Information processing device, information processing method, and program

Abstract

The present invention provides an information processing device, an information processing method, and a program that can obtain answers to the response items requested by the user. [Solution] One aspect of the information processing device of the present disclosure includes: a receiving unit that receives input data entered by a user; an output unit that generates and outputs answers to a plurality of items based on the input data; and a display control unit that displays a display screen having an individual generation button that generates and outputs answers to items one by one, and a batch generation button that generates and outputs answers to a plurality of items simultaneously.

Description

Technical Field

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

Background Art

[0002] Conventionally, conversational AI services using generative AI (Generative Artificial Intelligence) have been known. For example, Patent Document 1 discloses a technique for providing an answer while referring to an appropriate document in response to a user's question using such generative AI.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In such a conversational AI service, when an answer to the content instructed to the generation model (generative AI) is composed of a plurality of answer items, the user may want to obtain answers to all answer items, or may be satisfied with answers to some of the answer items. However, conventional conversational AI services cannot meet such user demands and there is room for improvement.

[0005] The present disclosure has been made in view of the above circumstances, and an object thereof is to provide an information processing apparatus, an information processing method, and a program capable of obtaining an answer to an answer item desired by a user.

Means for Solving the Problems

[0006] One aspect of the information processing device of the present disclosure includes a reception unit that receives input data entered by a user, an output unit that generates and outputs answers to a plurality of items based on the input data, and a display control unit that displays a display screen having an individual generation button that generates and outputs answers to items one by one, and a batch generation button that generates and outputs answers to a plurality of items simultaneously.

[0007] One aspect of the information processing method of the present disclosure includes a reception step in which a reception unit receives input data entered by a user; an output step in which an output unit generates and outputs answers to a plurality of items based on the input data; and a display control step in which a display control unit displays a display screen having an individual generation button that generates and outputs answers to items one by one, and a batch generation button that generates and outputs answers to a plurality of items simultaneously.

[0008] One aspect of the program of this disclosure causes a computer to execute a reception step for receiving input data entered by a user, an output step for generating and outputting answers to a plurality of items based on the input data, an individual generation button for generating and outputting answers to items one by one, and a batch generation button for generating and outputting answers to a plurality of items simultaneously. [Effects of the Invention]

[0009] According to this disclosure, it is possible to provide an information processing device, an information processing method, and a program that can obtain answers to the response items requested by the user. [Brief explanation of the drawing]

[0010] [Figure 1] Figure 1 is a block diagram showing an example of the system configuration of the data generation system of this embodiment. [Figure 2] Figure 2 is a block diagram showing an example of the hardware configuration of the information processing device of this embodiment. [Figure 3]Figure 3 is a block diagram showing an example of the functional configuration of the information processing device according to this embodiment. [Figure 4] Figure 4 shows an example of the UI screen of the AI ​​service for generating documents according to this embodiment. [Figure 5] Figure 5 shows an example of input data entered into the input area of ​​this embodiment. [Figure 6] Figure 6 shows an example of a template for batch generation in this embodiment. [Figure 7] Figure 7 shows an example of a template for individual generation according to this embodiment. [Figure 8] Figure 8 shows an example of the first answer displayed in the output area of ​​this embodiment. [Figure 9] Figure 9 shows an example of the second answer displayed in the output area of ​​this embodiment. [Figure 10] Figure 10 is a flowchart showing an example of the data generation process performed in the information processing device of this embodiment. [Figure 11] Figure 11 is an explanatory diagram showing an example of the individual generation method for Modification Example 1. [Figure 12] Figure 12 shows an example of the UI screen for Modification Example 2. [Figure 13] Figure 13 shows an example of a template for batch generation of Modification Example 3. [Modes for carrying out the invention]

[0011] Hereinafter, embodiments of the present disclosure (hereinafter simply referred to as "these embodiments") will be described in detail with reference to the drawings. However, this disclosure is not limited to the following embodiments. Furthermore, the following embodiments and their variations can be combined as appropriate.

[0012] Hereinafter, the method of the present disclosure will be described by taking as an example a service that generates materials using generative AI (hereinafter sometimes referred to as "material generation AI service"). Specifically, when causing a generation model (generative AI) to generate an answer (material) composed of a plurality of answer items based on a user's input, a method of allowing the user to select whether to generate answers for each answer item collectively or individually will be described. However, the present disclosure is not limited thereto.

[0013] First, the configuration of the material generation system of the present embodiment will be described.

[0014] FIG. 1 is a block diagram showing an example of the system configuration of the material generation system 1 of the present embodiment. As shown in FIG. 1, the material generation system 1 includes an information processing device 10 and a generation model 20.

[0015] The information processing device 10 and the generation model 20 are connected via a network 2. The network 2 can be realized by at least any one of, for example, the Internet and a LAN (Local Area Network). The network 2 may be a wired network, a wireless network, or a mixture of a wired network and a wireless network.

[0016] The information processing device 10 is a terminal device used by a user who uses the material generation AI service, and examples include, but are not limited to, a PC (Personal Computer), a tablet terminal, or a smartphone.

[0017] The generation model 20 is a natural language processing model called so-called generative AI (Generative Artificial Intelligence) and provides a service using natural language processing. In the present embodiment, the case where the generation model 20 is an interactive AI service obtained by fine-tuning a large language model (LLM: Large Language Models) will be described as an example, but the present disclosure is not limited thereto.

[0018] Figure 2 is a block diagram showing an example of the hardware configuration of the information processing device 10 of this embodiment. As shown in Figure 2, the information processing device 10 comprises a control device 11, a main memory 12, an auxiliary storage device 13, a communication device 14, an input device 15, a display device 16, and various buses 19. The control device 11, main memory 12, auxiliary storage device 13, communication device 14, input device 15, and display device 16 are connected via various buses 19. Thus, the information processing device 10 of this embodiment has a general hardware configuration using a normal computer.

