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

Abstract

To provide an appropriate answer to a user's question.SOLUTION: An information processing device comprises a determination unit, an extraction unit, and a generation unit. The determination unit determines whether or not a question accepted from a user is a question related to a predetermined content. When the determination unit determines that the question is related to the predetermined content, the extraction unit extracts index information having a high relevance to the question among the index information where the predetermined content is summarized for each region. The generation unit generates an answer to the question from the index information extracted by the extraction unit.SELECTED DRAWING: Figure 6

Description

Technical Field

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

Background Art

[0002] Conventionally, techniques for making it easier to obtain the answers that users want are known.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional technology, there is still room for further improvement in providing appropriate answers to users' questions.

[0005] The present application has been made in view of the above, and an object thereof is to provide an appropriate answer to a user's question.

Means for Solving the Problems

[0006] The information processing apparatus according to the present application includes a determination unit that determines whether a question received from a user is a question related to predetermined content, and when it is determined by the determination unit that the question is a question related to the predetermined content, an extraction unit that extracts index information having a high relevance to the question from index information obtained by summarizing the predetermined content for each region, and a generation unit that generates an answer to the question from the index information extracted by the extraction unit.

Effects of the Invention

[0007] According to one aspect of the embodiment, it is possible to provide an appropriate answer to a user's question. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is an explanatory diagram for explaining an overview of information processing according to an embodiment. [Diagram 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 information processing according to the embodiment (first embodiment). [Figure 4] FIG. 4 is a diagram illustrating an example of information processing according to the embodiment (second embodiment). [Figure 5] FIG. 5 is a diagram illustrating an example of the configuration of a terminal device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of the configuration of an information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of an index information storage unit according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of the response evaluation information storage unit according to the embodiment. [Figure 9] FIG. 9 is a flowchart showing an example of information processing according to the embodiment (first embodiment). [Figure 10] FIG. 10 is a flowchart showing an example of information processing according to the embodiment (second embodiment). [Figure 11] FIG. 11 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, 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 same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0010] (Embodiment) [1. Overview of Information Processing] An overview of information processing according to an embodiment will be described with reference to FIG. 1. FIG. 1 is an explanatory diagram for explaining the overview of information processing according to an embodiment. As shown in FIG. 1, Overview R includes Overviews R1 to R6. Overview R1 acquires content such as regulations, web content, and store information (such as sales history). An answer to a question from User U is generated using sentences in this content. Overview R2 is an index builder that indexes the content acquired in Overview R1. Overview R3 acquires indexed information (index information) indexed in Overview R2. Overview R4 is a dispatcher that executes tasks based on operations by User U. For example, it executes a task to answer a question received from User U. Overview R5 is a prompt builder that generates a prompt using the index information acquired in Overview R3 and the question received in Overview R4. For example, incentive information corresponding to the question received in Overview R4 is extracted and a prompt is generated from the incentive information. Overview R6 is a generative AI model such as GPT that generates an answer to User U's question based on the prompt generated in Overview R5. The answer generated in overview R6 is provided to user U via the dispatcher.

[0011] [2. Information Processing System Configuration] An information processing system 1 shown in Fig. 2 will be described. As shown in Fig. 2, the information processing system 1 includes a terminal device 10 and an information processing device 100. The terminal device 10 and the information processing device 100 are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other via wired or wireless communication. Fig. 2 is a diagram showing an example of the configuration of the information processing system 1 according to an embodiment.

[0012] The terminal device 10 is an information processing device used by a user who asks a question. The user may, for example, ask a question about the contents of regulations, laws, rules, manuals, etc. For example, a user who is going on a business trip may ask, "What is the upper limit on accommodation costs in the company's accommodation regulations?" The user inputs the question using, for example, a chat tool that allows for the exchange of comments in text. The terminal device 10 may be any device that can realize the processing in the embodiment. The terminal device 10 may also be a device such as a smartphone, a tablet device, a notebook PC, a desktop PC, a mobile phone, or a PDA. FIG. 4 shows a case where the terminal device 10 is a smartphone.

