Information processing method, information processing device, and computer program

Abstract

To provide an information processing method, an information processing device, and a computer program for outputting an answer text in which ideas of a specific person is reflected, to a query from a user.SOLUTION: In an AI chat system, an AI server 10 quantifies a sentence included in a received query to be compared with book data registered in a book database DB, to extract one or more pieces of book data having high similarity to the query from the book database DB. The AI server generates, based on the book data extracted from the book database BN, data to be input to a large language model (LLM) server 20, transmits a prompt generated based on the book data to the LLM server 20, acquires an answer text, as a response, generated by the LLM, and transmits the answer text to a user terminal 30. The user terminal 30 receives the answer text from the AI server 10 and displays, on a display unit, the received answer text.SELECTED DRAWING: Figure 8

Description

[Technical field]

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

[0002] Conventionally, systems have been provided that perform natural language processing such as question-and-answering using a language model (see, for example, Patent Document 1). The language model is a natural language processing model trained using a large amount of text data, and is configured to receive a sentence as input and output a sentence. When applied to a question-and-answering system, the language model is trained to output an answer sentence in response to an input question sentence. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional language models only output general answers to user questions, and are unable to reflect the thoughts of a specific person in the answer.

[0005] In one aspect, an object of the present invention is to provide an information processing method, an information processing device, and a computer program capable of outputting a response to a user's question that reflects the thoughts of a specific person. [Means for solving the problem]

[0006] The information processing method disclosed herein includes a process of acquiring a user's query, and outputting a response sentence to the acquired query by a language model using book data, by a computer. Effect of the Invention

[0007] In one aspect, answers to user questions can be output that reflect the thoughts of a particular person. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic diagram showing a configuration example of an AI chat system according to an embodiment. [Diagram 2] FIG. 2 is a block diagram showing the internal configuration of the AI ​​server. [Diagram 3] FIG. 1 is a conceptual diagram illustrating an example of a book database. [Figure 4] FIG. 2 is a block diagram showing the internal configuration of an LLM server. [Diagram 5] FIG. 2 is a block diagram showing the internal configuration of a user terminal. [Figure 6] This is an explanatory diagram that explains the outline of processing in the AI ​​chat system. [Figure 7] This is an explanatory diagram that explains the outline of processing in the AI ​​chat system. [Figure 8] 1 is a flowchart illustrating the processing steps performed by the AI ​​chat system. [Figure 9] 1 is a schematic diagram showing an example of a user interface screen provided by an AI server. [Figure 10] This is a conceptual diagram illustrating an example of a prompt generated by an AI server. [Figure 11] FIG. 13 is a schematic diagram showing an example of an output of a reply sentence to a user's query. [Figure 12] FIG. 13 is a conceptual diagram illustrating an example of a prompt that takes into consideration the attributes of a questioner (user) and a respondent. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The present invention will now be described in detail with reference to the drawings showing embodiments thereof. (Embodiment 1) FIG. 1 is a schematic diagram showing an example of the configuration of an AI chat system according to an embodiment. The AI ​​chat system according to this embodiment includes an AI server 10, an LLM server 20, and a user terminal 30. The AI ​​server 10, the LLM server 20, and the user terminal 30 are communicatively connected to each other via a communication network NW such as the Internet. The AI ​​server 10 is a server computer that provides chat services to users. The LLM server 20 is a server computer that provides services using a large-scale language model (LLM: Large Language Model, hereinafter referred to as LLM). The user terminal 30 is a client computer used by a user.

[0010] The AI ​​server 10 includes a book database DB that stores texts included in books. In this embodiment, a book may be any text that includes texts, and may include not only printed and bound publications, but also e-books, magazines, comics, company histories, and draft manuscripts that were not adopted in books. In this embodiment, text data included in a book is converted into data that is easy to handle in a computer system (for example, numerical data such as vector data) and registered in the book database DB. Text data registered in the book database DB is hereinafter referred to as book data. Book data is classified by book, by author, and by expert and registered in the book database DB. In this embodiment, a group of authors classified into appropriate categories is referred to as an expert. Experts include managers, entrepreneurs, investors, politicians, critics, thinkers, artists, researchers, persons with professional or teacher qualifications (lawyers, tax accountants, patent attorneys, doctors, nurses, teachers, etc.), professional athletes, and sports instructors. In this embodiment, an expert may be a group of one or more authors, and the authors included in the group do not necessarily have to have a common specialty. In addition, the book data registered in the book database DB is not limited to text extracted from books, but may also be data on text contained in content made public by authors on the communications network NW (such as articles posted on social media or blogs).