[0019] The control device 11 controls the overall operation of the information processing device 10. The control device 11 may be, for example, at least one of a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit), but is not limited to these. There may be one or more CPUs or GPUs, and they may be single-core or multi-core.

[0020] Examples of main memory 12 include, but are not limited to, ROM (Read Only Memory) and RAM (Random Access Memory). ROM stores various programs, such as programs for controlling the information processing device 10 and programs for realizing the data generation AI service. RAM is used as a workspace when the control device 11 performs various controls based on the programs stored in ROM.

[0021] The auxiliary storage device 13 stores the various programs described above and various data used to realize the data generation AI service. The various programs described above only need to be stored in at least one of the main storage device 12 and the auxiliary storage device 13. Examples of the auxiliary storage device 13 include, but are not limited to, at least one of existing storage devices capable of magnetic, electrical, or optical storage, such as an HDD (Hard Disk Drive), SSD (Solid State Drive), and DVD (Digital Versatile Disc). The auxiliary storage device 13 may be built into the information processing device 10 or externally connected to the information processing device 10 via an interface such as USB (Universal Serial Bus). Furthermore, the auxiliary storage device 13 may be a NAS (Network Attached Storage) connected via a network such as a LAN or WAN (Wide Area Network).

[0022] The communication device 14 is used to communicate with the generative model 20 and the like via the network 2. Examples of the communication device 14 include, but are not limited to, a communication device for a wired LAN or a wireless communication device for a wireless LAN.

[0023] The input device 15 is used by the user for various inputs, selections, and specifications, and serves as a user interface between the user and the system. Examples of input devices 15 include, but are not limited to, keyboards, mice, and touch panels. The input device 15 may be built into the information processing device 10 or connected externally to the information processing device 10 via an interface such as USB.

[0024] The display device 16 displays various screens and serves as a user interface between the user and the device. Examples of the display device 16 include, but are not limited to, liquid crystal displays, organic electro-luminescence (OLED) displays, and touch panel displays. The display device 16 may be an internal display built into the information processing device 10, or an external display connected to the information processing device 10 via a display interface such as HDMI®.

[0025] In addition to the above configuration, the information processing device 10 may also be equipped with hardwired circuits such as ICs (Integrated Circuits), ASICs (Application Specific Integrated Circuits), and FPGAs (Field-Programmable Gate Arrays) that are specific to the information processing device 10.

[0026] Figure 3 is a block diagram showing an example of the functional configuration of the information processing device 10 in this embodiment. As shown in Figure 3, the information processing device 10 includes a display control unit 101, a reception unit 103, a generation unit 105, an acquisition unit 107, and an output unit 109. The display control unit 101, reception unit 103, generation unit 105, acquisition unit 107, and output unit 109 can be realized, for example, by the control device 11, main memory 12, and communication device 14 described in Figure 2. The control device 11 reads the program for realizing the data generation AI service stored in the main memory 12 (ROM) or auxiliary memory 13 and expands it into the main memory 12 (RAM). The control device 11 realizes each of the above-mentioned functional units by executing various processes according to the expanded program. Here, the case in which each of the above-mentioned functional units is realized as software has been explained as an example, but at least a part of each of the above-mentioned functional units may be realized as hardware. In this case, the functional unit to be realized as hardware can be realized, for example, by the hardwired circuit described above. Furthermore, any of the above-mentioned functional units may be implemented through the cooperation of software and hardware.

[0027] Furthermore, the information processing device 10 of this embodiment does not necessarily require all of the above-described functional units to be part of its essential configuration; at least some of the functional units can be omitted.

[0028] In the following, this embodiment will be described using, as appropriate, a case in which a draft of a news release is generated from user input information, but this embodiment is not limited to this.

[0029] The display control unit 101 displays the UI (User Interface) screen (an example of a display screen) of the document generation AI service on the display device 16 in response to a user's operation to start the document generation AI service using an input device 15 or the like. Examples of operations to start the document generation AI service include, but are not limited to, launching an application that implements the document generation AI service or connecting to (accessing) a Web service that implements the document generation AI service.

[0030] Figure 4 shows an example of the UI screen 201 of the document generation AI service of this embodiment, and shows the initial state (initial screen) of the UI screen 201 displayed when the document generation AI service is started. Note that in the UI screen 201 shown in Figure 4, some of the elements that make up the screen have been appropriately omitted for explanatory purposes.

[0031] As shown in Figure 4, the UI screen 201 consists of an input area 211, a batch generation button 231 (an example of the first image), and an output area 241.

[0032] Input area 211 is a display area for displaying input data (case information) entered by the user. Input area 211 includes a predetermined number of input items and input fields associated with each of those input items. In the example shown in Figure 4, the input item "Who and Who" belonging to the main item "The most important news to convey in this announcement" is associated with input field 212, the input item "What" is associated with input field 213, and the input item "When" is associated with input field 214. In each input field, the user enters content corresponding to the corresponding input item in order to generate a draft of the news release. Alternatively, the user may upload a file in CSV (Comma Separated Values) format or similar so that the content corresponding to the input item is entered into each input field.

[0033] The batch generation button 231 is a UI component (UI image) that causes the generation model 20 to generate a batch of responses (draft news release text) consisting of multiple response items based on the input data displayed (entered) in the input area 211.

[0034] The output area 241 is a display area that displays the response (draft of the news release) generated by the generation model 20 based on the input data displayed in the input area 211. The output area 241 includes a predetermined number of response items, a response field associated with each of the response items, an individual generation button associated with each of the response items (an example in the second image), and a restore button associated with each of the response items.