[0013] The terminal device 10 is, for example, a smart device such as a smartphone or tablet, and is a mobile terminal device that can communicate with any server device via a wireless communication network such as 4G to 5G (Generations) or LTE (Long Term Evolution). The terminal device 10 also has a screen such as a liquid crystal display with a touch panel function, and may accept various operations on displayed data such as content, such as tapping, sliding, and scrolling, performed by a user's finger or stylus. In FIG. 4, the terminal device 10 is used by a user U1.

[0014] The information processing device 100 is an information processing device intended to provide appropriate answers to user questions, and may be any device capable of implementing the processes described in the embodiments. The information processing device 100 broadly performs two types of processing. The first is processing performed before accepting a question from a user, and is processing for providing an appropriate answer when the question is accepted from the user. The second is processing performed when the question is accepted from the user, and is processing for generating an answer to the user's question using information resulting from the first processing. Specifically, in the first processing, the information processing device 100 generates information (hereinafter referred to as "index information") that summarizes content (such as regulations, laws, rules, and manuals) by predetermined unit (hereinafter referred to as "area" in the embodiments), such as by chapter, article (provision), sentence, or main idea (a main idea with a predetermined meaning assigned in advance). The generated index information is then used in the second processing. In the second processing, when the information processing device 100 accepts a question from a user, it inputs the index information generated in the first processing into a generation AI to generate an answer to the question.

[0015] Here, index information according to the embodiment will be described. Llama Index and the like are used to generate index information according to the embodiment. Llama Index is a tool for generating context from a large amount of user data and for performing data searches by inputting a question received from a user and personal user data. That is, Llama Index accesses database information sources and the like to assist in generating prompts. Index information is structured to organize data acquired from such information sources and make it easier to search. By using such index information, the information processing device 100 can efficiently access private information when generating prompts and generate contexts that include private information. When the information processing device 100 receives a question in natural language from a user, it uses Llama Index and the like to search for index information that matches the user's question and inputs it into the generation AI.

[0016] A generative AI is, for example, a text generation model that has learned from data published on the Internet, etc. For example, it is a GPT (Generative Pre-trained Transformer) model that generates answers to questions. Such a model generates answers to questions from data published on the Internet. Since new data is published on the Internet every day, the answers generated by the model will be updated every day. That is, even if the same question is asked, the data referred to by the model when generating an answer will be different depending on the timing of the question, etc., so different answers will be generated. In addition, since the model can provide detailed answers to a wide variety of questions, a wide variety of questions are asked by users to the model.

[0017] Note that in FIG. 2, the case where the terminal device 10 and the information processing device 100 are separate devices is shown, but the terminal device 10 and the information processing device 100 may be integrated.

[0018] 〔3. An Example of Information Processing〕 Conventionally, techniques for making it easier for users to obtain desired answers are known. For example, a technique for providing an in-house chatbot system by utilizing in-house data is known (Patent Document 1 above). Also, for example, a technique for dividing regulations, manuals, etc. into predetermined units such as chapters and paragraphs and tagging them is known (Patent Document 2 above). However, in the conventional techniques, for example, since processing for answer generation is performed using the natural language questions from users as they are, there is room for further improvement in providing appropriate answers to users' questions. The present application has been made in view of the above, and an object thereof is to provide an appropriate answer to a user's question.

[0019] The following describes two information processes as the information processing of the information processing system 1 according to the embodiment. As described above, the first information process (Embodiment 1) is an information process for generating index information, and the second information process (Embodiment 2) is an information process for generating an answer to a question from a user. By combining the two information processes, it becomes possible to provide an appropriate answer to the user's question. In the first information process (Indexing Stage), the information processing apparatus 100 sorts the data acquired from the data source and performs indexing. In the second information process (Querying Stage), the information processing apparatus 100 analyzes the question input by the user, extracts relevant information from the index, and generates a final response. By using this mechanism, the LAMA index can efficiently manage a large amount of data, and the user can quickly obtain the necessary information. In particular, it is useful when a lot of information is scattered or when specific information needs to be quickly retrieved, greatly improving the efficiency of generating prompts for generative AI and enabling better results to be obtained.

