Data processing device, data processing method, and data processing program

Abstract

To provide a device, method and program, which facilitate acquisition of vector data for use in RAG.SOLUTION: A data processing device disclosed herein performs processes of vectorizing book data into a data format usable by a generative model in RAG to generate vectorized book data, storing the vectorized book data in a database, selling the vectorized book data according to user instructions, collecting usage fees from users for selling the vectorized book data, and distributing the usage fees to rights holders of the book data.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The technology of the present disclosure relates to a data processing apparatus, a data processing method, and a data processing program.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, due to the remarkable progress of AI (Artificial Intelligence), various generative AIs that generate content using generative models have emerged. However, generative models have problems such as not including the latest data or outputting plausible lies (hallucinations). Therefore, a technique is known for improving the output accuracy and reliability of a generative model by using RAG (Retrieval Augmented Generation). However, there is a problem that it is difficult to obtain vector data used in RAG.

[0005] Therefore, an object of the technology disclosed herein is to provide an apparatus, a method, and a program that can facilitate obtaining vector data used in RAG.

Means for Solving the Problems

[0006] A first aspect of the technology according to the present disclosure includes a process of vectorizing book data into a data format that can be used by a generation model in RAG to create vectorized book data, a process of storing the vectorized book data in a database, a process of selling the vectorized book data based on a user's instruction, a process of collecting a usage fee from the user due to the sale of the vectorized book data, and a process of distributing the usage fee to the rights holder of the book data. It is a data processing apparatus that executes the above processes.

[0007] When receiving a search instruction for purchasing the vectorized book data stored in the database from the user, it may execute a process of outputting a search result.

[0008] The vectorized book data and vectorized related book data obtained by vectorizing related book data associated with the vectorized book data may be sold together.

[0009] The vectorized book data sold to the user may be stored for each user, and the user may be allowed to add or delete the stored vectorized book data.

[0010] The sale of the vectorized book data may be performed for a portion of the vectorized book data desired by the user.

[0011] The usage fee may be calculated based on the amount of usage in RAG.

[0012] A process of obtaining a prompt input from the user to the generation model, a process of searching the database for the vectorized book data related to the prompt input from the user to the generation model, and a process of outputting the search result to the user may be executed.

[0013] A second aspect of the technology according to the present disclosure is a data processing method in which a computer executes a process of vectorizing book data into a data format that can be used by a generation model in RAG to create vectorized book data, a process of storing the vectorized book data in a database, a process of selling the vectorized book data based on a user's instruction, a process of collecting a usage fee from the user due to the sale of the vectorized book data, and a process of distributing the usage fee to the rights holder of the book data.

[0014] A third aspect of the technology according to the present disclosure is a data processing program for causing a computer to execute a process of vectorizing book data into a data format that can be used by a generation model in RAG to create vectorized book data, a process of storing the vectorized book data in a database, a process of selling the vectorized book data based on a user's instruction, a process of collecting a usage fee from the user due to the sale of the vectorized book data, and a process of distributing the usage fee to the rights holder of the book data.

Brief Description of Drawings

[0015]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a data processing device, a data processing method, and a data processing program according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit), etc.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0023] FIG. 1 shows an example of the configuration of the data processing system 10 according to the embodiment.

[0024] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a user terminal 14. An example of the data processing device 12 is a server. Examples of the user terminal 14 include a personal computer, a smartphone, and the like. The data processing device 12 is an example of the "data processing device" according to the technology of the present disclosure.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of the "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The user terminal 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by contact of an indicator (e.g., a pen or a finger, etc.) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires data indicating the user input.

[0028] The output device 40 includes a display 40A, a speaker 40B, etc., and presents data to the user by outputting the data in a form that can be perceived by the user (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, an aperture, and a shutter, and an imaging device such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to the network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the user terminal 14.

[0031] As shown in FIG. 2, in the data processing device 12, specific processing is performed by the processor 28. The storage 32 stores a specific processing program 56. The specific processing program 56 is an example of the "data processing program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a database 59. The database 59 stores vectorized book data created by vectorizing book data in a data format that can be used by the generation model 58 in RAG. The database 59 is used by the specific processing unit 290.