[0011] The AI ​​server 10 provides a chat service to a user by using book data registered in the book database DB. Specifically, the AI ​​server 10 accepts a user's query through the user terminal 30, extracts book data related to the accepted query from the book database DB, and generates input data for the LLM by using the extracted book data. The input data for the LLM is also called a prompt. The AI ​​server 10 transmits the generated prompt to the LLM server 20, and receives an answer sentence returned from the LLM server 20 as a response to the prompt. The AI ​​server 10 outputs the answer sentence received from the LLM server 20 as a response to the user's query.

[0012] Below, we will explain the configuration of each device that makes up the AI ​​chat system.

[0013] 2 is a block diagram showing the internal configuration of the AI ​​server 10. The AI ​​server 10 is a dedicated or general-purpose server computer, and includes a control unit 11, a storage unit 12, a communication unit 13, an operation unit 14, and a display unit 15.

[0014] The control unit 11 includes, for example, a central processing unit (CPU), a read only memory (ROM), and a random access memory (RAM). The ROM included in the control unit 11 stores a control program that controls the operation of each hardware part included in the AI ​​server 10. The CPU in the control unit 11 reads and executes the control program stored in the ROM and a computer program (described below) stored in the memory unit 12, and controls the operation of each hardware part, thereby causing the entire device to function as the information processing device of the present disclosure. The RAM included in the control unit 11 temporarily stores data used during the execution of calculations and control.

[0015] In the embodiment, the control unit 11 is configured to include a CPU, a ROM, and a RAM, but the configuration of the control unit 11 is not limited to the above. The control unit 11 may be, for example, one or more control circuits or arithmetic circuits including a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), a quantum processor, a volatile or non-volatile memory, etc. The control unit 11 may also include functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when a measurement start instruction is given to when a measurement end instruction is given, and a counter that counts numbers.

[0016] The storage unit 12 includes a storage device such as a hard disk drive (HDD), a solid state drive (SSD), etc. In the storage unit 12, various computer programs executed by the control unit 11 and various data used by the control unit 11 are stored.

[0017] The computer program (program product) stored in the storage unit 12 includes a chat generation program PG for causing a computer to execute a process of acquiring a user's query and outputting a response sentence to the acquired query by a language model using book data. The chat generation program PG may be a single computer program or a group of programs consisting of multiple computer programs. The chat generation program PG may be executed by multiple computers in cooperation. The chat generation program PG may also partially use an existing library.

[0018] A computer program including the chat generation program PG is provided by a non-transitory recording medium RM on which the computer program is readably recorded. The recording medium RM is a portable memory such as a CD-ROM, a USB memory, a Secure Digital (SD) card, a micro SD card, or a Compact Flash (registered trademark). The control unit 11 reads various computer programs from the recording medium RM using a reading device not shown in the figure, and stores the various computer programs thus read in the storage unit 12. The computer program including the chat generation program PG may be provided by communication. In this case, the control unit 11 acquires the computer program including the chat generation program PG by communication via the communication unit 13, and stores the acquired computer program in the storage unit 12.

[0019] The AI ​​server 10 has the book database DB described above in the storage unit 12. FIG. 3 is a conceptual diagram showing an example of the book database DB. The book database DB stores author IDs, group IDs, book IDs, and book data in association with each other. The author ID is an identifier for identifying the author. The group ID is an identifier for identifying the group (expert) to which the author belongs. One or more group IDs are assigned to each author. Some authors may not be assigned a group ID. The book ID is an identifier for identifying a book by the author. Some authors may have multiple book IDs registered. The book data represents data obtained by quantifying sentences included in a book. Existing methods are used to quantify sentences. For example, sentences are quantified by dividing the sentences into words (morphemes), counting the number of occurrences of each word for each sentence, and generating a vector whose length is the number of vocabulary words. The quantification may be performed on a sentence-by-sentence basis, or may be performed on a sentence-by-sentence basis. In this embodiment, book data is a term that represents a collection of numerical data obtained from one book, but individual sentences or numerical data corresponding to sentences are also referred to as book data without distinction from the above. The control unit 11 of the AI ​​server 10 can use the book database DB to calculate the similarity between a query received from a user and a sentence contained in a book.

