JP7833487B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

This invention relates to an information processing device, an information processing method, and an information processing program.

Traditionally, technologies have been developed to make it easier for users to obtain the answers they want.

Japanese Patent Publication No. 2023-081009 Patent No. 4900041

However, conventional technology still had room for improvement in providing appropriate answers to user questions.

This application was made in view of the above, and aims to provide appropriate answers to user questions.

The information processing device according to this application is characterized by comprising: a determination unit that determines whether a question received from a user is related to predetermined content; an extraction unit that, if the determination unit determines that the question is related to predetermined content, extracts index information that is highly relevant to the question from index information that summarizes the predetermined content by area; and a generation unit that generates an answer to the question from the index information extracted by the extraction unit.

According to one embodiment, it has the effect of providing appropriate answers to user questions.

Figure 1 is an explanatory diagram illustrating the overview of the information processing according to the embodiment. Figure 2 shows an example of the configuration of an information processing system according to the embodiment. Figure 3 shows an example of information processing according to the embodiment (Embodiment 1). Figure 4 shows an example of information processing according to the embodiment (Embodiment 2). Figure 5 shows an example of the configuration of a terminal device according to this embodiment. Figure 6 shows an example of the configuration of an information processing device according to the embodiment. Figure 7 shows an example of an index information storage unit according to the embodiment. Figure 8 shows an example of a response evaluation information storage unit according to the embodiment. Figure 9 is a flowchart showing an example of information processing according to the embodiment (Embodiment 1). Figure 10 is a flowchart showing an example of information processing according to the embodiment (Embodiment 2). Figure 11 is a hardware configuration diagram showing an example of a computer that implements the functions of an information processing device.

The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing device, information processing method, and information processing program according to this application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to this application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

(Embodiment)
[1. Overview of Information Processing]
Figure 1 will be used to explain the overview of the information processing according to the embodiment. Figure 1 is an explanatory diagram for explaining the overview of the information processing according to the embodiment. As shown in Figure 1, Overview R includes Overviews R1 to R6. Overview R1 is the acquisition of content such as terms and conditions, web content, and store information (sales history, etc.). Answers to user U's questions are generated using the sentences in this content. Overview R2 is an index builder, which indexes the content acquired in Overview R1. Overview R3 is the acquisition of the indexed information (index information) that has been indexed in Overview R2. Overview R4 is a dispatcher, which executes tasks based on user U's operations. For example, a task to answer a question received from user U is executed. Overview R5 is a prompt builder, which 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 that incentive information. Summary R6 is a generative AI model such as GPT, which generates answers to user U's questions based on prompts generated in Summary R5. The answers generated by Summary R6 are provided to user U via a dispatcher.

[2. Configuration of the Information Processing System]
The information processing system 1 shown in Figure 2 will now be described. As shown in Figure 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) by wired or wireless means. Figure 2 is a diagram showing an example configuration of the information processing system 1 according to an embodiment.

Terminal device 10 is an information processing device used by a user who asks a question. The user is, for example, a user who asks questions regarding the content of regulations, laws, rules, or manuals. For example, a user who asks, "What is the maximum accommodation expense limit in the company's accommodation regulations?" for business trips. The user inputs the question using, for example, a chat tool that allows text-based comment exchange. Terminal device 10 can be any device as long as it can realize the processing in this embodiment. Furthermore, terminal device 10 may be a smartphone, tablet, notebook PC, desktop PC, mobile phone, or PDA. Figure 4 shows the case where terminal device 10 is a smartphone.

The terminal device 10 is, for example, a smart device such as a smartphone or tablet, and is a portable terminal device capable of communicating with any server device via a wireless communication network such as 4G-5G (Generation) or LTE (Long Term Evolution). Furthermore, the terminal device 10 may have a screen such as a liquid crystal display with touch panel functionality, and may accept various operations on displayed data such as content from the user, such as tapping, sliding, and scrolling, using a finger or stylus. In Figure 4, the terminal device 10 is used by user U1.