[0020] (Embodiment 1: Information Processing for Generating Index Information) FIG. 3 is a diagram showing an example of the information processing of the information processing system 1 according to Embodiment 1. The information processing apparatus 100 acquires content (Content A) that is the subject of a question from the user (step S101). The content according to the embodiment is, for example, regulations, laws, rules, manuals, etc., but may be content of any kind and need not be particularly limited. Note that the content according to the embodiment may be converted into a document object such as a PDF. In the embodiment described later, an example where the content is the "Business Trip Expense Regulations" will be described, but the content may be the "Service Use Regulations" that define the rights and obligations of the service provider and the matters to be observed by the user between the service provider and the user. That is, information acquired from different databases may be converted into a document object. Then, the document object thus converted may be converted into more manageable nodes and indexed for efficient data access.

[0021] The information processing apparatus 100 divides the acquired content into areas (area A1, area A2, area A3, ···) (step S102). For example, the information processing apparatus 100 divides the content by areas such as by chapter, by article, by sentence, by main idea, etc. Note that the size of the area to be divided (the range of area division) may be determined from the context of the content. That is, the information processing apparatus 100 may divide the content into areas according to, for example, the context of the content.

[0022] The information processing apparatus 100 generates summaries (summary A1, summary A2, ···) for each of the divided areas (step S103). Here, the generated summary is, for example, "The business trip travel expenses have a ceiling of 5000 yen per night", etc. The summary generated in this way is included in the index information.

[0023] The information processing apparatus 100 generates index information (index F1, index F2, ···) by associating the generated summary with a label (which may be a label indicating the entire article) indicating the content that is the source of the summary (step S104). The labels (label B1, label B2, ···) are, for example, labels indicating what kind of regulations, laws, what kind of rules or manuals they are. For example, in the case of content related to regulations, the label is something like "Business Trip Travel Expenses Regulations". Also, at this time, the information processing apparatus 100 may generate index information by associating, for example, the summary, the label, and a label (hereinafter, appropriately referred to as a "range label") indicating the range in the content that is the source of the summary. The range labels (range label C1, range label C2, ···) are, for example, labels indicating which chapter, which article, which sentence, etc. in the content the summary is. For example, the range label is something like "Article 5". Therefore, taking a specific example, the information processing apparatus 100 generates index information by associating a summary such as "The business trip travel expenses have a ceiling of 5000 yen per night" with a label such as "Business Trip Travel Expenses Regulations" and a range label such as "Article 5". The label may be information indicating the parent-child relationship with the content, and the range label may be information indicating the parent-child relationship with the content or the label.

[0024] In this way, in Embodiment 1, the information processing apparatus 100 divides the content into regions, generates a summary for each divided region, assigns a label to the generated summary, and uses it as index information. For example, for a summary such as "The business trip travel expenses have a ceiling of 5,000 yen per night", the information processing apparatus 100 assigns a label related to a regulation such as "Business trip travel expense regulations" and a label related to an article such as "Article 5".

[0025] (Embodiment 2: Information processing for generating an answer to a user's question) FIG. 4 is a diagram showing an example of information processing of the information processing system 1 according to Embodiment 2. The information processing apparatus 100 acquires information related to the question P1 received from the user U1 (step S201). In the following embodiments, the case where the information processing apparatus 100 acquires information related to a question P1 with the content such as "What is the upper limit of the accommodation fee for the company's accommodation regulations?" from the user U1 will be taken as an example for explanation. In Embodiment 2, when receiving a user's question, appropriate information corresponding to it is retrieved from the index information, relevant nodes are retrieved, necessary information is selected, and it is used as part of an inquiry to the generation AI. As a result, it becomes possible to efficiently extract highly relevant information from a large amount of data, and it becomes possible to generate a natural language response corresponding to the user's question.

[0026] Based on the acquired information, the information processing apparatus 100 determines whether the question P1 received from the user U1 is a question related to a predetermined content (such as regulations, laws, rules, or manuals) (step S202). For example, the information processing apparatus 100 determines whether the question P1 received from the user U1 is a question related to regulations.