[0020] In this embodiment, a book ID is assigned to each book, but a book ID may be assigned to each chapter within a book, or a book ID may be assigned to a portion of a sentence in a book.

[0021] In addition, in the present embodiment, the book data extracted from the book is registered in association with the author ID. However, data extracted from the text included in the content (such as articles posted on SNS or blogs) that the author has made public on the communication network NW may be registered in association with the author ID. In this case, for example, text data may be acquired from the SNS or blog of the author that is set in advance, and the identifier for identifying the author may be registered as the author ID, the identifier for identifying the SNS or blog of the author may be registered as the book ID, and the numerical data converted from the acquired text may be registered as book data in the book database DB. In this way, by registering the text acquired from the SNS or blog in the book database DB, the expression of the author on the SNS or blog can be handled in the same way as the book data extracted from the book. Note that only a part of the text included in the content may be registered in the book database DB as book data, or the entire text may be registered in the book database DB as book data. Note that the text included in the content may be summarized and registered in the book database DB, or may be translated and registered in the book database DB.

[0022] The communication unit 13 includes a communication interface for transmitting and receiving various data to and from an external device. As the communication interface of the communication unit 13, a communication interface conforming to a communication standard such as WiFi (registered trademark), LAN (Local Area Network), Bluetooth (registered trademark), ZigBee (registered trademark), 3G, 4G, 5G, or LTE (Long Term Evolution) can be used. When data to be transmitted is input from the control unit 11, the communication unit 13 transmits the data to a destination external device, and when data transmitted from an external device is received, the communication unit 13 outputs the received data to the control unit 11. In this embodiment, an example of an external device is a user terminal 30.

[0023] The operation unit 14 includes operation devices such as a touch panel, a keyboard, and switches, and receives various operations and settings from an administrator, etc. The control unit 11 performs appropriate control based on various operation information provided by the operation unit 14, and stores setting information in the storage unit 12 as necessary.

[0024] The display unit 15 includes a display device such as a liquid crystal display or an organic EL (Electro-Luminescence) display, and displays information to be presented in response to an instruction from the control unit 11.

[0025] In this embodiment, the AI ​​server 10 may be a single computer, or a computer system made up of multiple computers and peripheral devices, etc. The AI ​​server 10 may also be a virtual machine whose entity has been virtualized, or may be a cloud.

[0026] 4 is a block diagram showing the internal configuration of the LLM server 20. The LLM server 20 is a dedicated or general-purpose server computer, and includes a control unit 21, a storage unit 22, a communication unit 23, an operation unit 24, and a display unit 25.

[0027] The control unit 21 includes, for example, a CPU, a ROM, a RAM, etc. The CPU of the control unit 21 loads various programs stored in advance in the ROM or the storage unit 22 into the RAM and executes them to control the operation of the various hardware components described above.

[0028] In the embodiment, the control unit 21 is configured to include a CPU, a ROM, and a RAM, but the configuration of the control unit 21 is not limited to the above. The control unit 21 may be one or more control circuits or arithmetic circuits including a GPU, an FPGA, a DSP, a quantum processor, a volatile or non-volatile memory, or the like.

[0029] The storage unit 22 includes storage such as a memory and a hard disk. The storage unit 22 stores various computer programs executed by the control unit 21, data necessary for executing the computer programs, and the like. The computer programs stored in the storage unit 22 include a natural language processing program for causing a computer to execute a process of interpreting a prompt received from the outside and generating a sentence using an LLM.

[0030] The storage unit 22 also includes an LLM such as GPT-3 (Generative Pretrained Transformer 3), LaMDA (Language Model for Dialogue Applications), PaLM (Pathways Language Model), LLaMA (Large Language Model Meta AI), Weblab-10B, etc. The LLM included in the LLM server 20 is not limited to the above, and may be any existing model or a model obtained by tuning an existing model.

[0031] The communication unit 23 includes a communication interface for connecting to the communication network NW. The communication interface included in the communication unit 23 is, for example, a communication interface conforming to a communication standard such as WiFi (registered trademark), LAN, Bluetooth (registered trademark), ZigBee (registered trademark), 3G, 4G, 5G, LTE, etc. The communication unit 23 transmits various information to be notified to the outside, and receives various information transmitted from the outside to the device itself.