The information processing device 100 is an information processing device intended to provide appropriate answers to user questions, and can be any device as long as it can realize the processing in the embodiment. The information processing device 100 performs two main types of processing. The first is processing before receiving a question from the user, which is processing to enable the provision of appropriate answers when a question is received from the user. The second is processing when a question is received from the user, which is processing to generate an answer to the user's question using the information from the first processing result. Specifically, in the first processing, the information processing device 100 generates information (hereinafter referred to as "index information" as appropriate) that summarizes content (such as regulations, laws, rules, and manuals) by chapter, article (clause), sentence, or main idea (a main idea with a predetermined meaning) for each predetermined unit (hereinafter referred to as "domain" in the embodiment). The generated index information is then used in the second processing. Furthermore, in the second processing, when the information processing device 100 receives a question from the user, it inputs the index information generated in the first processing into the generating AI to generate an answer to that question.

Here, we will describe the index information according to the embodiment. The Lama Index, etc., is used to generate the index information according to the embodiment. The Lama Index is a tool for generating context from a large amount of user data, and it is a tool that performs data retrieval by inputting questions received from the user and individual user data. In other words, the Lama Index accesses database information sources and assists in prompt generation. The index information is structured to organize and facilitate retrieval of data taken from such information sources. By using such index information, the information processing device 100 can efficiently access private information during prompt generation and generate context including private information. When the information processing device 100 receives a natural language question from the user, it uses the Lama Index, etc., to search for index information that matches the user's question and inputs it into the generating AI.

Generative AI is a text generation model that has been trained using data publicly available on the internet. For example, a GPT (Generative Pre-trained Transformer) model generates answers to questions. Such models generate answers to questions from publicly available internet data. Because new data is published daily on the internet, the model's answers are updated daily. This means that even if the same question is asked, the data the model references when generating the answer will differ depending on when the question is asked, resulting in different answers. Furthermore, because the model can provide detailed answers to questions across a wide range of fields, users ask the model a diverse variety of questions.

Note that while Figure 2 shows the terminal device 10 and the information processing device 100 as separate devices, the terminal device 10 and the information processing device 100 may be integrated into a single unit.

[3. An example of information processing]
Conventionally, technologies have been developed to make it easier for users to obtain the answers they want. For example, a technology is known for providing an internal chatbot system using internal company data (Patent Document 1 above). Also, for example, a technology is known for dividing regulations, manuals, etc., into predetermined units such as chapters and paragraphs and tagging them (Patent Document 2 above). However, conventional technologies, for example, process answers using natural language questions from users as they are, leaving room for further improvement in providing appropriate answers to user questions. This application has been made in view of the above, and aims to provide appropriate answers to user questions.

Below, two information processing steps are described as part of the information processing of the information processing system 1 according to the embodiment. As described above, the first information processing step (Embodiment 1) is for generating index information, and the second information processing step (Embodiment 2) is for generating answers to user questions. By combining the two information processing steps, it becomes possible to provide appropriate answers to user questions. In the first information processing step (Indexing Stage), the information processing device 100 organizes and indexes the data acquired from the data source, and in the second information processing step (Querying Stage), it analyzes the question entered by the user, extracts relevant information from the index, and generates the final response. By using this mechanism, Lama Index can efficiently manage large amounts of data, and users can quickly obtain the necessary information. This is particularly useful when a lot of information is scattered or when specific information needs to be retrieved quickly, significantly improving the efficiency of generating prompts to the generating AI and enabling the acquisition of better results.

(Embodiment 1: Information processing for generating index information)
Figure 3 shows an example of information processing in the information processing system 1 according to Embodiment 1. The information processing device 100 acquires content (Content A) that is the subject of a question from the user (step S101). The content in this embodiment is an example of terms and conditions, laws, rules, or manuals, but it can be any kind of content and is not particularly limited. The content in this embodiment may be converted into a document object such as a PDF. In the embodiment described later, an example is given where the content is a "travel expense agreement," but the content may also be a "service terms of use" which defines the rights and obligations of the service provider and the compliance matters of the user between the service provider and the user. In other words, information acquired from different databases may be converted into document objects. The document objects converted in this way may then be converted into more user-friendly nodes and indexed for efficient data access.

The information processing device 100 divides the acquired content into regions (region A1, region A2, region A3, ...) (step S102). For example, the information processing device 100 divides the content into regions such as chapters, articles, sentences, and main points. The size of the divided regions (the scope of region division) may be determined based on the context of the content. That is, the information processing device 100 may divide the content into regions according to the context of the content.

