generate a question including a term indicating a location and a term indicating a purpose at that location by using information including the term indicating a location and the term indicating a purpose at that location as input information.

[0158] Furthermore, in cases where a term indicating a location can be extracted from the search query but a term indicating a purpose at that location cannot be extracted from the search query, the generation processing unit 41 can include the term indicating the purpose estimated by the estimation processing unit 40 in the input information as information that complements the search query. This also enables the generation processing unit 41 to generate a question that includes information indicating a location and information indicating a purpose at the location.

[0159] It is desirable that the generation AI is trained so as not to include personal information in the generated results. The generation AI is placed in an external information processing device, and the generation processing unit 41 uses the generation AI via an API, but the generation AI may also be placed within the information processing device 1.

[0160] The generation processing unit 41 inputs information including search query information and instruction information that instructs the generation of a question using the search query information to the generation AI, and can cause the generation AI to generate a question based on the search query information.

[0161] The instruction information may be, for example, a string of characters such as "You are a person with high-level questioning skills. Please create a question that many people will find useful based on the given keywords." However, the instruction information is not limited to such an example.

[0162] The instruction information may also include constraints. Constraints include, for example, an upper limit on the number of characters, a format of expression, and limitations on the type of each item to be included in the output content, and are set, for example, for each category. The format of expression may be, for example, a formal formal expression, or a polite formal expression. Items to be included in the output content include, for example, "participants" and "season" for a question about tourism, and "participants," "purpose of use," "planned drinking," and "budget" for a question about food, but are not limited to these examples. "Participants" includes, for example, age, gender, and number of people.

[0163] The generative AI may be a multimodal generative AI, etc. The multimodal generative AI is, for example, a generative AI that can generate text and images from text and images, etc. Examples of the multimodal generative AI include, but are not limited to, GPT-4 Turbo with vision, Gemini, and CM3Leon.

[0164] Furthermore, in the case of a category related to sightseeing or gourmet food, the generation processing unit 41 may include, in the instruction information, information indicating an instruction to include information indicating the attributes of all family members, including the user U who sent the search query, as "participants" in the question, in the information indicating the constraint conditions. Furthermore, the instruction information may include, in the information indicating the constraint conditions, information indicating an instruction to include "participants" in the question as virtual personas to increase realism.

[0165] In this way, the generation processing unit 41 can generate a question based on the search query and the attributes of the user U of the terminal device 2 that sent the search query. The information indicating the attributes of the user U used by the generation processing unit 41 is information indicating the attributes of the user U acquired by the acquisition unit 30 or information indicating the attributes of the user U estimated by the estimation processing unit 40.

[0166] The instruction information may also include information indicating search query information and example questions based on the search query information. For example, the instruction information may include a string such as "# Example\n\n# Search query example\n Yokosuka sightseeing\n# Question example\nPlease tell me some tourist spots in Yokosuka that are fun for families.\n\n·Participants: Family of 3 (1 man in his 30s, 1 woman in her 30s, 1 teenage woman)\n·Time: Summer vacation (July to August)\n\nWe are particularly interested in interactive attractions that children can enjoy and educational tourist spots. We would also like to know about delicious local gourmet spots. Thank you in advance."

[0167] The instruction information may also include, for example, other questions that satisfy a predetermined condition as example questions. Examples of other questions that satisfy the predetermined condition include, but are not limited to, other questions with a threshold or more of answers, other questions for which the time period from the question until the predetermined number of answers is received is within a threshold, other questions with the top m number of answers, and other questions with the top n number of answers for which the time period from the question until the predetermined number of answers is received is shortest.

[0168] Furthermore, the generation processing unit 41 generates questions for which answers from answer candidates can be accepted, based on the behavioral history of the answer candidate users U. The answer candidate is, for example, a user U whose frequency of answering questions is equal to or greater than a threshold value.