[0032] The operation unit 24 is equipped with input devices such as a touch panel and operation buttons, and receives various types of operation information and setting information. The operation unit 24 outputs the received operation information and setting information to the control unit 21. The control unit 21 performs appropriate control based on the operation information input from the operation unit 24, and stores the setting information in the storage unit 22 as necessary.

[0033] The display unit 25 includes a display device such as a liquid crystal display or an organic EL display, and displays information to be presented to the manager or the like based on a control signal output from the control unit 21.

[0034] In this embodiment, the AI ​​server 10 and the LLM server 20 are separate entities, but they may be integrated. That is, the AI ​​server 10 may be configured to include an LLM. In this case, the AI ​​server 10 may generate a prompt based on a query received from the user terminal 30, generate an answer sentence based on the generated prompt inside the AI ​​server 10, and output it to the user terminal 30.

[0035] 5 is a block diagram showing the internal configuration of the user terminal 30. The user terminal 30 is a computer such as a smartphone, a tablet terminal, or a personal computer, and includes a control unit 31, a storage unit 32, a communication unit 33, an operation unit , and a display unit .

[0036] The control unit 31 includes, for example, a CPU, a ROM, a RAM, etc. The CPU of the control unit 31 expands various programs stored in advance in the ROM or the storage unit 32 into the RAM and executes them, thereby controlling the operation of the various hardware described above and causing the entire device to function as the user terminal 30 in the present disclosure.

[0037] The control unit 31 is not limited to the above configuration, and may be configured as a single piece of hardware (SoC: System On a Chip) that integrates a processor, memory, storage, communication interface, etc. The control unit 31 may also have functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when a measurement start instruction is given to when a measurement end instruction is given, and a counter that counts numbers.

[0038] The storage unit 32 includes storage such as a memory and a hard disk. The storage unit 32 stores various computer programs executed by the control unit 31, and data necessary for executing the computer programs. The computer programs stored in the storage unit 32 include application programs for using the services provided by the AI ​​server 10.

[0039] The programs stored in the storage unit 32 may be provided by a non-transitory recording medium on which the programs are readably recorded. The recording medium is, for example, a portable memory such as a CD-ROM, a USB memory, or an SD card. The control unit 31 reads the various programs from the recording medium using a reading device (not shown), and installs the read various programs in the storage unit 32. The programs stored in the storage unit 32 may also be provided by communication. In this case, the control unit 31 acquires the various programs through the communication unit 33, and installs the acquired various programs in the storage unit 32.

[0040] The communication unit 33 includes a communication interface for connecting to the communication network NW. The communication interface included in the communication unit 33 is, for example, a communication interface conforming to a communication standard such as WiFi (registered trademark), LAN, Bluetooth (registered trademark), ZigBee (registered trademark), 3G, 4G, 5G, LTE, etc. The communication unit 33 transmits various information to be notified to the outside, and receives various information transmitted from the outside to the device itself.

[0041] The operation unit 34 is equipped with input devices such as a touch panel and operation buttons, and receives various types of operation information and setting information. The operation unit 34 outputs the received operation information and setting information to the control unit 31. The control unit 31 performs appropriate control based on the operation information input from the operation unit 34, and stores the setting information in the storage unit 32 as necessary.

[0042] The display unit 35 includes a display device such as a liquid crystal display or an organic EL display, and displays information to be presented to the user based on a control signal output from the control unit 31.

[0043] Below, we will explain an overview of the processing in the AI ​​chat system. 6 and 7 are explanatory diagrams outlining the processing in the AI ​​chat system. FIG. 6 shows an overview of the processing in the preparation stage before the service starts, and FIG. 7 shows an overview of the processing after the service starts. In the preparation stage before the service starts, the AI ​​server 10 extracts book data from books and registers the extracted book data in the book database DB. This registration processing is also executed at any time after the service starts.

[0044] When the AI ​​server 10 acquires a book to be registered, it converts the sentences contained in the book into digital text data using, for example, OCR (Optical Character Recognition) technology, and converts the text data into book data (numeric data) using an existing digitization method. The AI ​​server 10 associates the book data extracted from one book with an author ID, a group ID, and a book ID, and registers them in the book database DB. The AI ​​server 10 performs such registration processing in the book database DB at any time.

[0045] For example, if a book contains the sentence "...the group's philosophy, 'It is the heart that matters,' is something my teacher taught me when I was a student...", the AI ​​server 10 calculates numerical data (vector data) such as [12.345, 67.890, ...], [33.444, 55.666, ...], ... from the text data of the sentence, and registers the obtained numerical data (book data) in the book database DB together with the author ID, group ID, and book ID.