The information processing device 100 generates summaries (summary A1, summary A2, ...) for each divided area (step S103). Here, the generated summaries might be, for example, "Business trip expenses are capped at 5,000 yen per night." These generated summaries are then included in the index information.

The information processing device 100 generates index information (index F1, index F2, ...) by associating the generated summary with a label indicating the content from which the summary is derived (which may also be a label indicating the entire text) (step S104). The label (label B1, label B2, ...) is, for example, a label indicating what kind of regulations, laws, rules, or manuals they are. For example, in the case of content related to regulations, the label would be "Business Trip Expense Regulations," etc. In this case, the information processing device 100 may also generate index information by associating the summary with a label indicating the scope within the content from which the summary is derived (hereinafter referred to as "scope label" as appropriate). The scope label (scope label C1, scope label C2, ...) is, for example, a label indicating which chapter, article, sentence, etc., within the content the summary is derived from. For example, the scope label would be "Article 5," etc. Therefore, to give a concrete example, the information processing device 100 generates index information by linking summaries such as "Business trip expenses are capped at 5,000 yen per night," labels such as "Business Trip Expense Regulations," and scope labels such as "Article 5." Labels may indicate parent-child relationships with content, and scope labels may indicate parent-child relationships with content or labels.

Thus, in Embodiment 1, the information processing device 100 divides the content into areas, generates a summary for each divided area, assigns labels to the generated summaries, and uses them as index information. For example, the information processing device 100 assigns labels related to the regulations, such as "Business Trip Expense Regulations," and labels related to the articles, such as "Article 5," to a summary such as "Business trip expenses are capped at 5,000 yen per night."

(Embodiment 2: Information processing for generating answers to user questions)
Figure 4 shows an example of information processing of the information processing system 1 according to Embodiment 2. The information processing device 100 acquires information regarding a question P1 received from user U1 (step S201). In the following embodiment, the case in which the information processing device 100 acquires information regarding a question P1 from user U1, such as "What is the upper limit for accommodation expenses in the company's accommodation regulations?", will be explained as an example. In Embodiment 2, when a user's question is received, appropriate information corresponding to it is searched from the index information, related nodes are retrieved, the necessary information is selected and becomes part of the query to the generating AI. As a result, it becomes possible to efficiently extract highly relevant information from a large amount of data and to generate a natural language response to address the user's question.

The information processing device 100 determines, based on the acquired information, whether the question P1 received from user U1 is related to predetermined content (such as terms and conditions, laws, rules, or manuals) (step S202). For example, the information processing device 100 determines whether the question P1 received from user U1 is related to terms and conditions.

If the information processing device 100 determines that a question is related to predetermined content, it extracts index information from the index information generated in Embodiment 1 (i.e., index information summarizing predetermined content by area) that is highly relevant to user U1's question P1 (step S203). For example, the information processing device 100 identifies labels that are highly relevant to user U1's question P1 by comparing the labels associated with the index information with user U1's question P1, thereby extracting index information that is highly relevant to user U1's question P1. For example, if there are index information associated with the label "Business Trip Expense Regulations," index information associated with the label "Employment Regulations," and index information associated with the label "Childcare/Family Care Leave Regulations" as candidates, the information processing device 100 identifies the label "Business Trip Expense Regulations" that is highly relevant to question P1 such as "What is the upper limit for accommodation expenses in the company's accommodation regulations?", and extracts the index information associated with the label "Business Trip Expense Regulations." The information processing device 100 extracts index information associated with the "Business Trip Expense Regulations" label, enabling, for example, the acquisition of a summary of "Business trip expenses are capped at 5,000 yen per night" associated with the "Business Trip Expense Regulations" label, or the scope label of "Article 5" associated with the "Business Trip Expense Regulations" label. The information processing device 100 may also perform a process to extract highly relevant index information through, for example, a search based on the vector information of the index information.