[0027] When it determines that it is a question related to predetermined content, the information processing apparatus 100 extracts index information (that is, index information obtained by summarizing predetermined content for each area) highly relevant to the question P1 of the user U1 from among the index information generated in Embodiment 1 (step S203). For example, the information processing apparatus 100 extracts index information highly relevant to the question P1 of the user U1 by matching the label associated with the index information with the question P1 of the user U1 to identify a label highly relevant to the question P1 of the user U1. For example, when index information associated with the label of "business trip expense regulations", index information associated with the label of "employment regulations", and index information associated with the label of "childcare / nursing care leave regulations" are candidates, the information processing apparatus 100 identifies the label of "business trip expense regulations" highly relevant to the question P1 such as "What is the upper limit of the accommodation expense in the company's accommodation regulations?" and extracts the index information associated with the label of "business trip expense regulations". By extracting the index information associated with the label of "business trip expense regulations", the information processing apparatus 100 can, for example, obtain a summary such as "The upper limit of the business trip expense per night is 5,000 yen" associated with the label of "business trip expense regulations" and a range label of "Article 5" associated with the label of "business trip expense regulations". Note that the information processing apparatus 100 may perform the extraction process of index information with high relevance through a search based on, for example, the vector information of the index information.

[0028] The information processing device 100 generates an answer to the user U1's question P1 from the extracted index information. Specifically, the information processing device 100 generates a prompt for generating an answer to the question P1 from the extracted index information, and inputs it to a text generation AI such as a GPT model to generate an answer to the question P1 (step S204). Taking a specific example, based on the extracted index information, the information processing device 100 generates a prompt such as "Please output the upper limit of accommodation expenses" from a question P1 with the content "What is the upper limit of accommodation expenses in the company's accommodation regulations?", a summary such as "The upper limit of business trip expenses per night is 5,000 yen", a label such as "Business trip expense regulations", and a range label such as "Article 5", enabling the output of an answer such as "In the business trip expense regulations, it is 5,000 yen". Then, the information processing device 100 provides the answer to the question P1 to the user U1 (step S205). Specifically, the information processing device 100 transmits information regarding the answer to the question P1 (information for displaying the answer) to the terminal device 10. Then, the terminal device 10 displays the answer provided by the information processing device 100.

[0029] As described above, in the second embodiment, when the information processing device 100 receives a question P1 from a user U1, it extracts highly relevant index information and generates a prompt for a sentence generation AI using a summary of the extracted index information. For example, the user U1 inputs the question P1 to a bulletin board of a specific tool. For example, the user U1 inputs the question P1 about the content of a specific content. When the information processing device 100 receives the question P1 from the user U1, it generates a prompt using a sentence generation AI. In this case, the information processing device 100 generates the prompt using a library in which the content of the content is divided into regions and index information is generated for each region. In this case, for example, the information processing device 100 calculates a score indicating the degree of relevance for each piece of index information and extracts index information with a high relevance score. Then, for example, the information processing device 100 generates a prompt for generating an answer using text data of a summary of the extracted index information. Furthermore, for example, if there is no index information with a high relevance score, the information processing device 100 generates a prompt for generating an answer without using the index information. In this case, for example, an answer to the question P1 is generated without index information (such as a summary). In this case, for example, the information processing device 100 generates an answer to the question P1 by inputting a prompt to the sentence generation AI for generating an answer without using index information. Note that, for example, if there is no index information with a high relevance score, the information processing device 100 may end information processing without generating a prompt for generating an answer.

[0030] (Processing variations) In the above embodiment, if the information processing device 100 determines that the question is not related to the predetermined content, it generates a prompt for generating an answer without using index information. In this case, for example, an answer to the question P1 is generated without index information (such as a summary), just as in the case where there is no index information with a high relevance score. In this case, for example, the information processing device 100 generates an answer to the question P1 by inputting a prompt for generating an answer without using index information to the sentence generation AI, just as in the case where there is no index information with a high relevance score. In this way, the information processing device 100 may determine whether to use index information depending on the type of question, and perform processing using the index information (processing for generating an answer) only for questions of a predetermined type. Furthermore, even if the information processing device 100 determines that the question is related to the predetermined content, the index information accessible by the user may be limited. In the above embodiment, for example, the information processing device 100 may extract highly relevant index information from the index information accessible to the user U1 to generate a prompt. Note that, if the information processing device 100 determines that the question is not related to the predetermined content, it may terminate information processing without generating a prompt for generating an answer, just as in the case where there is no index information with a high relevance score.