[0046] The AI ​​server 10 starts providing services when the registration process to the book database DB has progressed, and accepts a user query from the user terminal 30. The AI ​​server 10 quantifies the sentences included in the accepted query and compares them with the book data registered in the book database DB to extract one or more book data items that are highly similar to the query from the book database DB. A known method such as cosine similarity is used to calculate the similarity. Cosine similarity is an index that indicates the degree to which vectors are oriented in the same direction, and takes a real value ranging from -1 to +1 depending on the level of similarity.

[0047] For example, when a query such as "Q: What is 'The heart is what matters?'" is input from the user terminal 30, the AI ​​server 10 digitizes a sentence included in the query (for example, "The heart is what matters," which is the main part of the query), and searches the book database DB based on the resulting numerical data ([12.333, 67.888, ...] in the example of FIG. 7), thereby extracting book data with high similarity. At this time, the AI ​​server 10 extracts one or more book data with a similarity higher than a threshold value from the book database DB. Alternatively, the AI ​​server 10 may extract only the book data with the highest similarity, or may extract a predetermined number of book data (for example, three) in descending order of similarity.

[0048] The AI ​​server 10 generates input data for the LLM based on the book data extracted from the book database DB. The input data is a prompt that includes a user's query as an instruction to the LLM and embeds book data extracted from the book database DB as reference information to be referred to when generating an answer sentence.

[0049] In the example of Figure 7, the instruction to the LLM (#question) includes the sentence "What does it mean that the heart is what matters? Please answer by referring to the reference information." The first half is a sentence that corresponds to the user's query, and the second half is a predetermined fixed phrase. The reference information (#data) is embedded with the book ID, book data extracted from the book database DB, and the similarity between the query and the book data. In the example of Figure 7, "id" represents the book ID, "text" represents the book data extracted from the book database DB, and "score" represents the similarity between the query and the book data.

[0050] The AI ​​server 10 transmits a prompt generated based on the book data to the LLM server 20, and receives an answer text by the LLM in response. The AI ​​server 10 transmits the received answer text by the LLM to the user terminal 30. The user terminal 30 receives the answer text from the AI ​​server 10, and displays the received answer text on the display unit 35.

[0051] The operation of the AI ​​chat system will be explained below. 8 is a flowchart explaining the procedure of the process executed by the AI ​​chat system. The user terminal 30 accesses the AI ​​server 10 through a dedicated application or a web browser (step S101). After user authentication, the user terminal 30 displays a user interface screen (UI screen) provided by the AI ​​server 10 on the display unit 35 (step S102).

[0052] FIG. 9 is a schematic diagram showing an example of a user interface screen provided by the AI ​​server 10. The user interface screen 100 shown in FIG. 9 includes a chat display field 101 for displaying a dialogue (chat) between a user and the system, a model selection field 102 for accepting a selection of an AI model, and a chat input field 103 for accepting a user's chat. The chat display field 101 displays a user's chat inputted into the chat input field 103 via the operation unit 34 and a system chat generated by the AI ​​server 10. The model selection field 102 displays a selection of a plurality of AI models in a pull-down menu format and accepts the selection of a desired AI model from among the displayed selections. In the embodiment, the AI ​​model (answer model) is configured to be able to select at least one of an author model that simulates an answer by a specific author, an expert model that simulates an answer by a specific expert, and a book model that simulates an answer by a specific book. That is, in the present embodiment, the AI ​​model (answer model) is a term that represents a selection for selecting an author, an expert, and a book, and does not represent a machine learning model that outputs some output data when input data is input. Each of the author model, the expert model, and the book model includes a plurality of options. The model selection field 102 and the chat input field 103 receive a selection operation and an input operation via the operation unit 34 of the user terminal 30.

[0053] For example, when an AI model (one of the author models) whose author is Mr. A is selected in the model selection field 102, the AI ​​server 10 generates a system chat in which Mr. A responds to the user's chat input, and displays it in the chat display field 101. When an AI model (one of the expert models) whose manager is selected in the model selection field 102, the AI ​​server 10 generates a system chat in which the manager responds to the user's chat input, and displays it in the chat display field 101. When an AI model (one of the book models) whose book is Book α is selected in the model selection field 102, the AI ​​server 10 generates a system chat in which the book α (or the author of Book α) responds to the user's chat input, and displays it in the chat display field 101.