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

In this embodiment 2, when the information processing device 100 receives a question P1 from user U1, it extracts highly relevant index information and generates a prompt for the text generation AI using a summary of the extracted index information. User U1, for example, enters question P1 on a bulletin board of a specific tool. For example, user U1 enters question P1 about the content of a predetermined content. When the information processing device 100 receives question P1 from user U1, it generates a prompt using the text generation AI, but in this case, it generates the prompt using a library in which the content is divided into areas and index information is generated for each area. 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 to generate an answer using the text data of the summary of the extracted index information. Also, for example, if there is no index information with a high relevance score, the information processing device 100 generates a prompt to generate an answer without using index information. In this case, for example, an answer to question P1 is generated without index information (summary, etc.). In this case, for example, the information processing device 100 generates an answer to question P1 by inputting a prompt to the text generation AI to generate an answer without using index information. The information processing device 100 may, for example, terminate information processing without generating a prompt to generate an answer if there is no index information with a high relevance score.

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

In the above embodiment, the information processing device 100 may perform processing to optimize the range (size of the area) of the area division according to the accuracy of the answer. In the example of the above embodiment, if user U1 evaluates the answer to question P1, such as "What is the upper limit for accommodation expenses in the company's accommodation regulations?", which is output as "It is 5,000 yen in the business trip expense regulations," the information processing device 100 may accept user U1's evaluation as the evaluation of that answer. In this way, the information processing device 100 may receive evaluations from (multiple) users, and if the evaluation is low, it may set multiple index information with changed area division ranges, and if changing to one of the multiple index information would improve the evaluation, it may change to the index information that yields the highest evaluation.

In the above embodiment, if a model answer (model response) such as a Q&A (or FAQ) is predetermined, the information processing device 100 may generate a prompt using the model answer. For example, the information processing device 100 may generate a prompt that instructs the system to output both the answer according to the above embodiment and the model answer. For example, the information processing device 100 may generate a prompt that outputs both an answer such as "According to the travel expense regulations, it is 5,000 yen" and a model answer such as "The model answer is as follows: ○×○×...".

In the above embodiment, the information processing device 100 may link to the generated responses. For example, the information processing device 100 may link the labels associated with the index information used to generate the responses to the corresponding content.

In the above embodiment, examples were given where the label is "Business Trip Expense Regulations," "Employment Regulations," or "Childcare/Family Care Leave Regulations," but the embodiment is not limited to these examples. The label in the embodiment may indicate a specific regulation, law, rule, or manual, but is not limited to these examples. Furthermore, in the above embodiment, an example was given where the scope label is "Article 5," but the embodiment is not limited to this example. The scope label in the embodiment may indicate a specific chapter, article, or sentence, but is not limited to these examples.

[4. Configuration of the terminal device]
Next, the configuration of the terminal device 10 according to the embodiment will be described using Figure 5. Figure 5 is a diagram showing an example of the configuration of the terminal device 10 according to the embodiment. As shown in Figure 5, the terminal device 10 has a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

(Communications Section 11)
The communication unit 11 is implemented, for example, by a NIC (Network Interface Card). The communication unit 11 is connected to a predetermined network N by wire or wireless connection and sends and receives information to and from the information processing device 100 via the predetermined network N.

(Input unit 12)
The input unit 12 accepts various operations from the user. In Figure 4, it accepts various operations from user U1. For example, the input unit 12 may accept various operations from the user via a display surface using a touch panel function. Alternatively, the input unit 12 may accept various operations from buttons provided on the terminal device 10, or from a keyboard or mouse connected to the terminal device 10. For example, the input unit 12 accepts an operation to input a question.

(Output section 13)
The output unit 13 is a display screen for a tablet terminal, for example, which is implemented using a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various types of information. For example, the output unit 13 displays information transmitted from the information processing device 100. For example, the output unit 13 displays the answer to a user question generated by the information processing device 100.

(Control unit 14)
The control unit 14 is, for example, a controller, and is implemented by a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs stored in the internal memory of the terminal device 10 using RAM (Random Access Memory) as the working area. For example, these various programs include application programs installed on the terminal device 10. For example, these various programs include application programs that display information transmitted from the information processing device 100 (such as answers to user questions). The control unit 14 is also implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

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

(Receiving unit 141)
The receiving unit 141 receives information transmitted from, for example, the information processing device 100. For example, the receiving unit 141 receives information related to the answer to the user's question. For example, the receiving unit 141 receives information for displaying the answer to the user's question.