[0031] In the above embodiment, the information processing apparatus 100 may perform processing for optimizing the range (size of the area) of area division according to the answer accuracy. In the example of the above embodiment, when the user U1 evaluates an answer which is an output result such as "What is the upper limit of the accommodation fee in the company's accommodation regulations? The accommodation fee limit in the business trip expense regulations is 5,000 yen." for the question P1, the evaluation of the user U1 may be received as the evaluation of the answer. In this way, the information processing apparatus 100 receives evaluations from (a plurality of) users. When the evaluation is low, a plurality of index information with the range of area division changed is set, and if the evaluation becomes high by changing to any of the plurality of index information, it may be changed to the index information when the evaluation is the highest.

[0032] In the above embodiment, when there is a predetermined exemplary answer (model answer) such as Q&A (or FAQ), the information processing apparatus 100 may generate a prompt using the model answer. For example, the information processing apparatus 100 may generate a prompt instructing to output the model answer together with the answer according to the above embodiment. For example, the information processing apparatus 100 may generate a prompt for outputting a model answer such as "The model answer is as follows: 〇×〇×···" together with an answer such as "The accommodation fee limit in the business trip expense regulations is 5,000 yen."

[0033] In the above embodiment, the information processing apparatus 100 may perform linking for the generated answer. For example, the information processing apparatus 100 may perform linking to the content corresponding to the label associated with the index information used for generating the answer.

[0034] In the above-described embodiment, the case where the label is "Business Trip Expense Regulations", "Employment Regulations", "Childcare / Nursing Care Leave Regulations", etc. has been described as an example, but it does not necessarily have to be particularly limited to these examples. The label according to the embodiment may be a label indicating a specific regulation, law, specific rule, manual, etc., but it does not necessarily have to be particularly limited. Also, in the above-described embodiment, the case where the range label is "Article 5" etc. has been described as an example, but it does not necessarily have to be particularly limited to this example. The range label according to the embodiment may be a label indicating a specific chapter, article, sentence, etc., but it does not necessarily have to be particularly limited.

[0035] [4. Configuration of Terminal Device] Next, with reference to FIG. 5, the configuration of the terminal device 10 according to the embodiment will be described. FIG. 5 is a diagram showing a configuration example of the terminal device 10 according to the embodiment. As shown in FIG. 5, the terminal device 10 includes a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

[0036] (Communication Unit 11) The communication unit 11 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 11 is connected to a predetermined network N by wire or wirelessly, and information is transmitted and received between the communication unit 11 and an information processing device 100 or the like via the predetermined network N.

[0037] (Input Unit 12) The input unit 12 receives various operations from the user. In FIG. 4, various operations from the user U1 are received. For example, the input unit 12 may receive various operations from the user via the display surface by a touch panel function. Also, the input unit 12 may receive various operations from buttons provided on the terminal device 10, or a keyboard or mouse connected to the terminal device 10. For example, the input unit 12 receives an operation for inputting a question.

[0038] (Output Unit 13) The output unit 13 is a display screen of a tablet terminal realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. For example, the output unit 13 displays the information transmitted from the information processing apparatus 100. For example, the output unit 13 displays the answer to the user's question generated by the information processing apparatus 100.

[0039] (Control unit 14) The control unit 14 is, for example, a controller, and is realized by various programs stored in the storage device inside the terminal device 10 being executed with the RAM (Random Access Memory) as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. For example, these various programs include the programs of the applications installed in the terminal device 10. For example, these various programs include the programs of the applications for displaying the information (such as the answer to the user's question) transmitted from the information processing apparatus 100. Further, the control unit 14 is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0040] As shown in FIG. 5, the control unit 14 has a receiving unit 141 and a transmitting unit 142, and realizes or executes the operations of information processing described below.

[0041] (Receiving unit 141) The receiving unit 141 receives, for example, the information transmitted from the information processing apparatus 100. For example, the receiving unit 141 receives the information regarding the answer to the user's question. For example, the receiving unit 141 receives the information for displaying the answer to the user's question.

[0042] (Transmitting unit 142) The transmission unit 142 transmits, for example, operation information performed by the user. For example, the transmission unit 142 transmits information regarding a question received from the user (for example, input by the user, specified by the user, selected by the user).

