Acquisition device and acquisition method

Abstract

To obtain evaluations of survey responses that align with the user's intent in requesting the evaluation. [Solution] The RAG system 20 includes a request acquisition unit 22 that acquires requests to create reports for multiple response text data for each respondent, a policy decision unit 23 that determines policy information regarding the report creation policy based on the creation requests, a prompt generation unit 24 that includes the policy information and multiple response text data and generates a prompt requesting the creation of a report based on the multiple response text data, and an information acquisition unit 25 that acquires a report by inputting input information into an interactive AI model 31.

Description

Technical Field

[0001] One aspect of the present disclosure relates to an acquisition device and an acquisition method.

Background Art

[0002] Conventionally, the use of computers has been automated to tabulate and analyze questionnaire results. In the device described in Patent Document 1 below, questionnaire result data obtained through interaction with subjects is tabulated to obtain a tabulation result, and the tabulation result is evaluated, analyzed, and interpreted using statistical methods. For example, in this device, tabulation is performed by age or gender of the response data, and the evaluation of the response is performed by determining the validity of the response or the tendency of the response.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the above conventional device, it has been difficult to obtain an evaluation of responses that meets the intentions of users who require evaluation. That is, in a device whose program is designed to perform a predetermined evaluation, it may not be possible to obtain an evaluation that meets the intentions of the user.

[0005] Therefore, an object of the present disclosure is to provide an acquisition device and an acquisition method capable of obtaining an evaluation of questionnaire responses that meets the intentions of users who require evaluation.

Means for Solving the Problems

[0006] The acquisition device of this disclosure comprises: a request acquisition unit that acquires a request to create a report for multiple response text data for each respondent; a policy determination unit that determines policy information regarding the report creation policy based on the creation request; an information generation unit that generates input information including the policy information and multiple response text data, and requests the creation of a report based on the multiple response text data; and an information acquisition unit that acquires a report by inputting the input information into a generation AI model. [Effects of the Invention]

[0007] According to this disclosure, it is possible to obtain evaluations of survey responses that match the intent of the user requesting the evaluation. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 is a block diagram showing the configuration of the acquisition system of this disclosure. [Figure 2] Figure 2 shows an example of the structure of the survey response data stored in the response data storage unit 26 of Figure 1. [Figure 3] Figure 3 shows an example of the data structure of attribute information stored in the attribute information storage unit 27 of Figure 1. [Figure 4] Figure 4 shows an example of the data structure of the extracted information stored in the policy information storage unit 28 in Figure 1. [Figure 5] Figure 5 shows an example of the data structure of the example document database stored in the policy information storage unit 28 of Figure 1. [Figure 6] Figure 6 is a flowchart showing the procedure for report acquisition by the RAG system 20. [Figure 7] Figure 7 is a flowchart showing other steps in the report acquisition process by the RAG system 20. [Figure 8] Figure 8 shows an example of the hardware configuration of a RAG system 20 according to one embodiment of the present disclosure. [Modes for carrying out the invention]

[0009] Embodiments of this disclosure will be described with reference to the attached drawings. Where possible, the same parts will be denoted by the same reference numerals, and redundant descriptions will be omitted.

[0010] Figure 1 is a diagram showing the device configuration of the acquisition system according to this embodiment. The acquisition system shown in Figure 1 includes terminals 10A and 10B, a RAG (Retrieval-Augmented Generation) system 20, and a server device 30, all configured to communicate with each other via a network including a wireless communication network and a fixed communication network. The RAG system 20 constitutes an acquisition device that acquires report data based on questionnaire response data received from terminal 10A.

[0011] Terminal 10A is a device used by a user who intends to input survey response data, which is data indicating the user's answers to a questionnaire. Terminal 10B is a device such as a personal computer, smartphone, tablet, feature phone, or server. Terminal 10A may directly transmit survey response data, such as text data for the questionnaire, to the RAG system 20 using a predetermined user interface, or it may transmit the survey response data to the RAG system 20 via another server device, another personal computer, etc. Although only one terminal 10A is shown in Figure 1, the acquisition system may include any number of terminals 10A, two or more.