[0033] At the user terminal 14, the input / output processing is performed by the processor 46. The storage 50 stores an input / output program 62. The input / output program 62 is used in combination with the specific processing program 56 by the data processing system 10. The processor 46 reads out the input / output program 62 from the storage 50 and executes the read input / output program 62 on the RAM 48. The input / output processing is realized by operating as the control unit 46A according to the input / output program 62 executed by the processor 46 on the RAM 48.

[0034] Next, the processing of the specific processing unit 290 when the data processing device 12 performs the specific processing of selling the vectorized book data will be described. Here, the "book data" refers to the so-called "e-book" configured in digital format. Note that what the data processing device 12 sells is not limited to book data, and may be other data, for example, audio data, movie data, etc.

[0035] FIG. 3 shows an overview of a specific process for selling vectorized book data created by vectorizing book data into a data format that can be used by a generation model 58 in RAG (Retrieval Augmented Generation). Generally, an author sends a manuscript created to a publisher, the publisher creates manuscript data based on the manuscript and sends it to a vector book store, a data processing device 12 of the vector book store vectorizes the manuscript data to create vectorized book data, registers the created vectorized book data in a database for sale, a user searches for and purchases the vectorized book data registered and sold in the database, and such transactions are carried out. Also, transactions such as payment of a usage fee for the vectorized book data from the user, payment of the usage fee from the vector book store to the publisher, and payment of a manuscript fee or royalty based on the usage fee from the publisher to the author are carried out. Note that the vectorized book data purchased by the user may be stored (embedded) in the vector database of the storage 50 of the user terminal 14. Also, the vectorized book data purchased by the user may be stored (embedded) in the vector database set for each user in the storage 32 of the data processing device 12. Note that it is desirable that the vector database set for each user enables the addition or deletion of the vectorized book data to be stored by the user. Then, when the user uses the generation model 58, the generation model 58 refers to the purchased vectorized book data from the vector database and outputs a generation result.

[0036] In recent years, due to the remarkable progress of AI, various generation tools 16 that input data of characters, voices, and images input from a user into the generation model 58 and obtain generation results have emerged. The generation model 58 is an example of the "generation model" according to the technology of the present disclosure.

[0037] Here, the generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of the generation model 58 include generative AIs such as ChatGPT (Internet search <URL: https: / / openai.com / blog / chatgpt>). The generation model 58 is obtained by performing deep learning on a neural network. A prompt including instructions is input into the generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is input. The generation model 58 infers the input inference data according to the instructions indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization, etc. And during inference, by using RAG, the accuracy and reliability of the inference result are improved using vectorized book data.

[0038] In addition, the generation tool 16 may be API (Application Programming Interface) - linked to the vector bookstore. API linkage means making data linkage with an external application or system using an API. In this case, the user can use the generative AI as if directly accessing it by logging in to the vector bookstore and selecting the generation tool 16 that is data - linked as an extension function. Also, since all interactions between the user and the generation model 58 go through the API, the data processing device 12 implemented in the vector bookstore can grasp the usage status (including the usage amount) of the vectorized book data. Thereby, it is also possible to calculate the usage fee for the vectorized book data collected from the user based on the usage amount actually used in RAG.

[0039] 4 shows a schematic functional configuration of the specific processing unit 290 of the data processing device 12. The specific processing unit 290 includes a book data receiving unit 291, a creating unit 292, a storage unit 293, a selling unit 294, a collecting unit 295, a distributing unit 296, and an interface unit 297.

[0040] The book data receiving unit 291 receives book data from publishers and authors.

[0041] The creation unit 292 vectorizes the book data received by the book data receiving unit 291 into a data format that can be used by the generative model 58 in RAG, creating vectorized book data. Here, the vectorization can be performed using known techniques. Note that the vectorization of book data is not limited to creating one vector data per piece of book data, and the book data may be divided into multiple pieces, for example, by chapter. Furthermore, a summary of the book data may be vectorized and saved together with the vectorized book data, and the summary may be used as a search target for the vectorized book data by a user.

[0042] The storage unit 293 stores the vectorized book data created by the creation unit 292 in the sales database 59.