[0169] The behavioral history of user U, who is a potential answer candidate, is, for example, a history of behavior including keywords included in the search query, or, for example, a history of behavior including locations indicated by keywords included in the search query and the purpose of those locations.User U's behavioral history can also be described as a history of user U's experiences.

[0170] The generation processing unit 41 generates questions that are easy for the answer candidate to answer based on the behavioral history of the user U who is the answer candidate. The behavioral history of the user U includes a history of answers given in the past by the answer candidate, and the generation processing unit 41 generates questions that are easy for the answer candidate to answer based on, for example, questions corresponding to answers given in the past by the answer candidate.

[0171] For example, the generation processing unit 41 sets as instruction information information further including the information of the string "Answerers who answer questions should create questions taking into consideration how easy it will be to answer the given example questions.", and inputs as input information to the generation AI information including such instruction information and questions corresponding to answers previously given by answer candidates.

[0172] [3.3.5.Providing Department 34] The providing unit 34 provides various types of information. For example, the providing unit 34 provides the information including the question generated by the generating unit 33 to the answer candidate by transmitting the information including the question generated by the generating unit 33 to the answer candidate. For example, the providing unit 34 provides the question generated by the generating unit 33 to the user U via a Q&A service.

[0173] Furthermore, the providing unit 34 provides information including the question generated by the generating unit 33 and the answer accepted by the accepting unit 31. For example, the providing unit 34 provides the answer to the question generated by the generating unit 33 via a Q&A service that accepts answers to questions.

[0174] For example, the providing unit 34 provides the user U with information including a question that includes a search word specified by the user U and is generated by the generating unit 33, and an answer to the question that is received by posting by the receiving unit 31.

[0175] The providing unit 34 can also provide the user U with information including a question generated by the generating unit 33 on a web page for each category in the Q&A service and an answer to the question that has been posted and accepted by the accepting unit 31.

[0176] Furthermore, providing unit 34 has a search function that performs search processing in response to the search query received by receiving unit 31. The search processing is a search processing of web content, and performs search processing in response to the search query based on, for example, information on web content stored in web content information storage unit 23. Such providing unit 34 includes a search processing unit 50 and a provision processing unit 51.

[0177] 3.3.5.1. Search Processing Unit 50 The search processing unit 50 performs search processing in accordance with the search query in the search service accepted by the accepting unit 31, based on the answer posted and accepted by the accepting unit 31.

[0178] For example, if the search query received by the receiving unit 31 is the same as the search query used by the generation unit 33 to generate a question, the search processing unit 50 performs a search process for web content based on the user U's answer to the question generated by the generation unit 33 using that search query.

[0179] For example, by using a ranking model in which the weights of features corresponding to keywords included in the answers accepted by the accepting unit 31 are increased, search processing is performed so that the display ranking in search results of web content related to the answers posted and accepted by the accepting unit 31 is increased. The ranking model is a neural network-based model, but may also be a model using logistic regression, a decision tree, or the like.

[0180] For example, in the case where there are many posts of information such as the character string "I recommend Cafe XXX" in response to a question generated from search query #1, if the search query accepted by the accepting unit 31 is search query #1, the search processing unit 50 performs search processing so that web content related to "Cafe XXX" is displayed higher in search results. Search query #1 includes, for example, the character string "Please tell me a recommended cafe in Nishi-ku, Fukuoka city," but is not limited to this example.

[0181] For example, the search processing unit 50 can perform search processing so that web content related to "cafe XXX" is displayed higher in search results by using a ranking model that increases the weight of the feature corresponding to "cafe XXX."

[0182] [3.3.5.2. Provision Processing Unit 51] The provision processing unit 51 provides the information including the question generated by the generation unit 33 to the answer candidate by transmitting the information including the question generated by the generation unit 33 to the terminal device 2 of the answer candidate. The provision processing unit 51 provides the question generated by the generation unit 33 to the user U, for example, via a Q&A service. The provision processing unit 51 provides, together with the question, information indicating that the question has been generated using a generation AI, for example.