(Transmitter 142)
The transmitting unit 142 transmits, for example, information about operations performed by the user. For example, the transmitting unit 142 transmits information about questions received from the user (for example, questions entered by the user, specified by the user, or selected by the user).

[5. Configuration of Information Processing Equipment]
Next, the configuration of the information processing device 100 according to the embodiment will be described with reference to Figure 6. Figure 6 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Figure 6, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130. The information processing device 100 may also have an input unit (for example, a keyboard or mouse) that receives various operations from the administrator of the information processing device 100, and a display unit (for example, a liquid crystal display) for displaying various information.

(Communications Department 110)
The communication unit 110 is implemented, for example, by a NIC. The communication unit 110 is connected to the network N by wire or wireless connection and sends and receives information to and from terminal devices 10, etc., via the network N.

(Storage unit 120)
The storage unit 120 is implemented by, for example, semiconductor memory elements such as RAM and flash memory, or storage devices such as hard disks and optical discs. As shown in Figure 6, the storage unit 120 has an index information storage unit 121 and a response evaluation information storage unit 122.

The index information storage unit 121 stores index information. Figure 7 shows an example of the index information storage unit 121 according to this embodiment. The information stored in the index information storage unit 121 is used, for example, to generate answers. As shown in Figure 7, the index information storage unit 121 has items such as "index information ID," "content ID," "label," "range label," and "summary."

The "Index Information ID" indicates the identification information used to identify the index information. The "Content ID" indicates the identification information used to identify the content. The "Label" indicates the label (a label indicating the content of the content). The "Scope Label" indicates the scope label (a label indicating a specific scope within the content). The "Summary" indicates the summary (a label indicating a summary corresponding to a specific scope within the content).

The response evaluation information storage unit 122 stores evaluation information for the responses. Figure 8 shows an example of the response evaluation information storage unit 122 according to this embodiment. The information stored in the response evaluation information storage unit 122 is used, for example, to optimize the range of area divisions. As shown in Figure 8, the response evaluation information storage unit 122 has items such as "index information ID" and "response evaluation information".

The "Index Information ID" indicates identification information used to identify the index information. The "Response Evaluation Information" indicates evaluation information for the response. In the example shown in Figure 8, conceptual information such as "Response Evaluation Information #1" and "Response Evaluation Information #2" are stored in "Response Evaluation Information," but in reality, a score indicating the overall evaluation by (multiple) users is stored.

(Control unit 130)
The control unit 130 is a controller, and is implemented, for example, by a CPU or MPU executing various programs stored in the memory device inside the information processing device 100 using RAM as the working area. Alternatively, the control unit 130 can be implemented by an integrated circuit such as an ASIC or FPGA.

As shown in Figure 6, the control unit 130 comprises 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 information processing operations described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in Figure 6; other configurations are also acceptable as long as they perform the information processing described later.

(Acquisition unit 131)
The acquisition unit 131 acquires various types of information from the storage unit 120. The acquisition unit 131 also stores the acquired information in the storage unit 120.

The acquisition unit 131 acquires various types of information from external information processing devices. The acquisition unit 131 also acquires various types of information from other information processing devices, such as the terminal device 10.

The acquisition unit 131 acquires, for example, the content that is the subject of a user's question. For example, the acquisition unit 131 acquires the text data of the content (for example, the entire document). Furthermore, when the acquisition unit 131 receives a question from a user, it acquires the user's question (the question text, etc.).

(Division part 132)
The division unit 132 divides the content acquired by the acquisition unit 131, for example. For example, the division unit 132 divides the content acquired by the acquisition unit 131 into contextually appropriate regions (for example, regions for each chapter, each article, each sentence, etc.). The division unit 132 divides the content into one or more (or more) regions in this way, for example.

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

(Second generation unit 134)
The second generation unit 134 generates index information that links, for example, the summary generated by the first generation unit 133 with a label corresponding to the content from which the summary was compiled. The second generation unit 134 also generates index information that links, for example, the summary generated by the first generation unit 133 with a label corresponding to the content from which the summary was compiled and a range label corresponding to a range within the content from which the summary was compiled (the range corresponding to the summary generated by the first generation unit 133).