[0054] In this embodiment, a selection of multiple AI models is displayed in the model selection field 102 and a selection by the user is accepted. Alternatively, an AI model may be automatically specified according to the user. For example, AI models of managers of various companies (users) may be prepared for each company, and the AI ​​server 10 may determine access from a company and automatically specify the AI ​​model of the manager of the company as the AI ​​model to be used by the company. In this case, only the model name of one AI model specified by the AI ​​server 10 is displayed in the model selection field 102. Alternatively, the user terminal 30 may display a user interface screen 100 that does not include the model selection field 102 on the display unit 35.

[0055] In step S102 described above, the user terminal 30 displays a user interface screen 100 as shown in FIG. 9 on the display unit 35, and accepts the selection of an AI model from the model selection field 102 (step S103). The user terminal 30 notifies the AI ​​server 10 of the identifier of the selected AI model (step S104). Among the AI ​​models, each author model is linked to an author ID, each expert model is linked to a group ID, and each book model is linked to a book ID, so the user terminal 30 may notify the AI ​​server 10 of the author ID, group ID, or book ID as the identifier of the selected AI model. In this embodiment, the selection of an AI model is not essential and may be omitted.

[0056] The user terminal 30 accepts a user query through the chat input field 103 of the user interface screen 100 (step S105). The query is input as a sentence such as "What is it that the heart is important?" Before accepting the user query, the system may inquire about the user's attributes (such as name, gender, age, etc.) and the user's current state (such as emotions and interests) through speech. Some of the user's attributes (such as name, gender, age, etc.) may be registered in advance in the storage unit 12 of the AI ​​server 10. In the latter case, the user's attributes can be read out from the storage unit 12 during login authentication to the AI ​​server 10.

[0057] The user terminal 30 transmits the query received in step S105 to the AI ​​server 10 (step S106). The query transmitted from the communication unit 33 of the user terminal 30 reaches the AI ​​server 10 via the communication network NW.

[0058] The AI ​​server 10 receives a query sent from the user terminal 30 (step S107). The control unit 11 of the AI ​​server 10 searches the book database DB based on the received query, and extracts book data corresponding to the query from the book database DB (step S108). Specifically, the control unit 11 converts the query (or the main part of the query) into a numerical value using a predetermined method, calculates the similarity with the book data registered in the book database DB, and extracts book data with a relatively high similarity from the book database DB. In addition, if text (numerical data) obtained from an author's SNS or blog is registered in the book database DB, the control unit 11 may calculate the similarity between the calculated numerical value from the query and the numerical data of the text obtained from the SNS or blog, and extract the text from the SNS or blog with a relatively high similarity from the book database DB.

[0059] In addition, when an AI model is selected in the user terminal 30 and its identifier is notified, the search range of the book database DB is limited by the identifiers of the AI ​​model (author ID, group ID, book ID). For example, when an author model is selected, the author is identified by the identifier (author ID) of the author model, so the search range can be book data related to the author identified by the author ID. In addition, when an expert model is specified, one or more authors are identified by the identifier (group ID) of the expert model, so the search range can be book data related to one or more authors identified by the group ID. Furthermore, when a book model is specified, a book is identified by the identifier (book ID) of the book model, so the search range can be book data of the book identified by the book ID.

[0060] The control unit 11 generates input data for the LLM based on the book data extracted from the book database DB (step S109). The control unit 11 generates a prompt as input data for the LLM, which includes a sentence for the user's query in an instruction to the LLM and includes the book data extracted from the book database DB in reference information. The reference information may include not only the book data with the highest similarity, but also multiple book data with relatively high similarity. The reference information may also include a book ID and information on the similarity between the query and the book data.

[0061] FIG. 10 is a conceptual diagram for explaining an example of a prompt generated by the AI ​​server 10. The prompt includes an instruction to the LLM and reference information to be referred to by the LLM. In the prompt shown in FIG. 10, the instruction to the LLM is described in a sentence in the "#question" part, and the reference information to be referred to by the LLM is described in a sentence in the "#data" part. The instruction to the LLM includes a user's query and a standard phrase to answer by referring to the reference information. The reference information includes a book ID, book data extracted from the book database DB, and a similarity between the query and the book data. In this embodiment, since the book data is numerical data, the numerical data is converted to the original text data (sentence) and then embedded in the reference information. For this reason, it is preferable that the book data registered in the book database DB is numerically converted using a reversible numerical conversion method. Alternatively, a database may be provided separately for storing the book data (numerical data) registered in the book database DB in association with the original text data, and the database may be referred to to convert the data to the original text data. The format of the prompt shown in FIG. 10 is an example, and the actual format may be appropriately designed according to the LLM.