[0183] Furthermore, the provision processing unit 51 provides information including the question generated by the generation unit 33 and the answer accepted by the acceptance unit 31. For example, the provision processing unit 51 provides the answer to the question generated by the generation unit 33 via a Q&A service that accepts answers to questions.

[0184] For example, the provision processing unit 51 provides the user U with information including a question that includes a search word specified by the user U and is generated by the generation unit 33, and an answer to the question that is received by posting by the reception unit 31.

[0185] The provision processing unit 51 can also provide the user U with information including a question generated by the generation unit 33 on a web page for each category in the Q&A service and an answer to the question that has been posted and accepted by the acceptance unit 31.

[0186] Furthermore, the provision processing unit 51 provides the search results by the search processing unit 50. For example, the provision processing unit 51 transmits information indicating a list of web content as the search results by the search processing unit 50 to the terminal device 2 that transmitted the web content search query, thereby providing the search results by the search processing unit 50 to the user U of the terminal device 2 that transmitted the web content search query.

[0187] 7 is a diagram showing an example of question generation information provided by the providing processing unit 51 of the providing unit 34 in the processing unit 12 of the information processing device 1 according to the embodiment, transmitted to the terminal, and displayed on the terminal device 2. As shown in FIG. 7, question generation information 60 displayed on the terminal device 2 includes questioner information 61, question-related information 62, and an answer button 63.

[0188] The questioner information 61 includes information indicating that the questioner is the generation AI. The question-related information 62 includes question information 62a, which is information indicating the question, and warning information 62b, which is information indicating that the question was generated by the generation AI. This allows the providing unit 34 to provide, along with the question, information indicating that the question was generated using the generation AI. The answer button 63 is a button that the user U of the terminal device 2 selects when providing an answer.

[0189] When the answer button 63 is selected by the user U of the terminal device 2, answer selection information, which is information indicating that the answer button 63 has been selected, is transmitted from the terminal device 2 to the information processing device 1. The providing unit 34 transmits answer input information corresponding to the answer selection information to the terminal device 2. The terminal device 2 displays the answer input information provided by the providing unit 34.

[0190] 8 is a diagram showing an example of answer input information provided by the providing processing unit 51 of the providing unit 34 in the processing unit 12 of the information processing device 1 according to the embodiment, transmitted to the terminal, and displayed on the terminal device 2. As shown in FIG. 8, answer input information 70 displayed on the terminal device 2 includes warning information 71, question information 72, an answer input box 73, a cancel button 74, and a post button 75.

[0191] The notice information 71 is information indicating that the question was generated by the generation AI. The question information 72 is information indicating the question. The answer input box 73 is an input box into which the user U inputs an answer, and the user U can input an answer into the answer input box 73 by operating the terminal device 2.

[0192] The cancel button 74 is a button that is selected by the user U to cancel the answer. The post button 75 is a button for posting the answer entered in the answer input box 73. The user U can post the answer entered in the answer input box 73 to the Q&A service by operating the terminal device 2 and selecting the post button 75.

[0193] [4. Processing Procedure] Next, a procedure of information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Fig. 9 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0194] 9, the processing unit 12 of the information processing device 1 determines whether or not a search query has been received (step S10). If the processing unit 12 determines that a search query has been received (step S10: Yes), the processing unit 12 performs search processing according to the received search query and provides search results (step S11).

[0195] When the processing of step S11 is completed or when it is determined that a search query has not been received (step S10: No), the processing unit 12 determines whether or not a query generation timing has arrived (step S12). The query generation timing is, for example, a timing that occurs at predetermined intervals or a timing designated by the operator of the information processing device 1, but is not limited to such examples.

[0196] When the processing unit 12 determines that it is time to generate a query (step S12: Yes), it collects information on multiple search queries from an external search server or the storage unit 11 (step S13). Then, the processing unit 12 selects information on one or more search queries from the information on the multiple search queries collected in step S13 based on predetermined conditions or the like (step S14), and generates a query based on the information on the one or more selected search queries (step S15). Then, the processing unit 12 provides the query generated in step S15 (step S16).