[0043] [5. Configuration of Information Processing Apparatus] Next, with reference to FIG. 6, the configuration of the information processing apparatus 100 according to the embodiment will be described. FIG. 6 is a diagram showing a configuration example of the information processing apparatus 100 according to the embodiment. As shown in FIG. 6, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. Note that the information processing apparatus 100 may include an input unit (for example, a keyboard or a mouse) that receives various operations from the administrator of the information processing apparatus 100, and a display unit (for example, a liquid crystal display) that displays various information.

[0044] (Communication Unit 110) The communication unit 110 is realized by, for example, a NIC or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and performs information transmission and acquisition with the terminal device 10 or the like via the network N.

[0045] (Storage Unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 6, the storage unit 120 includes an index information storage unit 121 and an answer evaluation information storage unit 122.

[0046] The index information storage unit 121 stores index information. Here, FIG. 7 shows an example of the index information storage unit 121 according to the embodiment. The information stored in the index information storage unit 121 is used, for example, for generating an answer. As shown in FIG. 7, the index information storage unit 121 has items such as "index information ID", "content ID", "label", "range label", and "summary".

[0047] "Index Information ID" indicates identification information for identifying index information. "Content ID" indicates identification information for identifying content. "Label" indicates a label (a label indicating the content of the content). "Range Label" indicates a range label (a label indicating a specific range within the content). "Summary" indicates a summary (a label indicating a summary corresponding to a specific range within the content).

[0048] The Answer Evaluation Information Storage Unit 122 stores evaluation information for an answer. Here, FIG. 8 shows an example of the Answer Evaluation Information Storage Unit 122 according to the embodiment. The information stored in the Answer Evaluation Information Storage Unit 122 is used, for example, for optimizing the range of area division. As shown in FIG. 8, the Answer Evaluation Information Storage Unit 122 has items such as "Index Information ID" and "Answer Evaluation Information".

[0049] "Index Information ID" indicates identification information for identifying index information. "Answer Evaluation Information" indicates evaluation information for an answer. In the example shown in FIG. 8, an example is shown in which conceptual information such as "Answer Evaluation Information #1" and "Answer Evaluation Information #2" is stored in "Answer Evaluation Information", but actually, a score indicating a comprehensive evaluation by (multiple) users is stored, etc.

[0050] (Control Unit 130) The Control Unit 130 is a controller and is realized, for example, by various programs stored in the storage device inside the information processing apparatus 100 being executed with the RAM as a work area by a CPU, MPU, etc. Also, the Control Unit 130 is realized by an integrated circuit such as an ASIC or FPGA, for example.

[0051] As shown in FIG. 6, the Control Unit 130 has an Acquisition Unit 131, a Division Unit 132, a First Generation Unit 133, a Second Generation Unit 134, a Determination Unit 135, an Extraction Unit 136, a Third Generation Unit 137, and a Provision Unit 138, and realizes or executes the operations of information processing described below. Note that the internal configuration of the Control Unit 130 is not limited to the configuration shown in FIG. 6, and other configurations may be used as long as they perform the information processing described later.

[0052] (Acquisition part 131) The acquiring unit 131 acquires various pieces of information from the storage unit 120. The acquiring unit 131 also stores the acquired various pieces of information in the storage unit 120.

[0053] The acquisition unit 131 acquires various pieces of information from an external information processing device. The acquisition unit 131 acquires various pieces of information from other information processing devices such as the terminal device 10.

[0054] The acquisition unit 131 acquires, for example, content that is the subject of a question from a user. For example, the acquisition unit 131 acquires text data of the content (for example, an entire sentence). Furthermore, for example, when the acquisition unit 131 receives a question from a user, it acquires the user's question (such as a question sentence).

[0055] (Divided part 132) The dividing unit 132, for example, divides the content acquired by the acquiring unit 131. For example, the dividing unit 132 divides the content acquired by the acquiring unit 131 into regions according to the context (for example, regions for each chapter, each article, each sentence, etc.). For example, the dividing unit 132 divides the content into one or more (may be multiple) regions in this way.

[0056] (First generation unit 133) For example, the first generation unit 133 generates a summary for each region divided by the division unit 132. For example, when the content is divided into regions for each chapter, the first generation unit 133 generates a summary for each chapter.

[0057] (Second generation unit 134) The second generating unit 134 generates index information that links, for example, the summary generated by the first generating unit 133 with a label corresponding to the original content. The second generating unit 134 also generates index information that links, for example, the summary generated by the first generating unit 133 with a label corresponding to the original content and a range label corresponding to a range in the original content (the range corresponding to the summary generated by the first generating unit 133).