[0012] Terminal 10B is a device used by users who wish to acquire report data automatically generated from survey response data using an interactive AI model. Terminal 10B can be, for example, a personal computer, smartphone, tablet, feature phone, or server device. Although only two terminals 10B are shown in Figure 1, the acquisition system may include any number of terminals 10B, two or more.

[0013] The server device 30 is a device that enables the provision of content using a generative AI model. A generative AI model is a model that, in response to a prompt containing input information, generates content according to one or a combination of the instructions, context, questions, and output format indicated by the prompt, and returns that content as response information. The prompt can also include input information, in which case the generative AI model generates response information targeting the input information. The generative AI model may be, for example, a conversational AI model that includes a Large Language Model (LLM) and a user interface (UI) for interaction with the user, enabling text chat or voice chat with the user.

[0014] The generative AI model used in this embodiment returns text-based response information in response to text-based prompt input. Examples of such generative AI models include ChatGPT, GPT(registered trademark)-3.5, GPT-3.5 Turbo, GPT-4.0, GPT-4.0 Turbo, Azure OpenAI Service, tsuzumi, GPT-4V, PaLM2, and others.

[0015] In this embodiment, the server device 30 enables the provision of content by the interactive AI model 31. This interactive AI model 31 may be stored within the server device 30, or it may be stored in another device connected to the server device 30 via a network, and configured to allow information exchange with the user via the server device 30. Alternatively, the interactive AI model 31 may be stored within the terminal 10B. Although only one server device 30 is shown in Figure 1, the acquisition system may include multiple server devices 30. Furthermore, while the above description uses a large-scale language model as an example, other AI models may also be used. In addition, the acquisition system may use an AI model selected from among several types of AI models.

[0016] The RAG system 20 is configured to include, as functional components, a response acquisition unit 21, a request acquisition unit 22, a policy determination unit 23, a prompt generation unit (information generation unit) 24, an information acquisition unit 25, a response data storage unit 26, an attribute information storage unit 27, and a policy information storage unit 28. The RAG system 20 relays a prompt (input information) generated based on the data acquired from the terminals 10A and 10B to the server device 30, and acquires response information from the server device 30 for the prompt. Hereinafter, the functions of each functional unit of the RAG system 20 will be described in detail.

[0017] The response acquisition unit 21 acquires questionnaire response data from the terminal 10A and stores the acquired questionnaire response data in the response data storage unit 26. The questionnaire response data is data representing responses input by the user of the terminal 10A to a preset questionnaire, and is either option identification data for a plurality of preset options, free input data including numbers, symbols, words, or sentences freely input for a question, or a combination of these data.

[0018] FIG. 2 shows an example of the configuration of the questionnaire response data stored in the response data storage unit 26. The questionnaire response data includes response text data related to a plurality of questionnaires specified by questionnaire names and implemented separately. In addition, the questionnaire response data corresponding to one questionnaire specified by the questionnaire name includes a plurality of response text data respectively representing responses input by a plurality of users. For example, the questionnaire response data related to the questionnaire specified by the questionnaire name "Questionnaire after Conversation for First-Year Employees" includes response text data "I want to find out if there is anything that can improve work efficiency in the branch store and also gain knowledge about DX." representing the response input by the user identified by the responder ID "AAA", and response text data "By utilizing data, the breadth of knowledge can be expanded..." representing the response input by the user identified by the responder ID "BBB".

[0019] The request acquisition unit 22 acquires, from the terminal 10B, a request for creating a report targeting a plurality of response text data for each respondent acquired by the response acquisition unit 21. That is, the request acquisition unit 22 acquires, in the creation request, questionnaire identification information (e.g., questionnaire name) for identifying the questionnaire to be the target of the report creation, questionnaire purpose information indicating the purpose of acquiring the questionnaire, questionnaire type information indicating the type of the questionnaire, and the like. Also, the request acquisition unit 22 acquires, from the terminal 10B, a user ID, which is identification information for identifying the user of the terminal 10B, together with the creation request.