[0197] When the processing of step S16 is completed or when it is determined that the timing for generating a question has not yet arrived (step S12: No), the processing unit 12 determines whether or not an answer to the question provided in step S18 has been received (step S17). When it is determined that an answer to the question provided in step S18 has been received (step S17: Yes), the processing unit 12 stores the received answer in the storage unit 11 (step S18). In addition, the processing unit 12 provides information including the question generated in step S15 and the answer to the question received in step S17 (step S19).

[0198] When the processing of step S19 is completed or when it is determined that the answer to the question provided in step S18 has not been received (step S17: No), the processing unit 12 determines whether or not the operation end time has arrived (step S20). The processing unit 12 determines that the operation end time has arrived when, for example, the power of the information processing device 1 is turned off.

[0199] If the processing unit 12 determines that the operation end time has not yet arrived (step S20: No), it proceeds to step S10, and if it determines that the operation end time has arrived (step S20: Yes), it terminates the processing shown in Figure 9.

[0200] [5. Modifications] The generation processing unit 41 can also generate questions on a rule-based basis using terms indicating purposes that are trending in other locations, in cases where terms indicating a location can be extracted from the search query but terms indicating a purpose at that location cannot be extracted from the search query.

[0201] The generation processing unit 41 can also include, in the instruction information, multiple questions for which no answers were obtained as negative examples. The generation processing unit 41 can also include, in the instruction information, multiple questions for which a threshold value (for example, 10) or more of answers were obtained as positive examples.

[0202] The generation processing unit 41 can also summarize past questions by category and include the summarized questions in the instruction information as exceptions for a new question. In addition, the generation processing unit 41 can regenerate a question with a different persona if no answer is obtained within a certain period of time.

[0203] [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. 10. Fig. 10 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.

[0204] 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.

[0205] 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.

[0206] The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard or 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.

[0207] 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.

[0208] 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.

[0209] [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.

[0210] 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.

[0211] For example, the information processing device 1 described above may be realized by a terminal device and a server computer, or may be realized by multiple server computers. Furthermore, depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API or network computing.

[0212] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0213] [8. Effects] As described above, the information processing device 1 according to the embodiment includes a generation unit 33 that generates a question based on a search query used to search web content, a reception unit 31 that receives an answer from a user U to the question generated by the generation unit 33, and a provision unit 34 that provides information including the question generated by the generation unit 33 and the answer received by the reception unit 31. This enables the information processing device 1 to improve convenience for the user U.

[0214] Furthermore, the generation unit 33 generates a question based on the search query and the attributes of the user U of the terminal device 2 that sent the search query. This allows the information processing device 1 to further improve convenience for the user U.

[0215] The generation unit 33 also includes an estimation processing unit 40 that estimates attributes of a user U of the terminal device 2, and a processing unit 41 that generates a question based on the search query and the attributes estimated by the estimation processing unit 40. This allows the information processing device 1 to improve the convenience of the user U. This allows the information processing device 1 to further improve the convenience of the user U.

[0216] The search query includes information indicating a location and information indicating a purpose at the location, and the generation unit 33 generates a question including the information indicating the location and the information indicating a purpose at the location. This allows the information processing device 1 to further improve convenience for the user U.

[0217] The search query also includes information indicating a location, and the generation unit 33 includes an estimation processing unit 40 that estimates a purpose at a location, and a generation processing unit 41 that generates a question including the information indicating the location and the information indicating the purpose estimated by the estimation processing unit 40. This allows the information processing device 1 to further improve convenience for the user U.

[0218] Furthermore, the generation unit 33 generates questions to which answers from answer candidates can be accepted, based on the behavioral history of the answer candidates. This allows the information processing device 1 to further improve convenience for the user U.