[0043] The sales unit 294 sells the vectorized book data based on instructions from the user. Here, before the sale, the sales unit 294 outputs to the user a search instruction from the user for vectorized book data stored in the database 59, for example, a keyword search result for the title or part of the content of a book related to the inference result that the user wants the generative model 58 to output. Then, based on the search results, the sales unit 294 sells the vectorized book data based on an instruction from the user to purchase the vectorized book data.

[0044] In addition, the sale of vectorized book data may involve the sale of all parts of the vectorized book data, or it may involve the sale of only the parts of the vectorized book data that the user desires, for example, if the vectorized book data consists of multiple chapters, only the chapters that the user desires.

[0045] In addition, the sale of vectorized book data is not limited to the sale of a single piece of vectorized book data, and multiple pieces of vectorized book data may be sold as a set. For example, the vectorized book data output by a user's search and the vectorized related book data obtained by vectorizing the related book data related to the vectorized book data may be sold together. Here, the related book data includes, for example, the complete works of the author of the vectorized book data, the documents described as references in the vectorized book data, and the like.

[0046] In addition, it is not limited to outputting to the user the result of a search instruction for the vectorized book data stored in the database 59 from the user before selling the vectorized book data. Specifically, the sales unit 294 may obtain the prompt input by the user to the generation model 58, search the database 59 for the vectorized book data related to the prompt, and output the search result to the user. Here, whether the vectorized book data is related to the prompt may be determined by whether the words included in the prompt are described in the vectorized book data above a threshold value, whether the words included in the prompt are described in the title of the vectorized book data, and the like.

[0047] The collection unit 295 collects the usage fee from the user for the sale of the vectorized book data by the sales unit 294. Here, the usage fee includes the case where the fee is a flat rate regardless of how many times the vectorized book data is used, and the case where the fee is paid each time it is used. In addition, the usage fee may be calculated based on the usage amount used in RAG among the vectorized book data.

[0048] The distribution unit 296 distributes the usage fee collected by the collection unit 295 to the rights holders of the book data, such as publishers and authors.

[0049] The interface unit 297 supplies instructions from the user to the generation model 58 via the API and obtains inference results from the generation model 58 via the API.

[0050] Next, the operation of the data processing system 10 will be described.

[0051] FIGS. 5 and 6 schematically show an example of the operation flow of specific processing by the data processing device 12. Note that the processing in FIG. 5 and the processing in FIG. 6 are not limited to being performed by the same data processing device 12, and other data processing devices 12 may perform them.

[0052] First, with reference to FIG. 5, the flow of specific processing related to the vectorization of book data will be described. Note that the flow of specific processing shown in FIGS. 5 and 6 is an example of the "data processing method" according to the technology of the present disclosure.

[0053] In step S300, the book data reception unit 291 receives book data to be vectorized.

[0054] In step S301, the creation unit 292 vectorizes the book data received in step S300 to create vectorized book data.

[0055] In step S302, the vectorized book data created in step S301 is stored in the sales database 59. Then, the specific processing in FIG. 5 ends.

[0056] Next, with reference to FIG. 6, the flow of specific processing related to the sale of vectorized book data will be described.

[0057] In step S310, the sales unit 294 receives a search instruction when purchasing vectorized book data stored in the database 59 from the user and outputs a search result.

[0058] In step S311, the sales unit 294 sells the vectorized book data from the search results output in step S310 based on the user's instructions.

[0059] In step S312, the collection unit 295 collects from the user the usage fee for the vectorized book data sold in step S311.

[0060] In step S313, the distribution unit 296 distributes the usage fee for the vectorized book data collected in step S312 to the right holder, and then the specification process in FIG.

[0061] In this way, the data processing device 12 according to this embodiment vectorizes book data into a data format that can be used by the generative model 58 in RAG to create vectorized book data, stores the vectorized book data in the database 59, sells the vectorized book data based on user instructions, collects usage fees from users for the sale of the vectorized book data, and distributes the usage fees to the rights holders of the book data. This makes it possible to enrich vectorized book data and facilitates the acquisition of vector data used in RAG. Furthermore, the use of vectorized book data improves the output accuracy and reliability of the generative model 58. It also makes it possible to prevent illegal copying of book data, allowing rights holders of the book data to obtain appropriate profits.