[0035] In the example shown in Figure 4, the answer item "Title / Subtitle" is associated with answer field 251, individual generation button 253, and restore button 255. The answer item "Lead" is associated with answer field 261, individual generation button 263, and restore button 265. The answer item "Background" is associated with answer field 271, individual generation button 273, and restore button 275.

[0036] Each answer field displays the corresponding answer generated by the generation model 20. Each individual generation button is a UI component (UI image) for individually generating answers corresponding to the answer items. Each restore button is a UI component (UI image) for restoring the answer content corresponding to the answer item to the previous content.

[0037] The reception unit 103 receives input data entered by the user. The input data consists of input sentences entered by the user in each of a predetermined set of input fields. Specifically, the reception unit 103 receives input sentences entered by the user in each input field included in the input area 211 on the UI screen 201 using an input device 15 or the like as input data, and the display control unit 101 displays the input sentences entered in each input field.

[0038] Figure 5 shows an example of input data entered into the input area 211 of this embodiment. In addition, the example shown in Figure 5 also shows the input items belonging to the major category "Product Overview / Features," which were not explained in Figure 4.

[0039] In the example shown in Figure 5, the input field "XX Corporation" is entered and displayed in input field 212 for the input field "Who and who...". The input field "What..." is entered and displayed in input field 213 for the input field "Image conversion service utilizing generation AI". The input field "When..." is entered and displayed in input field 214 for the input field "December 2024". Furthermore, the input field "Product / service name is...", which belongs to the major category "Product overview / features", is entered and displayed in input field 215 for the input field "XX Image Conversion AI". Furthermore, the input field "Target customer base..." is entered and displayed in input field 216 for the input field "Customers who handle images in their work". Furthermore, the input field "Product / service is..." is entered and displayed in input field 217 for the input field "I want to convert images and photos to high resolution at low cost". Furthermore, regarding the input field "For customers who will be implementing the system...", the input text "It can achieve twice the resolution of other companies' systems. Costs can be halved." is entered and displayed in input field 218.

[0040] The input fields used to generate the news release draft are not limited to the examples above. For example, under a major category such as "Product Overview / Features," you may further use at least one of the following input fields: "Features of this product / service," "Challenges and Needs of Consumers Using the Product / Service Through Customers," "Benefits for Consumers," and "Price of the Product / Service." Alternatively, you may create a major category such as "Background and Challenges of Product / Service Development," and under that category, at least one of the following input fields may be used: "Social Issues and Trends Underlying the Provision of the Product / Service," "Sources Providing the Basis for Social Issues and Trends," "Contribution of the Product / Service to Social Issues and Trends," "Internal Policies and Plans that Form the Basis for Communicating the Product / Service," and "Past Businesses, Products, and Services Related to this Product / Service." Furthermore, you may create a major category such as "Future Developments," and under that category, at least one of the following input fields may be used: "Sales Target or Number of Installation Target for the Product / Service," and "Future Feature Additions."

[0041] The generation unit 105 generates a prompt that includes the input data received by the reception unit 103. Specifically, when the user performs a first operation, the generation unit 105 generates a first prompt to cause the generation model 20 to generate a first response using the input data received by the reception unit 103. Furthermore, when the user performs a second operation, the generation unit 105 generates a second prompt to cause the generation model 20 to generate a second response using the input data received by the reception unit 103.

[0042] The first operation is the operation of selecting the batch generation button 231, for example, the operation of pressing the batch generation button 231 using the input device 15 or the like. The first answer is an answer consisting of the answer content for each of the above-mentioned multiple answer items, that is, an answer that includes the answer content for all answer items. In other words, in this embodiment, when the receiving unit 103 receives the operation of pressing the batch generation button 231, the generation unit 105 generates a first prompt, which is a prompt to cause the generation model 20 to generate the answer content for all answer items in a batch.

[0043] The second operation is the operation of selecting an individual generation button, for example, the operation of pressing an individual generation button using an input device 15 or the like. The second answer is the answer consisting of the content of the answers to the predetermined answer items associated with the second operation from among the multiple answer items described above, that is, the answer to the predetermined answer items associated with the second operation. Specifically, the predetermined answer items associated with the second operation are the answer items to which the individual generation buttons are associated. For example, the individual generation button 253 (the operation of pressing it) is associated with the answer item "Title / Subtitle", the individual generation button 263 (the operation of pressing it) is associated with the answer item "Lead", and the individual generation button 273 (the operation of pressing it) is associated with the answer item "Background".

[0044] In other words, in this embodiment, when the receiving unit 103 receives an operation to press an individual generation button, the generation unit 105 generates a second prompt, which is a prompt to cause the generation model 20 to individually generate the answer content for the answer item associated with the pressed individual generation button.

[0045] In this embodiment, the generation unit 105 generates a first prompt by including the input data in a template for batch generation, and generates a second prompt by including the input data in a template for individual generation. For example, the templates for batch generation and individual generation are stored in an auxiliary storage device 13 or the like. In this embodiment, a template for individual generation is prepared for each answer item, but it is not limited to this. When the user presses the batch generation button 231, the generation unit 105 generates a first prompt by including the input data received by the reception unit 103 in the batch generation template. When the user presses the individual generation button, the generation unit 105 generates a second prompt by including the input data received by the reception unit 103 in the individual generation template. Templates stored in the auxiliary storage device 13 or the like may be added by the user. The generation unit 105 may also generate prompts by including input items in the input data (input sentences). In other words, multiple prompts may be generated by using input data that consists of sets of multiple input items and the input sentences for those input items.

[0046] Figure 6 shows an example of a batch generation template 310 of this embodiment. In the template 310 shown in Figure 6, the instruction content indicated by reference numeral 311 corresponds to a system prompt for defining the behavior of the generation model 20. The instruction content indicated by reference numeral 311 defines that the user will create a news release article as a public relations expert.