The index information generated in this way is used to generate prompts for creating answers when a user submits a question. Furthermore, this index information is used to extract index information highly relevant to the question when a user submits a question.

(Determination unit 135)
The determination unit 135 determines, for example, whether a question acquired by the acquisition unit 131 is related to a predetermined content. For example, the determination unit 135 determines whether a question is related to any of the following: terms and conditions, laws, rules, or manuals. Alternatively, for example, the determination unit 135 determines whether a question is related to specific terms and conditions, laws, rules, or manuals.

(Extraction unit 136)
If the extraction unit 136 determines, for example, that a question is related to a predetermined content, it extracts index information from the index information that is highly relevant to the question. In this case, the extraction unit 136 calculates a score indicating the degree of relevance to the question for each piece of index information, and extracts index information whose score is above a predetermined threshold. If, for example, there is no index information whose score is above a predetermined threshold (i.e., there is no highly relevant index information), the extraction unit 136 does not extract any index information.

(Third generation unit 137)
The third generation unit 137 generates answers to questions received from the 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 answers to questions received from the user, and the answer output by inputting that prompt into the text generation AI is used as the answer to the question received from the user.

The third generation unit 137 generates an answer to a user-submitted question without using index information, for example, if the extraction unit 136 fails to extract index information. For instance, the third generation unit 137 generates a prompt for generating an answer to a user-submitted question without using index information, and then inputs this prompt into the text generation AI. The resulting output is then used as the answer to the user-submitted question.

The third generation unit 137, for example, if the determination unit 135 determines that the question is not related to a predetermined content, generates an answer to the question received from the user without using index information, similar to the case where the extraction unit 136 did not extract index information.

(Providing unit 138)
The providing unit 138 provides, for example, information regarding the answer generated by the third generation unit 137 to the user who asked the question. For example, the providing unit 138 transmits content showing the answer generated by the third generation unit 137 to the terminal device 10. Also, for example, the providing unit 138 transmits information to the terminal device 10 for displaying the content showing the answer generated by the third generation unit 137.

[6. Information Processing Flow]
Next, the information processing procedure by the information processing system 1 according to the embodiment will be described using Figures 9 and 10. Figures 9 and 10 are flowcharts showing the information processing procedure by the information processing system 1 according to the embodiments (Embodiment 1 and Embodiment 2).

As shown in Figure 9 (Embodiment 1), the information processing device 100 acquires the content to be learned (step S301).

The information processing device 100 divides the acquired content into context-appropriate regions (step S302).

The information processing device 100 generates a summary for each divided region (step S303).

The information processing device 100 generates index information corresponding to the generated summary (step S304).

As shown in Figure 10 (Embodiment 2), the information processing device 100 acquires a question received from the user (step S401).

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

If the information processing device 100 determines that the question is related to a predetermined content (step S402; YES), it determines whether there is any index information among the index information summarizing the predetermined content by area that is highly relevant to the question (step S403).

If the information processing device 100 determines that there is index information highly relevant to the question (step S403; YES), it extracts the index information highly relevant to the question (step S404). Then, the information processing device 100 generates an answer to the question from the extracted index information (step S405).

On the other hand, if the information processing device 100 determines that the question is not related to the predetermined content (step S402; NO), or if it determines that there is no index information highly relevant to the question (step S403; NO), it generates an answer to the question without extracting index information (step S406).

[7. Effects]
As described above, the information processing device 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 related to predetermined content. If the determination unit 135 determines that the question is related to predetermined content, the extraction unit 136 extracts index information that is highly relevant to the question from the index information which summarizes the predetermined content by area. The third generation unit 137 generates an answer to the question from the index information extracted by the extraction unit 136.

As a result, the information processing device 100 according to this embodiment can, for example, generate an appropriate answer to the user's question by converting the user's natural language question into easily manageable information, rather than using it directly.

Furthermore, the third generation unit 137 generates a prompt for generating an answer to a question, which is then input to the text generation AI.

This allows the information processing device 100 according to the embodiment to significantly improve the efficiency of generating prompts for the generated AI, for example.

Furthermore, if the third generation unit 137 cannot extract index information highly relevant to the question, it generates the answer without using the index information.