[0219] Furthermore, the providing unit 34 provides an answer to the question generated by the generating unit 33 via a service that accepts answers to questions. This allows the information processing device 1 to further improve the convenience for the user U.

[0220] The receiving unit 31 receives a search query in a web content search service, and the providing unit 34 includes a search processing unit 50 that performs search processing according to the search query in the search service received by the receiving unit 31 based on the response received by the receiving unit 31, and a providing processing unit 51 that provides the search results by the search processing unit 50. This allows the information processing device 1 to further improve convenience for the user U.

[0221] Furthermore, when the search query received by the receiving unit 31 is the same as the search query used in the question generation AI, the search processing unit 50 performs search processing based on the answer received by the receiving unit 31. This allows the information processing device 1 to further improve the convenience for the user U.

[0222] Furthermore, the generation unit 33 generates questions using a generation AI, which allows the information processing device 1 to improve the accuracy of question generation.

[0223] Furthermore, the providing unit 34 provides, together with the question, information indicating that the question has been generated using a generation AI. This allows the information processing device 1 to further improve the convenience for the user U.

[0224] 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.

[0225] 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]

[0226] 1. Information processing equipment 2. Terminal Device 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Question history information storage unit 22 Answer history information storage unit 23 Web content information storage unit 30 Acquisition Department 31 Reception 32 Selection section 33 Generation part 34 Providing Department 40 Estimation processing unit 41 Generation processing section 50 Search processing unit 51 Provision Processing Unit 100 Information Processing Systems N Network

Claims

1. a generator that generates a query based on a search query used to search web content; a receiving unit that receives an answer from a user to the question generated by the generating unit; a providing unit that provides information including the question generated by the generating unit and the answer received by the receiving unit.

1. An information processing device comprising:

2. The generation unit The question is generated based on the search query and the attributes of the user of the terminal device that sent the search query.

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

3. The generation unit an estimation processing unit that estimates attributes of a user of the terminal device; a generation processing unit that generates the question based on the search query and the attribute estimated by the estimation processing unit.

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

4. The search query is information indicating a location and information indicating a purpose at the location, The generation unit A question including information indicating the location and information indicating a purpose at the location is generated as the question.

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

5. The search query is Contains location information, The generation unit an estimation processing unit that estimates a purpose at the location; a generation processing unit that generates a question including the information indicating the location and the information indicating the purpose estimated by the estimation processing unit.

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

6. The generation unit Generate questions to which answers from the candidate answerers are accepted based on the behavioral history of the candidate answerers.

4. The information processing device according to claim 1, wherein the information processing device is a computer.

7. The providing unit Providing an answer to the question generated by the generation unit via a service that accepts answers to questions 4. The information processing device according to claim 1, wherein the information processing device is a computer.

8. The reception unit Accepting search queries in a web content search service; The providing unit a search processing unit that performs search processing in accordance with the search query in the search service received by the receiving unit based on the answer received by the receiving unit; a providing processing unit that provides the search results obtained by the search processing unit.

4. The information processing device according to claim 1, wherein the information processing device is a computer.

9. The search processing unit If the search query received by the receiving unit is the same as the search query used to generate the question, the search process is performed based on the answer received by the receiving unit.

9. The information processing apparatus according to claim 8,

10. The generation unit Generate the question using generation AI 4. The information processing device according to claim 1, wherein the information processing device is a computer.

11. The providing unit Providing information with the question indicating that the question was generated using generative AI 11. The information processing apparatus according to claim 10,

12. 1. A computer-implemented information processing method, comprising: a generation step of generating a query based on a search query used to search the web content; a receiving step of receiving an answer from a user to the question generated by the generating step; a providing step of providing information including the question generated in the generating step and the answer received in the receiving step.

1. An information processing method comprising:

13. a generation step for generating a query based on a search query used to search the web content; a receiving step of receiving an answer from a user to the question generated by the generating step; a providing step of providing information including the question generated by the generating step and the answer received by the receiving step, An information processing program characterized by:

Images