[0047] Furthermore, in the template 310 shown in Figure 6, the instructions indicated by reference numerals 313 to 319 correspond to user prompts that instruct the generation model 20 to make a specific request (generation of the first response). The instructions indicated by reference numerals 313 and 317 correspond to the task requested from the generation model 20 (generation of a draft of the news release), reference numeral 315 indicates the section where the input data received by the reception unit 103 is inserted, and the instructions indicated by reference numeral 319 correspond to the output format of the response requested from the generation model 20.

[0048] Figure 7 shows an example of a template 320 for individual generation in this embodiment, specifically a template for the answer item "Title / Subtitle". In the template 320 shown in Figure 7, the instruction content indicated by reference numeral 321 corresponds to a system prompt for defining the behavior of the generation model 20. The instruction content indicated by reference numeral 321 adds underlined content to the instruction content indicated by reference numeral 311 (see Figure 6), and defines the task as creating a title for a news release article as a public relations professional.

[0049] Furthermore, in the template 320 shown in Figure 7, the instructions indicated by reference numerals 323 to 329 correspond to user prompts that instruct the generation model 20 to make a specific request (generation of the second response). The instructions indicated by reference numerals 323 and 327 correspond to the task requested from the generation model 20 (generation of the news release title / subtitle), reference numeral 315 indicates the section where the input data received by the reception unit 103 is inserted, and the instructions indicated by reference numeral 319 correspond to the output format of the response requested from the generation model 20.

[0050] Thus, the template 320 shown in Figure 7 differs from the template 310 shown in Figure 6 in that the instructions indicated by symbols 321, 323, 327, and 329 are specifically for generating titles / subtitles.

[0051] When the generation unit 105 generates a first prompt using the template 310, the first prompt includes a system prompt for defining the behavior of the generation model 20 and a user prompt that instructs the generation model 20 to generate answers for each of the multiple answer items. When the generation unit 105 generates a second prompt using the template 320, the second prompt includes a system prompt for defining the behavior of the generation model 20 and a user prompt that instructs the generation model 20 to generate answers for predetermined answer items (answer items such as title / subtitle associated with the individual generation button 253).

[0052] As is clear from the descriptions in Figures 6 and 7, the system prompt included in the second prompt has different content from the system prompt included in the first prompt, and the user prompt included in the second prompt has different content from the user prompt included in the first prompt.

[0053] Furthermore, the multiple answer items displayed in the output area 241 mentioned above are set to correspond to the output format of the first prompt (the answer output format indicated by reference numeral 319 in Figure 6).

[0054] When the user performs a first operation, that is, when the generation unit 105 generates a first prompt, the acquisition unit 107 inputs the first prompt to the generation model 20 to obtain the first answer. Specifically, the acquisition unit 107 inputs the first prompt generated by the generation unit 105 to the generation model 20. The generation model 20 generates the answer content for each answer item indicated by the input first prompt and outputs it to the information processing device 10 as the first answer. The acquisition unit 107 obtains the first answer from the generation model 20.

[0055] Furthermore, when a second operation is performed by the user, that is, when a second prompt is generated by the generation unit 105, the acquisition unit 107 inputs the second prompt to the generation model 20 to obtain the second answer. Specifically, the acquisition unit 107 inputs the second prompt generated by the generation unit 105 to the generation model 20. The generation model 20 generates the answer content for the predetermined answer items instructed by the input second prompt and outputs it to the information processing device 10 as the second answer. The acquisition unit 107 obtains the second answer from the generation model 20.

[0056] When the user performs the first operation, that is, when the acquisition unit 107 acquires the first response, the output unit 109 outputs the first response, which is the answer to each of the multiple answer items generated by the generation model 20 based on the input data. Specifically, when the user performs the first operation, the output unit 109 displays the answers to each of the multiple answer items included in the first response in the corresponding answer fields within the output area 241.

[0057] For example, suppose the first response is a response generated by the generation model 20 based on the first prompt generated using the input data shown in Figure 5 and the template 310 shown in Figure 6. Since the first response contains the response content according to the response output format indicated by reference numeral 319, the output unit 109 displays the response content of each response item included in the first response in the corresponding response field of the output area 241.

[0058] Figure 8 shows an example of the first response displayed in the output area 241 of this embodiment. Note that the example shown in Figure 8 also shows the response item "Features," which was omitted from the explanation in Figure 4. In the output area 241 shown in Figure 8, the response fields 251 for the "Title / Subtitle," 261 for the "Lead Text," 271 for the "Background," and 281 for the "Features" each display the corresponding response content included in the first response generated by the generation model 20.

[0059] Furthermore, when a second operation is performed by the user, that is, when a second response is obtained by the acquisition unit 107, the output unit 109 outputs the second response, which is the response to a predetermined response item associated with the second operation from among the multiple response items generated by the generation model 20 based on the input data. Specifically, when a second operation is performed by the user, the output unit 109 outputs the response to the predetermined response item associated with the second operation as the output of the second response, displaying it in the response field of the predetermined response item in the output area 241.

[0060] For example, suppose the second response is a response generated by the generation model 20 based on the second prompt generated using the input data shown in Figure 5 and the template 320 shown in Figure 7. Since the content of the second response is written according to the response output format indicated by the reference numeral 329, the output unit 109 displays the content of the "Title / Subtitle" response item included in the second response in the response field 251 included in the output area 241.

[0061] In this embodiment, the output of the second answer by the output unit 109, that is, the user pressing the individual generation button, is assumed to be performed for the purpose of correcting (regenerating) the answer after the batch generation of answers has been performed (while the answer content is displayed in each answer field), as shown in Figure 8. In other words, if the second operation is performed after the first answer has been displayed and output by the output unit 109, the second answer will be displayed and output, and the answers to the predetermined answer items included in the displayed first answer will be updated. In this way, if the answer content of some answer items is correct but the answer content of others is not, the answer can be corrected in a shorter and more efficient time than redoing the batch generation of answers. Furthermore, it is possible to prevent situations where the answer content of answer items that are not problematic is also corrected, as can happen when redoing the batch generation of answers.