[0020] The policy determination unit 23 determines policy information regarding the report creation policy based on the user ID and the creation request acquired by the request acquisition unit 22. First, the policy determination unit 23 extracts the attribute information pre-stored in the attribute information storage unit 27 using the user ID, and identifies the reader attribute regarding the attribute of the report reader based on the extracted attribute information. However, this reader attribute may be acquired included in the creation request by the request acquisition unit 22, or the policy determination unit 23 may identify the reader attribute based on the creation request.

[0021] FIG. 3 shows an example of the data configuration of the attribute information stored in the attribute information storage unit 27. In the attribute information storage unit 27, attribute information including name, affiliated department, position, business information, etc. is stored in association with the user ID for identifying the users of the terminals 10A and 10B. For example, as the attribute information of the user identified by the user ID “AAA”, attribute information including name “Taro Sato”, affiliated department “Personnel Department”, position “Section Chief”, business information “Recruitment of human resources, training affairs office”, and attribute “in their 30s” is stored. The policy determination unit 23 extracts the attribute information corresponding to the user ID acquired by the request acquisition unit 22 from the attribute information storage unit 27, and identifies the reader attribute based on the extracted attribute information. For example, the policy determination unit 23 identifies, as the reader attribute corresponding to the user ID “BBB”, the combination of the affiliated department “Personnel Department” and the position “Responsible employee” included in the attribute information.

[0022] Furthermore, the policy decision unit 23 searches the policy information storage unit 28 using the creation request or reader attributes to extract information associated with the information contained in the creation request or the reader attributes, and determines the extracted information to be policy information.

[0023] Figure 4 shows an example of the data structure of the extracted information stored in the policy information storage unit 28. The policy information storage unit 28 pre-stores policy information regarding the report creation policy for each combination of three search keys. For example, the three search keys, namely the information on the type of questionnaire "Training participant questionnaire," the information on the purpose of the questionnaire "Training participant satisfaction survey," and the information on the attributes of the report reader "Person in charge of the questionnaire secretariat in the Human Resources Department," are associated with a combination of policy information, namely the information on the purpose of the report "Planning of training for the next fiscal year" and the information on the report creation policy "Please describe in detail any constructive opinions you have regarding the improvement of the training content." Note that multiple policy information may be associated with the three search keys. For example, the three search keys mentioned above are also associated with a combination of information on the purpose of the report "Training evaluation" and the information on the report creation policy "Please describe any positive aspects of the training content."

[0024] Furthermore, each policy information stored in the policy information storage unit 28 includes predetermined priority information indicating the priority of that information. The policy decision unit 23 may determine the priority information corresponding to the policy information using a learning model (AI model) or an existing scoring method, and pre-store the determined priority information in the policy information storage unit 28. For example, the policy decision unit 23 may use a learning model that has been pre-trained on the relationship between the information on the purpose of the questionnaire and the information on the creation policy, and determine the output of the learning model obtained by inputting the information on the purpose of the questionnaire and the information on the creation policy as priority information indicating the priority of the information on the creation policy. Alternatively, the policy decision unit 23 may use a learning model that has been pre-trained on the relationship between the information on the purpose of the questionnaire and the information on the purpose of the report, and determine the output of the learning model obtained by inputting the information on the purpose of the questionnaire and the information on the purpose of the report as priority information indicating the priority of the information on the purpose of the report.

[0025] Furthermore, the attribute information of each reader stored in the policy information storage unit 28 may include predetermined priority information indicating the priority of each piece of information. For example, the policy decision unit 23 uses a learning model that has been pre-trained on the relationship between the information on the purpose of the questionnaire and the information on the reader's attributes, and determines the output of the learning model obtained by inputting the information on the purpose of the questionnaire and the information on the reader's attributes as priority information indicating the priority of the information on the reader's attributes.