[0062] In addition, when a search instruction is received from a user when purchasing vectorized book data stored in the database 59, a process of outputting search results may be executed, thereby enabling the user to search for suitable vectorized book data.

[0063] The vectorized book data may be sold together with vectorized related book data, which is obtained by vectorizing related book data related to the vectorized book data. This reduces the effort required for users to search for vectorized book data.

[0064] Store the vectorized book data sold to each user for each user, and allow the user to add or delete the stored vectorized book data. This allows the user to obtain the inference result of the generation model 58 specialized for the user.

[0065] The sale of the vectorized book data may be performed for the parts desired by the user among the vectorized book data. This can prevent the user from paying for parts that are not relevant.

[0066] The usage fee may be calculated based on the usage amount used in RAG. This can prevent the user from paying a fee for which they do not receive aftercare for the inference result by the generation model 58.

[0067] Execute the process of obtaining the prompt input from the user to the generation model 58, the process of searching the database 59 for the vectorized book data related to the prompt input from the user to the generation model 58, and the process of outputting the search result to the user. This can prevent the user from buying book data that is not related to the prompt.

[0068] As described above, the system according to the present disclosure has been mainly described in terms of the functions of the data processing device 12. However, the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program operating on a personal computer or as an application operating on a smartphone or the like. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[0069] In the above embodiment, an example form in which specific processing is performed by a single computer 22 has been given. However, the technology of the present disclosure is not limited to this, and distributed processing for specific processing by a plurality of computers including the computer 22 may be performed.

[0070] In the above embodiment, an example form in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0071] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed in the computer 22 in response to a request from the data processing device 12.

[0072] Note that it is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32. A part of the specific processing program 56 may be stored.

[0073] As hardware resources for executing specific processing, various types of processors shown below can be used. As a processor, for example, there is a CPU which is a general-purpose processor that functions as a hardware resource for executing specific processing by executing software, that is, a program. Also, as a processor, for example, there is a dedicated electric circuit which is a processor having a circuit configuration designed specifically for executing specific processing such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit). A memory is built in or connected to any of these processors, and any of these processors executes specific processing by using the memory.

[0074] The hardware resources for executing specific processing may be composed of one of these various processors, or may be composed of a combination of two or more processors of the same type or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resources for executing specific processing may be one processor.

[0075] As an example of being composed of one processor, first, there is a form in which one or more CPUs and software are combined to form one processor, and this processor functions as a hardware resource for executing specific processing. Second, there is a form in which a processor that realizes the functions of an entire system including a plurality of hardware resources for executing specific processing in one IC chip as represented by an SoC (System-on-a-chip) is used. Thus, specific processing is realized as a hardware resource by using one or more of the above various processors.

[0076] Furthermore, as the hardware structure of these various processors, more specifically, an electric circuit combining circuit elements such as semiconductor elements can be used. Also, the above specific processing is merely an example. Therefore, it goes without saying that within the scope not departing from the gist, unnecessary steps may be deleted, new steps may be added, or the processing order may be changed.

[0077] The description content and illustrated content shown above are detailed descriptions of the part related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the descriptions regarding the above configuration, function, action, and effect are descriptions regarding an example of the configuration, function, action, and effect of the part related to the technology of the present disclosure. Therefore, it goes without saying that within the scope not departing from the gist of the technology of the present disclosure, the description content and illustrated content shown above may be deleted of unnecessary parts, new elements may be added, or replaced. Also, in order to avoid complication and facilitate the understanding of the part related to the technology of the present disclosure, in the description content and illustrated content shown above, descriptions regarding common technical knowledge and the like that do not particularly require explanation for implementing the technology of the present disclosure are omitted.

[0078] All documents, patent applications, and technical standards described in this specification are incorporated herein by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually stated to be incorporated by reference.

[0079] Regarding the above, the following supplementary notes are further disclosed.