[0062] In the example of FIG. 10, the book data extracted from the book database DB is embedded in the reference information of the prompt, but the control unit 11 may store a series of dialogues as a history in the storage unit 12 and add the dialogues to the reference information of the prompt. That is, the control unit 11 may register the data of the user's query as book data in the book database DB, and add it to the prompt as reference information when generating an answer later. The control unit 11 may also register the data of the generated answer as book data in the book database DB, and add it to the prompt as reference information when generating an answer later. Furthermore, the control unit 11 may store the data of the user's query in association with the user's identifier, and extract information on the user's emotion, behavior, or state based on the content of the stored query.

[0063] The AI ​​server 10 transmits the prompt generated in step S109 described above to the LLM server 20 (step S110). The prompt transmitted from the communication unit 13 of the AI ​​server 10 reaches the LLM server 20 via the communication network NW.

[0064] The LLM server 20 receives the prompt sent from the AI ​​server 10 (step S111). The LLM server 20 generates an answer sentence to the user's query by referring to the received prompt (step S112). Specifically, the control unit 21 of the LLM server 20 generates an answer sentence to the user's query by referring to the reference information according to the instructions included in the prompt and generating a sentence that is highly compatible with the sentence (book data) included in the reference information by LLM. The LLM server 20 returns the generated answer sentence to the AI ​​server 10 as a response to the prompt received in step S111 (step S113).

[0065] The AI ​​server 10 receives the answer text returned from the LLM server 20 (step S114), and outputs the received answer text to the user terminal 30 (step S115).

[0066] The user terminal 30 displays the reply sentence output by the AI ​​server 10 on the display unit 35 (step S116). The user terminal 30 may display the reply sentence output by the AI ​​server 10 in the chat display field 101 of the user interface screen 100 described above. FIG. 11 is a schematic diagram showing an example of an output reply sentence to a user's query. The output example of FIG. 11 shows an example in which a reply sentence such as "The heart is what matters most" is output by the AI ​​server 10 in response to a user's query of "What does the heart is what matters most?" and is displayed in the chat display field 101 of the user interface screen 100.

[0067] As described above, in the first embodiment, a response sentence to a user's query can be output by a language model using book data. Since a book contains the thoughts and ideas of the author, by using book data, a response can be obtained as if one were having a conversation with the author himself / herself. In the present embodiment, an author model is prepared for specifying an author, an expert model for specifying a specific expert, and a book model for specifying a specific book are prepared. When the expert model is selected, a response can be obtained as if one were having a conversation with an expert, and when the book model is selected, a response can be obtained as if one were extracting from a book.

[0068] In the present embodiment, a query is received as text data and a reply is output as text data. However, a query may be received as voice data and a reply may be output as voice data.

[0069] In addition, in this embodiment, attributes may be assigned to the author model or the expert model. The attributes assigned to the author model or the expert model include the name, sex, age, job title, etc. of the respondent (author or expert). Information on the attributes is registered in, for example, a book database DB. When attributes are assigned to the author model or the expert model, the AI ​​server 10 can instruct the LLM server 20 to generate a prompt including information on the respondent's attributes and generate an answer sentence according to the attributes.

[0070] In addition, in this embodiment, user attributes may be acquired. User attributes include the user's name, sex, age, mood, etc. Information on user attributes may be registered in advance for each user in the storage unit 12, or may be acquired by the AI ​​server 10 inquiring of the user terminal 30 after login authentication. When user attributes are assigned, the AI ​​server 10 can instruct the LLM server 20 to generate a prompt including information on the user's attributes and generate an answer sentence according to the attributes.

[0071] FIG. 12 is a conceptual diagram for explaining an example of a prompt that takes into account the attributes of the questioner (user) and the answerer. FIG. 12 shows an example of a prompt when the answerer's attribute is a man in his 70s and the questioner's (user's) attribute is a man in his 30s. When the author model or the expert model is selected by the user, the answerer's attribute is specified by reading the attribute associated with the selected model from the author database DB. The questioner's attribute is specified by reading it from the storage unit 12 when the user logs in, or by inquiring of the user after the user logs in. In the example of FIG. 12, by adding an instruction such as "Please answer as if a man in his 70s were speaking to a man in his 30s," an answer according to the attributes of the questioner and the answerer can be provided to the user.