[0026] The policy decision unit 23 extracts policy information from the policy information storage unit 28 that is similar to the identified reader attributes and the survey purpose information and survey type information included in the creation request, and that have three similar search keys. At this time, the policy decision unit 23 can determine the similarity between the reader attribute information and the search keys by vectorizing the information of each other. For example, if the policy information storage unit 28 with the data configuration shown in Figure 4 is targeted, the policy decision unit 23 extracts two sets of information on the purpose of the report and the policy for creating the report that correspond to the reader attribute information "person in charge of the survey secretariat in the Human Resources Department" and the survey purpose information "training satisfaction survey," which are similar to the reader attribute "Human Resources Department, employee in charge" and the survey purpose information "survey on training participant feedback."

[0027] The policy decision unit 23 may also search the policy information storage unit 28 based on the survey purpose information or survey type information included in the creation request, and determine a combination of reader attribute information, report purpose information, and report creation policy information corresponding to the survey purpose information or survey type information as policy information.

[0028] The prompt generation unit 24 generates a prompt (input information) that includes policy information determined by the policy decision unit 23 and survey response data related to the survey to be created as the subject of the report, and requests the creation of a report based on multiple response text data included in the survey response data. At this time, the prompt generation unit 24 obtains the survey response data by extracting it from the survey response data stored in the response data storage unit 26 using the survey identification information included in the creation request.

[0029] Furthermore, the prompt generation unit 24 may search the example sentence database pre-stored in the policy information storage unit 28 based on the report creation policy information included in the policy information determined by the policy decision unit 23, extract example sentences corresponding to the report creation policy information, and include the extracted example sentences in the prompt. Figure 5 shows an example of the data structure of the example sentence database stored in the policy information storage unit 28. In the example sentence database stored in the policy information storage unit 28, for example, example sentences such as "It was good that the instructor answered all the questions" and "The time allocation was excellent" are associated with the report creation policy information "Please include anything that praises the training content." When the prompt generation unit 24 searches the example sentence database with the configuration shown in Figure 5 using the report creation policy information "Please include anything that praises the training content," it extracts example sentences such as "It was good that the instructor answered all the questions" and "The time allocation was excellent" that are associated with report creation policy information similar to that information.

[0030] The following is an example of a prompt generated by the prompt generation unit 24. Here, we show an example of a prompt created when the reader attribute information "person in charge of the survey secretariat in the HR department" and "management executive," and the total priority values ​​"70" and "30" corresponding to the survey objective information "training participant satisfaction survey," are extracted from the policy information of the data structure shown in Figure 4. <Example of a prompt> Your role is that of an excellent employee. Please create a report based on the task survey results. #Input Information "I was glad to find out that there are plenty of AI resources for generation within the company.",... #conditions Please generate the report considering the readers listed below. reader • Person in charge of the Human Resources Department's survey office • Executive Since the HR department's survey office staff will be the primary readers, please prioritize them at a ratio of 70:30. The report will be used for the following purposes: the purpose • Compiling the survey results Report preparation policy Please include any positive comments about the training content. For example, "I appreciated that the instructor answered all of the questions." Please provide specific, constructive suggestions for improving the training content. For example, please write...

[0031] The information acquisition unit 25 inputs the prompt generated by the prompt generation unit 24 to the interactive AI model 31 and acquires response information from the interactive AI model 31, including a report automatically generated for the survey response data. The information acquisition unit 25 then outputs the acquired report as output data. The output data from the information acquisition unit 25 may be transmitted to an external device such as the terminal 10B, or it may be stored in the data storage unit within the RAG system 20 in a way that allows it to be accessed from the outside.

[0032] The following is an example of a report obtained by the information acquisition unit 25. <Report> (Recognition of DX and efficiency improvements) - There is a growing awareness of improving operational efficiency through data utilization and digital transformation (DX). - There is an understanding that utilizing generation AI and other technologies can improve the efficiency and expand the scope of operations. - There are high expectations for the benefits of early digital transformation. (Changes in skills and awareness of growth) - There is a recognition that ambition and initiative are more important than specialized skills for digital transformation. - Some people have realized the importance of personal growth, such as by creating a second business card. - They place more importance on their personal identity than on their company title. (Issue recognition) - We recognize the importance of proactive adoption of DX (Digital Transformation) by younger generations. - There is an awareness of issues such as the digital divide. (evaluation) Overall, the results appear to be very positive. There is a growing understanding and awareness of digital transformation (DX), data utilization, and generative AI. Furthermore, individuals are demonstrating a proactive attitude towards professional skill development and self-improvement. Negative aspects include the need to address challenges such as the digital divide and the recognition of the need for more active participation from younger generations. However, recognizing these challenges can also be seen as a step towards improvement.