[0062] Furthermore, when a user modifies an answer, they may or may not modify the input text for each input item in the input area 211 before pressing the individual generation button. For example, as in this embodiment, if the instructions for the answer item to be modified differ between the first prompt for batch generation and the second prompt for individual generation, it can be expected that different answers will be generated without modifying the input text. Also, if different generation models are used for batch generation and individual generation, it can be expected that different answers will be generated without modifying the input text.

[0063] However, the output of the second response by the output unit 109, that is, the user pressing the individual generation button, is not limited to cases where it is performed for the purpose of correcting the response. For example, it may be performed when the batch generation of responses has not been performed (when the response content is not displayed in each response field), as shown in Figure 4. This is useful, for example, when issuing a news release jointly with another company, where the response content for other response items is specified by the other company, and it is necessary to generate the response content for some response items, or vice versa.

[0064] Figure 9 shows an example of a second answer displayed in the output area 241 of this embodiment. Note that the example in Figure 9 also shows the answer item "Features," which was omitted from the explanation in Figure 4. In Figure 9, the individual generation button 253 was pressed in the state shown in Figure 8, so the answer content of the answer item "Title / Subtitle" displayed in the answer field 251 has been updated to the second answer. Note that, as explained in Figure 7, the template 320 for individual generation of the answer item "Title / Subtitle" has different content from the template 310 for batch generation shown in Figure 6. For this reason, the second answer displayed in the answer field 251 differs from the answer content of "Title / Subtitle" in the first answer, and the content underlined is added to the answer content of the answer field 251 shown in Figure 8.

[0065] If the user dislikes the content of the second answer displayed in answer field 251 and wants to revert to the first answer, they can press the restore button 255. When the restore button 255 is pressed, the output unit 109 displays the content of the answer field 251 that was stacked when the individual generation button 253 was pressed back into the answer field 251, returning it to the state shown in Figure 8.

[0066] The output unit 109 may output the response (draft) displayed in the output area 241 to a file based on user input. Furthermore, the response (draft) displayed in the output area 241 may be edited or evaluated by the user.

[0067] Next, the operation of the data generation system of this embodiment will be described.

[0068] Figure 10 is a flowchart showing an example of the data generation process performed by the information processing device 10 of this embodiment.

[0069] First, the display control unit 101 displays the UI screen of the document generation AI service on the display device 16 when the user initiates the document generation AI service (step S101).

[0070] Next, the reception unit 103 receives the input text entered by the user in each input field included in the input area 211 on the UI screen 201 as input data (step S103), and the display control unit 101 displays the input text entered in each input field.

[0071] Next, the reception unit 103 waits for the user to press the batch generation button 231 (No in step S105), and when it receives confirmation that the batch generation button 231 has been pressed (Yes in step S105), the generation unit 105 generates the first prompt (step S107).

[0072] Next, the acquisition unit 107 inputs the first prompt generated by the generation unit 105 into the generation model 20 to obtain the first response (step S109).

[0073] Next, the output unit 109 displays the answers to each of the multiple answer items included in the first answer acquired by the acquisition unit 107 in the corresponding answer fields in the output area 241 (step S111).

[0074] Next, when the reception unit 103 receives a press operation of the user's individual generation button (Yes in step S113), the generation unit 105 generates a second prompt (step S115).

[0075] Next, the acquisition unit 107 inputs the second prompt generated by the generation unit 105 into the generation model 20 to obtain the second response (step S117).

[0076] Next, the output unit 109 outputs the answers to the predetermined answer items associated with the second operation as the output of the second response, displaying them in the answer fields of the predetermined answer items within the output area 241, and updating the answer content in the answer fields of the predetermined answer items (step S119).

[0077] Next, when the reception unit 103 receives another press operation from the user for the individual generation button (Yes in step S113), the processes in steps S115 to S119 are performed again.

[0078] On the other hand, once the user finishes pressing the individual generation button (No in step S113), the process ends.

[0079] As described above, in this embodiment, when generating a response (document) consisting of multiple response items based on user input, the user can choose whether to generate the responses for each response item all at once or individually. Therefore, according to this embodiment, the user can obtain the responses for the response items they desire.

[0080] Furthermore, in this embodiment, some of the answers included in the batch-generated responses can be modified individually. Since the second prompt for individual generation has fewer instructions than the first prompt for batch generation, the answers can be modified more quickly and efficiently than redoing the batch generation of responses. In addition, it prevents situations where the content of answers for non-problematic response items is modified, as can occur when redoing the batch generation of responses.

[0081] Furthermore, in this embodiment, if you don't like the modified response generated individually, you can revert to the original response.

[0082] (Variation 1) In the above embodiment, an example was described in which the answer content is generated individually for each answer item. However, in Modification 1, a portion of the answer content may be generated individually. In each of the following modifications, the parts that differ from the above embodiment will be mainly described, and the parts that are the same as the above embodiment will not be described.

[0083] In the modified example 1, when a second operation is performed by specifying a portion of the answer to a predetermined answer item included in the first answer that has been displayed, the output unit 109 displays and outputs a partial answer corresponding to the portion of the answer, which has been generated by the generation model 20 based on the input data, as the second answer, and updates the portion of the answer that has been displayed.

[0084] Figure 11 is an explanatory diagram illustrating an example of the individual generation method of Modification 1, showing an example of the first answer displayed in the output area 241. In the example shown in Figure 11, a portion of the answer content displayed in the answer field 251 has been selected by the user and is shown as the selection range 252. By pressing the individual generation button 253 in this state, the user displays and outputs the partial answer corresponding to the selection range 252 as the second answer, and updates the displayed answer for the selection range 252.