[0080] <Supplementary Note 1> A process of vectorizing book data into a data format usable by a generation model in RAG to create vectorized book data, A process of storing the vectorized book data in a database, A process of selling the vectorized book data based on a user's instruction, A process of collecting a usage fee from the user due to the sale of the vectorized book data, The process of distributing the usage fee to the rights holder of the book data, A data processing device that executes <Appendix 2> The data processing device according to Appendix 1, which executes a process of outputting a search result when receiving a search instruction for purchasing the vectorized book data stored in the database from the user. <Appendix 3> The data processing device according to Appendix 1 or Appendix 2, which sells the vectorized book data and the vectorized related book data obtained by vectorizing the related book data related to the vectorized book data together. <Appendix 4> The vectorized book data sold to the user is stored for each user, The data processing device according to any one of Appendices 1 to 3, which enables the user to add or delete the vectorized book data to be stored. <Appendix 5> The data processing device according to any one of Appendices 1 to 4, wherein the sale of the vectorized book data is performed for the part desired by the user among the vectorized book data. <Appendix 6> The data processing device according to any one of Appendices 1 to 5, wherein the usage fee is calculated based on the usage amount used in RAG. <Appendix 7> The process of obtaining the prompt input by the user to the generation model, The process of searching the database for the vectorized book data related to the prompt input by the user to the generation model, The data processing device according to any one of Appendices 1 to 6, which executes a process of outputting the search result to the user. <Appendix 8> A computer The process of creating vectorized book data by vectorizing book data into a data format that can be used by a generation model in RAG, The process of storing the vectorized book data in a database, The process of selling the vectorized book data based on the user's instructions, The process of collecting usage fees from the user due to the sale of the vectorized book data, The process of distributing the usage fees to the rights holders of the book data, A data processing method for executing the above. <Appendix 9> On a computer, The process of vectorizing book data into a data format that can be used by the generation model in RAG to create vectorized book data, The process of storing the vectorized book data in a database, The process of selling the vectorized book data based on the user's instructions, The process of collecting usage fees from the user due to the sale of the vectorized book data, The process of distributing the usage fees to the rights holders of the book data, A data processing program for causing the above to be executed.

Explanation of Reference Signs

[0081] 10 Data processing system 12 Data processing device 14 User terminal 58 Generation model 290 Specific processing unit 291 Book data reception unit 292 Creation unit 293 Storage unit 294 Sales unit 295 Collection unit 296 Distribution unit

Claims

1. A process of vectorizing book data into a data format usable by a generation model in RAG to create vectorized book data, a process of storing the vectorized book data in a database, a process of selling the vectorized book data based on a user's instruction, a process of collecting a usage fee from the user due to the sale of the vectorized book data, a process of distributing the usage fee to the rights holder of the book data, and a data processing device that executes the above.

2. The data processing device according to claim 1, which executes a process of outputting a search result when receiving a search instruction for purchasing the vectorized book data stored in the database from the user.

3. The data processing device according to claim 1, which sells the vectorized book data together with vectorized related book data obtained by vectorizing related book data associated with the vectorized book data.

4. The data processing device according to claim 1, which stores the vectorized book data sold to the user for each user, and enables the user to add or delete the stored vectorized book data.

5. The data processing device according to claim 1, wherein the sale of the vectorized book data is performed on a part desired by the user among the vectorized book data.

6. The data processing device according to claim 1, wherein the usage fee is calculated based on the amount of usage in RAG.

7. A process of obtaining a prompt input from the user to the generation model, a process of searching the database for the vectorized book data related to the prompt input from the user to the generation model, and a process of outputting the search result to the user. The data processing device according to claim 1 executes the above processes.

8. A data processing method in which a computer performs a process of vectorizing book data into a data format usable by a generation model in RAG to create vectorized book data, a process of storing the vectorized book data in a database, a process of selling the vectorized book data based on a user's instruction, a process of collecting a usage fee from the user due to the sale of the vectorized book data, a process of distributing the usage fee to the rights holder of the book data, and executes the above processes.

9. On a computer, A process of vectorizing book data into a data format usable by a generation model in RAG to create vectorized book data, A process of storing the vectorized book data in a database, A process of selling the vectorized book data based on a user's instruction, A process of collecting a usage fee from the user due to the sale of the vectorized book data, A process of distributing the usage fee to the rights holder of the book data, A data processing program for causing the above to be executed.

Images