[0033] The procedure for acquiring a report using the RAG system 20 configured as described above, that is, the flow of the acquisition method according to this embodiment, will now be explained. Figure 6 is a flowchart showing the procedure for acquiring a report using the RAG system 20.

[0034] First, the response acquisition unit 21 of the RAG system 20 acquires multiple survey response data for pre-configured questionnaires from terminal 10A and stores them in the response data storage unit 26 (step S01). Subsequently, at any time thereafter, the request acquisition unit 22 acquires a report creation request from terminal 10B along with the user ID (step S02). Then, the policy decision unit 23 searches for policy information based on the user ID and the creation request (step S03). Furthermore, the prompt generation unit 24 searches the example sentence database based on the policy information and extracts example sentences corresponding to the policy information (step S04).

[0035] Then, the prompt generation unit 24 creates a prompt based on policy information, multiple survey response data, and example sentences (step S05). Finally, the information acquisition unit 25 acquires a report when the prompt is input to the interactive AI model 31, and the acquired report is output (step S06).

[0036] Next, the effects of the acquisition system of this disclosure will be explained. According to the RAG system 20 of this disclosure, a report creation request is obtained from terminal 10B, policy information is determined based on that creation request, and a prompt including the determined policy information and multiple response document data for each respondent is input to the interactive AI model 31, thereby acquiring the report. As a result, a report created with a policy that matches the creation request obtained from the user of terminal 10B can be acquired, and an evaluation of the survey response that matches the intent of the user requesting the evaluation can be obtained.

[0037] In the RAG system 20 of this disclosure, the creation request includes information about the attributes of the report reader, and the policy decision unit 23 extracts information associated with the attribute information by searching the policy information storage unit 28, and determines that the extracted information is the policy information. As a result, it is possible to obtain a report created with a policy corresponding to the attributes of the report reader. For example, it is possible to obtain a report that is suitable for the purpose of use of the report corresponding to the department to which the reader belongs, or a report that includes items corresponding to the department to which the reader belongs. As a result, it is possible to obtain evaluations of survey responses that are useful to the reader user.

[0038] Furthermore, in the RAG system 20 of this disclosure, the policy decision unit 23 further determines multiple priority information indicating the respective priorities for each of the multiple extracted pieces of information, and includes the multiple priority information in the policy information. In this case, it is possible to obtain a focused report regarding the report creation policy, and to obtain an evaluation of survey responses that is beneficial to the overall user base of multiple readers.

[0039] The acquisition device described herein has the following configuration.

[0040] [1] A request acquisition unit that acquires requests to create reports for multiple response text data for each respondent, A policy decision unit determines policy information regarding the report creation policy based on the aforementioned creation request, An information generation unit that generates input information requesting the creation of a report based on the policy information and the plurality of response text data, An information acquisition unit that acquires the report by inputting the aforementioned input information into a generating AI model, An acquisition device equipped with the following features.

[0041] [2] The aforementioned request for creation includes information about the attributes of the reader of the report, The policy determination unit extracts information associated with the attribute information by searching the information storage unit, and determines the extracted information as the policy information. The acquisition device described in [1] above.

[0042] [3] The creation request includes multiple pieces of information regarding the attribute, The policy determination unit searches the information storage unit to extract multiple pieces of extracted information associated with each of the multiple pieces of information relating to the attributes, and determines that the multiple pieces of extracted information will be the policy information. The acquisition device described in [2] above.

[0043] [4] The policy determination unit further determines a plurality of priority information indicating the respective priority for each of the plurality of extracted information, and includes the plurality of priority information in the policy information. The acquisition device described in [3] above.

[0044] [5] The request acquisition unit further acquires purpose information regarding the purpose of acquiring the response text data, The policy decision unit determines the plurality of priority information for each of the plurality of extracted information by performing calculations based on the objective information. The acquisition device described in [4] above.