[0085] The method for generating the second response using the generation model 20 may be the same as in the above embodiment. In other words, instead of generating only the partial response corresponding to the selection range 252 using the generation model 20, the entire content of the response item "Title / Subtitle" may be generated by the generation model 20, and the portion corresponding to the selection range 252 may be extracted from the generated response as a partial response and displayed as the second response.

[0086] (Modification 2) In the above embodiment, an example was described in which individual generation is performed for each answer item, but it is also possible to individually generate the answer content for any of the multiple answer items at once.

[0087] Figure 12 shows an example of the UI screen 401 of Modification 2. The UI screen 401 shown in Figure 12 differs from the above embodiment in that the batch generation button and the individual generation button are integrated into the generation button 431 (an example in the first image), and each of the multiple answer items is associated with a checkbox.

[0088] In the example shown in Figure 12, checkbox 453 is associated with the answer item "Title / Subtitle," checkbox 463 is associated with the answer item "Lead," and checkbox 473 is associated with the answer item "Background."

[0089] Each checkbox sets whether or not to generate an answer for the corresponding answer item when the generate button 431 is operated. If checked, the answer will not be generated (non-generated state), and if unchecked, the answer will be generated (generated state).

[0090] Therefore, in the modified example 2, the first operation for generating the answers all at once is to press the generate button 431 without checking the checkboxes for each of the multiple answer items. In other words, the first operation is to set each of the multiple answer items to the generate state and then select the first image.

[0091] Similarly, in the modified example 2, the second operation for individually generating answers involves checking the checkboxes for all answer items except for any answer items that require individual generation, and then pressing the generate button 431. In other words, it involves setting all answer items other than the specified answer items to a non-generated state and then selecting the first image.

[0092] In the example shown in Figure 12, since checkboxes 463 and 473 are checked, when the generate button 431 is pressed, the answer for the "Title / Subtitle" item is generated, and the answer displayed in the answer field 251 is updated.

[0093] In the modified example 2, the output unit 109 displays the answers to each of the multiple answer items in the corresponding answer fields as the output of the first response when the first operation is performed, and displays the answers to the predetermined answer items (answer items whose checkboxes are not checked) in the answer fields of the predetermined answer items as the output of the second response.

[0094] According to Modification 2, since answers for response items that require individual generation can be generated at once, responses can be corrected more quickly and efficiently.

[0095] (Variation 3) In the above embodiment, separate templates were prepared for batch generation and individual generation to generate the first and second prompts. However, in Modification 3, an example is described in which the batch generation template is reused to generate the second prompt.

[0096] Figure 13 shows an example of a template 510 for batch generation of Modification 3. In the template 510 shown in Figure 13, the instruction content indicated by reference numeral 511 corresponds to the system prompt, the instruction content indicated by reference numeral 512 corresponds to the user prompt for the title and subtitle, and the instruction content indicated by reference numeral 514 corresponds to the user prompt for the lead sentence.

[0097] In Modification 3, when the first operation is performed, the generation unit 105 includes the input data in the template 510 and generates a first prompt. In other words, in Modification 3, the first prompt consists of a system prompt and a user prompt that has instructions for each answer item to generate an answer for that answer item in the generation model 20.

[0098] In the modified example 3, when the second operation is performed, the generation unit 105 extracts the system prompt shown by reference numeral 511 and the corresponding user prompt from the template 510, and generates the second prompt including the input data. In other words, in the modified example 3, the second prompt consists of the system prompt and the user prompt for a predetermined answer item associated with the second operation from among the user prompts for each answer item.

[0099] For example, when the generation unit 105 generates a second prompt for the title and subtitle, it extracts the system prompt shown by reference numeral 511 and the user prompt shown by reference numeral 512 from the template 510, and generates the second prompt including the input data. Also, for example, when the generation unit 105 generates a second prompt for the lead sentence, it extracts the system prompt shown by reference numeral 511 and the user prompt shown by reference numeral 514 from the template 510, and generates the second prompt including the input data.

[0100] According to Modification 3, the second prompt can be generated by reusing the template for batch generation, thus increasing its versatility. This is particularly useful when generating the second prompt in Modification 2.

[0101] Furthermore, when generating some of the second prompts, you may reuse the template for batch generation, and when generating other second prompts, you may use the template for individual generation.

[0102] For example, when generating a second prompt for the lead text, the generation unit 105 may reuse template 510 to generate the second prompt, and when generating a second prompt for the title and subtitle, it may use template 320 shown in Figure 7 to generate the second prompt.

[0103] In other words, when generating a second prompt for a lead sentence (an example of a first response item) as a predetermined response item, the generation unit 105 extracts the system prompt shown by reference numeral 511 and the user prompt shown by reference numeral 514 from the template 510, and generates the second prompt by including the input data. Also, when generating a second prompt for a title and subtitle (an example of a second response item) as a predetermined response item, the generation unit 105 generates the second prompt by including the input data in the template 320.

[0104] (Modification 4) In the above embodiment, an example of generating multiple answers using a single generation model 20 was described, but in Modification 4, multiple answers may be generated using multiple generation models. That is, in Modification 4, the generation model for generating the second answer (used when the individual generation button is operated) may be a different generation model from the generation model for generating the first answer (used when the batch generation button is operated). In this case, the generation model for generating the second answer may be a generation model that has better characteristics for generating answers to predetermined answer items than the generation model for generating the first answer.

[0105] For example, a general-purpose generative model may be used to generate the first answer, and a high-accuracy generative model may be used to generate the second answer. Alternatively, a general-purpose generative model may be used to generate the first answer, and a generative model with learned or additionally learned specialized knowledge may be used to generate the second answer. Furthermore, a multimodal generative model may be used to generate the first answer, and an image-specific generative model may be used to generate the second answer.