As a result, the information processing device 100 according to this embodiment can generate appropriate answers to user questions by, for example, preventing noise from being introduced when the information is not highly relevant to the question.

Furthermore, if the determination unit 135 determines that the question is not related to the predetermined content, the third generation unit 137 generates an answer without using index information.

This allows the information processing device 100 according to the embodiment to generate appropriate answers to user questions by, for example, preventing noise from being introduced when the question is not related to a predetermined content.

Furthermore, the specified content is the terms and conditions.

This allows the information processing device 100 according to the embodiment to generate, for example, an appropriate response regarding the regulations.

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

The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, controlling various components. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs dependent on the computer 1000's hardware.

The HDD 1400 stores programs executed by the CPU 1100, as well as data used by such programs. The communication interface 1500 acquires data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input/output interface 1600. The CPU 1100 acquires data from input devices via the input/output interface 1600. Furthermore, the CPU 1100 outputs the generated data to output devices via the input/output interface 1600.

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

For example, when the computer 1000 functions as an information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded onto the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a predetermined communication network.

[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 by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those illustrated; all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

Furthermore, the embodiments described above can be combined as appropriate, provided that the processing content is not contradictory.

Although several embodiments of this application have been described in detail based on the drawings, these are illustrative examples, and the present invention can be implemented in various modified and improved forms based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

Furthermore, the terms "section," "module," and "unit" mentioned above can be replaced with "means" or "circuits." For example, the acquisition unit can be replaced with acquisition means or acquisition circuit.

1 Information Processing System 10 Terminal Device 11 Communication Unit 12 Input Unit 13 Output Unit 14 Control Unit 100 Information Processing Device 110 Communication Unit 120 Storage Unit 121 Index Information Storage Unit 122 Response Evaluation Information Storage Unit 130 Control Unit 131 Acquisition Unit 132 Division Unit 133 First Generation Unit 134 Second Generation Unit 135 Judgment Unit 136 Extraction Unit 137 Third Generation Unit 138 Provision Unit 141 Receiving Unit 142 Transmitting Unit N Network

Claims (7)

A determination unit that determines whether a question received from a user is related to a specified content,
If the determination unit determines that the question is related to predetermined content, the extraction unit extracts index information that is highly relevant to the question from the index information which summarizes the predetermined content by area,
A generation unit generates an answer to the question from the index information extracted by the extraction unit,
It has,
The information processing device is characterized in that each of the aforementioned regions is a region division range according to the context of the predetermined content, and is a region divided based on a region division range that has been modified so that the user's evaluation of the answer generated from any of the multiple index information is higher . The generating unit is
The information processing device according to claim 1, characterized in that it generates a prompt for generating an answer to the aforementioned question, which is to be input to a text generation AI. The generating unit is
The information processing device according to claim 1, characterized in that, if it is not possible to extract index information that is highly relevant to the aforementioned question, it generates the answer without using the index information. The generating unit is
The information processing device according to claim 1, characterized in that if the determination unit determines that the question is not related to a predetermined content, it generates the answer without using index information. The information processing device according to claim 1, characterized in that the aforementioned predetermined content is a set of terms and conditions. A method of information processing performed by a computer,
A determination step to determine whether a question received from a user is related to a specified content,
If the determination step determines that the question is related to predetermined content, the extraction step involves extracting index information that is highly relevant to the question from the index information which summarizes the predetermined content by area.
A generation step that generates an answer to the question from the index information extracted by the extraction step,
Includes,
The information processing method is characterized in that each of the aforementioned regions is a region division range according to the context of the predetermined content , and is a region divided based on a region division range that has been modified so that the user's evaluation of the answer generated from any of the multiple index information is higher . A determination procedure for determining whether a question received from a user is related to a specified content,
If the determination procedure determines that the question is related to a predetermined content, an extraction procedure is performed to extract index information that is highly relevant to the question from the index information which summarizes the predetermined content by area,
A generation procedure for generating answers to the questions from the index information extracted by the extraction procedure,
Have the computer run it,
An information processing program characterized in that each of the aforementioned regions is a region division range according to the context of the predetermined content, and is a region divided based on a region division range that has been modified so that the user's evaluation of the answer generated from any of the multiple index information is higher .