[0045] The block diagram used in the description of the above embodiment shows functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may be realized by combining the above one device or the above multiple devices with software.

[0046] Functions include, but are not limited to, judgment, decision, judgment, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. As mentioned above, the method of implementation is not particularly limited.

[0047] For example, the RAG system 20 in one embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure. Figure 8 is a diagram showing an example of the hardware configuration of the RAG system 20 according to one embodiment of the present disclosure. The RAG system 20 described above may be physically configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc. Note that the RAG system 20 may be configured as a computer device including at least one processor such as a CPU or GPU, may be configured as a computer device including multiple processors, or may be configured as including multiple computer devices.

[0048] In the following explanation, the term "device" can be interpreted as a circuit, device, unit, etc. The hardware configuration of the RAG system 20 may include one or more of the devices shown in the figure, or it may be configured to omit some of the devices.

[0049] Each function in the RAG system 20 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of the reading and writing of data in the memory 1002 and storage 1003.

[0050] The processor 1001 controls the entire computer, for example, by running the operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. For example, the above-mentioned response acquisition unit 21, request acquisition unit 22, policy decision unit 23, prompt generation unit 24, information acquisition unit 25, etc., may be implemented by the processor 1001.

[0051] Furthermore, the processor 1001 reads programs (program code), software modules, data, etc., from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the response acquisition unit 21, request acquisition unit 22, policy decision unit 23, prompt generation unit 24, and information acquisition unit 25 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be implemented similarly. The above-described various processes have been explained as being executed by one processor 1001, but they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may be transmitted from a network via a telecommunications line.

[0052] Memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. Memory 1002 may also be called a register, cache, main memory, etc. Memory 1002 can store executable programs (program code), software modules, etc., for carrying out a processing method according to one embodiment of this disclosure.

[0053] Storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. Storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0054] The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include high-frequency switches, duplexers, filters, frequency synthesizers, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the response acquisition unit 21, request acquisition unit 22, information acquisition unit 25, etc., described above may be implemented by the communication device 1004.

[0055] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0056] Furthermore, each device, such as the processor 1001 and memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.

[0057] Furthermore, the RAG system 20 may include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be implemented by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0058] Information notification is not limited to the embodiments described herein and may be carried out by other means. For example, information notification may be carried out by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block))), other signals, or combinations thereof. RRC signaling may also be called RRC messages, and may be, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc.

[0059] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described herein may be reordered, provided they are consistent with each other. For example, the methods described herein present various step elements in an exemplary order and are not limited to that specific order.

[0060] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be sent to other devices.

[0061] The determination may be made by a value represented by 1 bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0062] Each aspect / embodiment described herein may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0063] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Accordingly, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0064] In other words, in the RAG system 20 of this disclosure, the request acquisition unit 22 may acquire a creation request that includes multiple pieces of information about the attributes of the report reader. In this case, the policy decision unit 23 searches the policy information storage unit 28 to extract multiple pieces of policy information associated with each of the multiple pieces of attribute information, and decides to include these multiple pieces of policy information as information to be included in the prompt. This makes it possible to obtain evaluations of questionnaire responses that are useful to multiple reader users.

[0065] Furthermore, in the RAG system 20 of this disclosure, the request acquisition unit 22 may acquire the creation request including survey purpose information regarding the purpose of acquiring the response text data. In this case, the policy decision unit 23 may determine multiple priority pieces of information for each of the extracted policy pieces by inputting the survey purpose information into a learning model and having the learning model perform calculations, similar to the embodiment described above. In this case, it is possible to provide multiple reader users with an evaluation of useful survey responses that takes into account the purpose of acquiring the survey responses.

[0066] Furthermore, in the RAG system 20 of this disclosure, survey response data may be obtained from terminal 10B by including it in the survey creation request. The survey response data may also include identification information that identifies the survey respondent and attribute information that indicates the respondent's attributes. This attribute information may be obtained in the RAG system 20 by referring to the attribute information storage unit 27 based on the identification information. In this case, the prompt generation unit 24 can include the respondent's attribute information along with the survey response data in the prompt.