[0058] The index information generated in this way is used to generate prompts for generating answers when a question is received from a user, and is also used to extract index information that is highly relevant to the question when a question is received from a user.

[0059] (Judgment unit 135) For example, the determination unit 135 determines whether the question acquired by the acquisition unit 131 is a question related to predetermined content. For example, the determination unit 135 determines whether the question is related to any of regulations, laws, rules, manuals, etc. Furthermore, for example, the determination unit 135 determines whether the question is related to a specific regulation, law, rule, manual, etc.

[0060] (Extraction part 136) For example, when the determination unit 135 determines that a question is related to a predetermined content, the extraction unit 136 extracts index information that is highly relevant to the question from the index information. At this time, the extraction unit 136 calculates, for example, a score indicating the degree of relevance to the question for each piece of index information, and extracts index information whose score is equal to or greater than a predetermined threshold. Note that, for example, when there is no index information whose score is equal to or greater than a predetermined threshold (i.e., there is no highly relevant index information), the extraction unit 136 does not extract any index information.

[0061] (Third generation unit 137) The third generation unit 137 generates an answer to a question received from a user, for example, from the index information extracted by the extraction unit 136. For example, the third generation unit 137 generates a prompt for generating an answer to the question received from the user, and inputs the prompt to a sentence generation AI, thereby outputting the answer as the answer to the question received from the user.

[0062] For example, the third generation unit 137 generates an answer to a question received from a user without using index information when index information is not extracted by the extraction unit 136. For example, the third generation unit 137 generates a prompt for generating an answer to a question received from a user without using index information, and inputs the prompt to a sentence generation AI, thereby outputting the answer as the answer to the question received from the user.

[0063] For example, if the determination unit 135 determines that the question is not related to the specified content, the third generation unit 137 generates an answer to the question received from the user without using the index information, just as in the case where the extraction unit 136 does not extract the index information.

[0064] (Provider 138) For example, the providing unit 138 provides information about the answer generated by the third generating unit 137 to the user who asked the question. For example, the providing unit 138 transmits content indicating the answer generated by the third generating unit 137 to the terminal device 10. Furthermore, for example, the providing unit 138 transmits information for displaying the content indicating the answer generated by the third generating unit 137 to the terminal device 10.

[0065] [6. Information Processing Flow] Next, the procedure of information processing by the information processing system 1 according to the embodiment will be described with reference to Fig. 9 and Fig. 10. Fig. 9 and Fig. 10 are flowcharts showing the procedure of information processing by the information processing system 1 according to the embodiment (embodiment 1 and embodiment 2).

[0066] As shown in FIG. 9 (first embodiment), the information processing device 100 acquires content to be studied (step S301).

[0067] The information processing device 100 divides the acquired content into regions according to the context (step S302).

[0068] The information processing apparatus 100 generates a summary for each divided area (step S303).

[0069] The information processing apparatus 100 generates index information corresponding to the generated summary (step S304).

[0070] As shown in FIG. 10 (Embodiment 2), the information processing apparatus 100 acquires a question received from a user (step S401).

[0071] The information processing apparatus 100 determines whether the acquired question is a question related to predetermined content (step S402).

[0072] When the information processing apparatus 100 determines that the question is a question related to the predetermined content (step S402; YES), it determines whether there is index information having a high relevance to the question among the index information obtained by summarizing the predetermined content for each area (step S403).

[0073] When the information processing apparatus 100 determines that there is index information having a high relevance to the question (step S403; YES), it extracts the index information having a high relevance to the question (step S404). Then, the information processing apparatus 100 generates an answer to the question from the extracted index information (step S405).

[0074] On the other hand, when the information processing apparatus 100 determines that the question is not a question related to the predetermined content (step S402; NO), and when it determines that there is no index information having a high relevance to the question (step S403; NO), it generates an answer to the question without extracting the index information (step S406).