[0106] Alternatively, for example, the generative model 20 may be configured to change its parameters for each prompt to generate an answer. This method achieves the same effect as generating multiple answers using multiple generative models.

[0107] (Variation 5) In the above embodiment, an example was described in which input data is entered by entering an input sentence for each input item, but the user is not limited to this, and may enter input data in a free format.

[0108] (Experimental variation 6) In the above embodiment, the same input data as the first prompt was used for the second prompt. However, it is also possible to extract the input sentences necessary for individual generation from the input data and use the extracted input sentences as input data for the second prompt.

[0109] (Example 7) In the above embodiment, a first prompt was used to generate the first answer and a second prompt was used to generate the second answer. However, the first prompt may also be used to generate the second answer, and the content of the answers for the necessary answer items may be extracted and output.

[0110] (Variation 8) In the above embodiments and their variations, the example of implementing the generation model 20 as a cloud service was used for explanation, but the generation model 20 may also be included in the information processing device 10. In this case, the generation model 20 can be implemented, for example, as an AI chat service that fine-tunes a small language model (SLM).

[0111] (program) The programs executed by the information processing devices of the above embodiments and each of the above modifications are provided in installable or executable file format, stored on a computer-readable storage medium such as a CD-ROM, CD-R, memory card, DVD, or flexible disk (FD).

[0112] Furthermore, the programs executed by the information processing devices of the above embodiments and their respective modifications may be stored on a computer connected to a network such as the Internet and provided by allowing downloads via the network. Alternatively, the programs executed by the information processing devices of the above embodiments and their respective modifications may be provided or distributed via a network such as the Internet. Furthermore, the programs executed by the information processing devices of the above embodiments and their respective modifications may be pre-installed in ROM or the like and provided.

[0113] The programs executed in the information processing devices of the above embodiments and their respective modifications are configured as modules for realizing the above-described parts on a computer. In actual hardware, for example, the CPU reads the program from the HDD into RAM and executes it, thereby realizing the above-described parts on the computer.

[0114] The above embodiments and their respective modifications are merely examples of how this disclosure may be implemented, and they do not restrict the technical scope of this disclosure. Therefore, this disclosure can be implemented in various ways without departing from its essence or its main features. For example, the above embodiments and their respective modifications may be combined as appropriate on a component basis. Also, for example, some components may be removed from the total components in the above embodiments and their respective modifications.

[0115] This disclosure also includes the following aspects:

[0116] (1) A reception unit that receives input data entered by the user, When the user performs a first operation, the output unit outputs a first response, which is the response to each of the multiple response items generated by the generation model based on the input data; and when the user performs a second operation, the output unit outputs a second response, which is the response to a predetermined response item associated with the second operation among the multiple response items generated by the generation model based on the input data. An information processing device equipped with the following features.

[0117] (2) If the second operation is performed after the first response has been displayed and outputted, the output unit displays and outputs the second response and updates the responses to the predetermined response items included in the first response that has been displayed and outputted. The information processing device described in (1) above.

[0118] (3) When the second operation is performed with a portion of the answer to the predetermined answer item included in the first answer that has been displayed, the output unit displays and outputs a partial answer corresponding to the portion of the answer that has been generated by the generation model based on the input data as the second answer, and updates the portion of the answer that has been displayed. The information processing device described in (2) above.

[0119] (4) The first operation is an operation to select the first image, The second operation is the operation of selecting a second image associated with the predetermined answer item. An information processing device as described in any one of the above items (1) to (3).

[0120] (5) The display control unit further comprises an input area for displaying the input data, an output area including an answer field associated with each of the plurality of answer items, and a display screen that includes the first image and a second image associated with each of the plurality of answer items, When the first operation is performed, the output unit displays the answers to each of the multiple answer items in the corresponding answer fields as the output of the first response, and when the second operation is performed, it displays the answers to the predetermined answer items in the answer fields of the predetermined answer items as the output of the second response. The information processing device described in (4) above.

[0121] (6) The first operation is an operation to set each of the multiple response items to a generation state and select the first image, The second operation is to set the answer items other than the predetermined answer items among the plurality of answer items to a non-generated state and select the first image. An information processing device as described in any one of the above items (1) to (3).

[0122] (7) The display control unit further comprises an input area for displaying the input data, an output area including answer fields associated with each of the plurality of answer items, and the first image, which displays a display screen. When the first operation is performed, the output unit displays the answers to each of the multiple answer items in the corresponding answer fields as the output of the first response, and when the second operation is performed, it displays the answers to the predetermined answer items in the answer fields of the predetermined answer items as the output of the second response. The information processing device described in (6) above.

[0123] (8) A generation unit that, when the first operation is performed, generates a first prompt for the generation model to generate the first response using the input data, and when the second operation is performed, generates a second prompt for the generation model to generate the second response using the input data, The system includes an acquisition unit that, when the first operation is performed, inputs the first prompt to the generation model to obtain the first response, and when the second operation is performed, inputs the second prompt to the generation model to obtain the second response. An information processing device as described in any one of the above items (1) to (3).

[0124] (9) The first prompt comprises a system prompt for defining the behavior of the generative model and a user prompt having instructions for the generative model to generate a response to each of the response items, The second prompt comprises the system prompt and the user prompt for the predetermined answer item among the user prompts for each answer item. The information processing device described in (8) above.

[0125] (10) The prescribed response items include the first response item and the second response item, The generation unit generates a second prompt for the first answer item and a second prompt for the second answer item, The first prompt comprises a system prompt for defining the behavior of the generative model, and a user prompt having instructions for the generative model to generate a response to each of the response items. The second prompt for the first answer item comprises the system prompt and the user prompt for the first answer item among the user prompts for each answer item. The system prompt included in the second prompt for the second answer item differs in content from the aforementioned system prompt. The user prompt included in the second prompt for the second answer item differs in content from the user prompt for the second answer item among the user prompts for each answer item. The information processing device described in (8) above.