[0067] Furthermore, in the RAG system 20 of this disclosure, reader attributes relating to the attributes of the report reader may be extracted from the attribute information stored in the attribute information storage unit 27, and the extracted reader attributes may be included in the prompt. Figure 7 is a flowchart showing the procedure for report acquisition processing by the RAG system 20 according to this modified example. The processing in steps S101 to S102 and S104 to S107 is the same as the processing in steps S01 to S06 in the embodiment described above. In step S103, attribute information associated with the user ID of terminal 10B is extracted from the attribute information stored in the attribute information storage unit 27.

[0068] Furthermore, in the RAG system 20 of this disclosure, a portion of the policy information (for example, information on the purpose of the report) may be obtained from the terminal 10B by including it in the questionnaire creation request. In that case, the prompt generation unit 24 can include the policy information obtained by including it in the creation request in the prompt.

[0069] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0070] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technologies (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0071] The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0072] In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of the channel and symbol may be a signal (signaling). Also, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, cell, frequency carrier, etc.

[0073] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a given value, or other corresponding information. For example, wireless resources may be indicated by an index.

[0074] The names used for the parameters described above are not restrictive in any way. Furthermore, formulas and other expressions using these parameters may differ from those expressly disclosed in this disclosure. Various channels (e.g., PUCCH, PDCCH, etc.) and information elements can be identified by any suitable name, and therefore, the various names assigned to these various channels and information elements are not restrictive in any way.

[0075] In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably.

[0076] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other appropriate term.

[0077] As used in this disclosure, the terms “determining” and “determining” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in a table, database, or other data structure), or ascertaining. “Determining” may also include, for example, receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, or accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

[0078] The terms “connected,” “coupled,” or any variation thereof, mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain.

[0079] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0080] Any reference to elements using designations such as “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to first and second elements do not imply that only two elements may be adopted, or that the first element must precede the second element in any way.

[0081] Where the terms “include,” “including,” and their variations are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0082] In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0083] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different." [Explanation of symbols]

[0084] 10A, 10B... Terminals, 20... RAG system, 22... Request acquisition unit, 23... Policy decision unit, 24... Prompt generation unit (information generation unit), 25... Information acquisition unit.

Claims

1. A request acquisition unit that acquires requests to create reports for multiple response text data for each respondent, A policy decision unit determines policy information regarding the report creation policy based on the aforementioned creation request, An information generation unit that generates input information requesting the creation of a report based on the policy information and the plurality of response text data, An information acquisition unit that acquires the report by inputting the aforementioned input information into a generating AI model, An acquisition device equipped with the following features.

2. The aforementioned request for creation includes information about the attributes of the reader of the report, The policy determination unit extracts information associated with the attribute information by searching the information storage unit, and determines the extracted information as the policy information. The acquisition device according to claim 1.

3. The creation request includes multiple pieces of information regarding the attribute, The policy determination unit searches the information storage unit to extract multiple pieces of extracted information associated with each of the multiple pieces of information relating to the attributes, and determines that the multiple pieces of extracted information will be the policy information. The acquisition device according to claim 2.

4. The policy determination unit further determines a plurality of priority information indicating the respective priority for each of the plurality of extracted information, and includes the plurality of priority information in the policy information. The acquisition device according to claim 3.

5. The request acquisition unit further acquires purpose information regarding the purpose of acquiring the response text data, The policy decision unit determines the plurality of priority information for each of the plurality of extracted information by performing calculations based on the objective information. The acquisition device according to claim 4.

6. An acquisition method performed by an acquisition device, A request acquisition step to obtain a request to create a report for multiple response text data for each respondent, A policy decision step in which policy information regarding the report creation policy is determined based on the aforementioned creation request, Information generation step includes generating input information that includes the policy information and the plurality of response text data, and that requests the creation of a report based on the plurality of response text data, An information acquisition step in which the report is obtained by inputting the aforementioned input information into a generating AI model, A method of acquisition that includes the necessary components.

Images