[0075] 〔7. Effects〕 As described above, the information processing apparatus 100 according to the embodiment includes a determination unit 135, an extraction unit 136, and a third generation unit 137. The determination unit 135 determines whether a question received from a user is a question related to predetermined content. The extraction unit 136 extracts index information having a high relevance to the question from among index information obtained by summarizing the predetermined content for each region when it is determined by the determination unit 135 that the question is related to the predetermined content. The third generation unit 137 generates an answer to the question from the index information extracted by the extraction unit 136.

[0076] Thereby, the information processing apparatus 100 according to the embodiment can generate an appropriate answer to the user's question by converting the user's natural language question into easy-to-handle information instead of using the question as it is, for example.

[0077] Further, the third generation unit 137 generates a prompt for generating an answer to the question, which is a prompt input to the text generation AI.

[0078] Thereby, the information processing apparatus 100 according to the embodiment can significantly improve the efficiency of generating a prompt for the generation AI, for example.

[0079] Further, when the third generation unit 137 cannot extract index information having a high relevance to the question, the third generation unit 137 generates an answer without using the index information.

[0080] Thereby, the information processing apparatus 100 according to the embodiment can generate an appropriate answer to the user's question by preventing noise from entering, for example, when the relevance to the question is low.

[0081] Further, when it is determined by the determination unit 135 that the question is not a question related to the predetermined content, the third generation unit 137 generates an answer without using the index information.

[0082] As a result, the information processing apparatus 100 according to the embodiment can generate an appropriate answer to the user's question by, for example, preventing noise from entering when the question is not related to a predetermined content.

[0083] Also, the predetermined content is a regulation.

[0084] As a result, the information processing apparatus 100 according to the embodiment can generate an appropriate answer regarding the regulation, for example.

[0085] 〔8. Hardware Configuration〕 Also, the information processing apparatus 100 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. 11. FIG. 11 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing apparatus 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0086] The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

[0087] The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 acquires data from other devices via a predetermined communication network and sends it to the CPU 1100, and sends the data generated by the CPU 1100 to other devices via a predetermined communication network.

[0088] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0089] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 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.

[0090] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 130. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0091] [9. 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 a known method. 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.

[0092] 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.

[0093] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0094] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, 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 undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0095] 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]

[0096] 1. Information Processing Systems 10 Terminal Equipment 11 Communications Department 12 Input section 13 Output section 14 Control Unit 100 Information processing device 110 Communications Department 120 Storage section 121 Index information storage unit 122 Answer evaluation information storage unit 130 control section 131 Acquisition Department 132 Division 133 1st generation part 134 Second generation part 135 Judgment section 136 Extraction part 137 Third generation part 138 Provision Department 141 Receiving unit 142 Transmitter N Network

Claims

1. A determination unit that determines whether a question received from a user is a question related to predetermined content; An extraction unit that, when the determination unit determines that the question is a question related to the predetermined content, extracts index information having a high relevance to the question from index information obtained by summarizing the predetermined content for each region; A generation unit that generates an answer to the question from the index information extracted by the extraction unit; An information processing apparatus, characterized by comprising the above.

2. The generation unit: Generates a prompt for generating an answer to the question and inputting it to a text generation AI. The information processing apparatus according to claim 1, characterized by the above.

3. The generation unit: When index information having a high relevance to the question cannot be extracted, generates the answer without using the index information. The information processing apparatus according to claim 1, characterized by the above.

4. The generation unit: When the determination unit determines that the question is not a question related to the predetermined content, generates the answer without using the index information. The information processing apparatus according to claim 1, characterized by the above.

5. The predetermined content is a regulation. The information processing apparatus according to claim 1, characterized by the above.

6. An information processing method executed by a computer, comprising: A determination step of determining whether a question received from a user is a question related to predetermined content; An extraction step of extracting, when it is determined in the determination step that the question is a question related to the predetermined content, index information having a high relevance to the question from index information obtained by summarizing the predetermined content for each region; A generation step of generating an answer to the question from the index information extracted in the extraction step; An information processing method, characterized by including the above.

7. A determination procedure for determining whether a question received from a user is a question related to predetermined content; An extraction procedure for extracting, when it is determined in the determination procedure that the question is a question related to the predetermined content, index information having a high relevance to the question from index information obtained by summarizing the predetermined content for each region; A generation procedure for generating an answer to the question from the index information extracted in the extraction procedure; An information processing program, characterized by causing a computer to execute the above.

Images