[0126] (11) The first prompt comprises a system prompt for defining the behavior of the generative model and a user prompt having instructions for causing the generative model to generate answers for each of the plurality of answer items, The system prompt included in the second prompt differs in content from the system prompt mentioned above. The user prompt included in the second prompt has different content from the user prompt mentioned above. The information processing device described in (8) above.

[0127] (12) The generative model used to generate the two responses is a different generative model from the generative model used to generate the one response. An information processing device as described in any one of the above items (1) to (3).

[0128] (13) The generative model used to generate the second response is a generative model that has better characteristics in generating responses to the predetermined response items than the generative model used to generate the first response. The information processing device described in (12) above.

[0129] (14) A reception step in which the reception department receives input data entered by the user, The output unit outputs a first response, which is the response to each of the multiple response items generated by the generation model based on the input data, when the first operation is performed by the user, and outputs a second response, which is the response to a predetermined response item associated with the second operation, which is generated by the generation model based on the input data, when the second operation is performed by the user. Information processing methods including

[0130] (15) A reception step that receives input data entered by the user, An output step in which, when the user performs a first operation, a first response is output, which is the response to each of the multiple response items generated by the generation model based on the input data, and when the user performs a second operation, a second response is output, which is the response to a predetermined response item associated with the second operation among the multiple response items generated by the generation model based on the input data, A program that causes a computer to execute something. [Explanation of symbols]

[0131] 1. Document Generation System 2 Network 10 Information Processing Devices 20 Generative Models 101 Display Control Unit 103 Reception Department 105 Generation part 107 Acquisition Department 109 Output section

Claims

1. A reception unit that receives input data entered by the user, An output unit that generates and outputs answers to multiple items based on the aforementioned input data, A display control unit that displays a display screen having individual generation buttons that generate and output answers for each item one by one, and batch generation buttons that generate and output answers for multiple items simultaneously. An information processing device equipped with the following features.

2. The output unit, when the batch generation button is operated and then the individual generation button is operated, regenerates and updates the answer for the item corresponding to the individual generation button among the multiple items. The information processing apparatus according to claim 1.

3. The output unit, after the batch generation button has been operated, will regenerate and update the portion of the answer corresponding to the individual generation button if a portion of the answer for that item is specified and the individual generation button is operated. The information processing apparatus according to claim 2.

4. The display screen further includes an input area for displaying the input data, an output area including answer fields associated with each of the multiple items, and individual generation buttons associated with each of the multiple items. The output unit, when the batch generation button is operated, displays and outputs each of the answers for the multiple items in the corresponding answer field, and when any of the multiple individual generation buttons is operated, displays and outputs the answer for the item corresponding to the operated individual generation button in the corresponding answer field. The information processing apparatus according to any one of claims 1 to 3.

5. When the batch generation button is operated, the generation unit generates a first prompt to cause the generation model to simultaneously generate answers for the multiple items using the input data, and when the individual generation button is operated, the generation unit generates a second prompt to cause the generation model to generate an answer for the item corresponding to the individual generation button using the input data. The system includes an acquisition unit that, when the batch generation button is operated, inputs the first prompt into the generation model to obtain answers for the multiple items, and when the individual generation button is operated, inputs the second prompt into the generation model to obtain answers for the items corresponding to the individual generation button. The information processing apparatus according to any one of claims 1 to 3.

6. The first prompt comprises a system prompt for defining the behavior of the generative model, and a user prompt for each item that has an instruction to cause the generative model to generate a response to that item. The second prompt comprises the system prompt and the user prompt for the item corresponding to the individually generated button among the user prompts for each item. The information processing apparatus according to claim 5.

7. The aforementioned individual generation button includes a first individual generation button and a second individual generation button. The generation unit generates a second prompt for a first item corresponding to the first individual generation button, and a second prompt for a second item corresponding to the second individual generation button. The first prompt comprises a system prompt for defining the behavior of the generative model, and a user prompt for each item that has an instruction to cause the generative model to generate a response to that item. The second prompt for the first item comprises the system prompt and the user prompt for the first item among the user prompts for each item. The system prompt included in the second prompt for the second item differs in content from the aforementioned system prompt. The user prompt included in the second prompt for the second item is different in content from the user prompt for the second item among the user prompts for each item. The information processing apparatus according to claim 5.

8. The first prompt comprises a system prompt for defining the behavior of the generative model and a user prompt having instructions for causing the generative model to generate answers to each of the multiple items. The system prompt included in the second prompt differs in content from the system prompt mentioned above. The user prompt included in the second prompt has different content from the user prompt mentioned above. The information processing apparatus according to claim 5.

9. The generation model used when the individual generation button is operated is different from the generation model used when the batch generation button is operated. The information processing apparatus according to any one of claims 1 to 3.

10. The generation model used when the individual generation button is operated has superior characteristics in generating answers for the items corresponding to the individual generation button compared to the generation model used when the batch generation button is operated. The information processing apparatus according to claim 9.

11. The reception department receives input data entered by the user in a reception step, The output unit performs an output step in which it generates and outputs answers to multiple items based on the input data, A display control step in which the display control unit displays a display screen having individual generation buttons that generate and output answers for each item one by one, and batch generation buttons that generate and output answers for multiple items simultaneously, Information processing methods including

12. A reception step that accepts input data entered by the user, An output step that generates and outputs answers to multiple items based on the aforementioned input data, A display control step that displays a display screen having individual generation buttons that generate and output answers for each item one by one, and batch generation buttons that generate and output answers for multiple items simultaneously, A program that causes a computer to execute something.

Images