[0072] In the example of FIG. 12, the attributes of both the questioner and the answerer are specified, but the attributes of either the questioner or the answerer may be specified.

[0073] In this embodiment, the input data (prompt) to the LLM is generated based on the book data registered in the book database DB. Alternatively, an AI model may be prepared for each author, each expert, and each book. In this case, the AI ​​model represents a language model (machine learning model) that is trained to output a sentence corresponding to the input sentence when some sentence is input. For example, an AI model of an author, Mr. A, is generated by collecting sentence data from Mr. A's books and contents published by Mr. A on a communication network NW, and learning using the collected sentence data as learning data. The same applies to AI models specialized for other authors, experts, and books. Note that the learning algorithm used to generate the AI ​​model is not limited to a specific algorithm, and any appropriate learning algorithm may be used. The AI ​​model may also be generated by fine-tuning an existing language model.

[0074] The AI ​​models specialized for each author, expert, and book thus generated are registered in the memory unit 12 of the AI ​​server 10 or in a server accessible from the AI ​​server 10. After the service starts, the AI ​​server 10 accepts a query from the user and also accepts the selection of an AI model. The AI ​​server 10 inputs the accepted user query into the AI ​​model selected by the user, and causes the AI ​​model to generate a response sentence corresponding to the user query. The AI ​​server 10 provides a chat service to the user by outputting the response sentence generated by the AI ​​model to the user terminal 30.

[0075] The embodiments disclosed herein are illustrative in all respects and should not be considered as limiting. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the scope and meaning equivalent to the claims. [Explanation of symbols]

[0076] 10 AI Server 11 Control section 12 Storage section 13. Communications Department 14 Control section 15 Display 20 LLM Server 21 Control section 22 Memory section 23 Communications Department 24 Control section 25 Display section 30 User terminal 31 Control Unit 32 Storage section 33 Communications Department 34 Control section 35 Display section PG Chat Generation Program DB Book Database

Claims

1. Get the user's query, Using a language model that uses book data, the system outputs answers to queries. An information processing method in which processing is carried out by a computer.

2. A plurality of answer models for generating the answer sentence are prepared, Book data is associated with each of the plurality of answer models. The information processing method according to claim 1 .

3. The answer model includes at least one of an author model that simulates answers by a particular author, an expert model that simulates answers by a particular expert, and a book model that simulates answers by a particular book. The information processing method according to claim 2 .

4. referring to a database that stores an identifier for identifying each answer model and book data of one or more books in association with each other, and extracting from the database book data to be used for generating input data to the language model based on the identifier of the selected answer model and the acquired query; The input data is generated based on the extracted book data.

3. The information processing method according to claim 2, wherein processing is executed by the computer.

5. The input data includes the query as an instruction to the language model, and is a prompt including book data extracted from the database as reference information to be referred to when generating the answer sentence. The information processing method according to claim 4.

6. Attributes are assigned to each of the plurality of answer models; Input data including attributes of the selected answer model is input to the language model, thereby generating an answer sentence according to the attributes.

3. The information processing method according to claim 2, wherein processing is executed by the computer.

7. Acquire attributes of the user; Inputting input data including the acquired user attributes into the language model, the system generates a response sentence according to the attributes.

3. The information processing method according to claim 2, wherein processing is executed by the computer.

8. the database stores, as book data, data of a part or all of a text included in the content on the communication network, data of a summary of the text, or data of a translation of the text; generating input data for said language model based on book data including data obtained from said content; 5. The information processing method according to claim 4, wherein processing is executed by the computer.

9. The obtained query data is registered as the book data.

2. The information processing method according to claim 1, wherein processing is carried out by the computer.

10. The answer data is registered as the book data.

2. The information processing method according to claim 1, wherein processing is carried out by the computer.

11. storing the retrieved query data in association with a user identifier; Extracting information about the user's emotions, behavior, or state based on the stored query data.

2. The information processing method according to claim 1, wherein processing is carried out by the computer.

12. At least one processor; The processor, Get the user's query, Using a language model that uses book data, the system outputs answers to queries. Information processing device.

13. Get the user's query, Using a language model that uses book data, the system outputs answers to queries. A computer program for causing a computer to execute a process.

Images