system

Abstract

An object of the system according to the embodiment is to efficiently create a proposal document and a work plan document based on an RFP.SOLUTION: A system according to an embodiment includes a summary generation part, a QA sheet generation part, a proposal generation part, a presentation generation part, and a work plan generation part. The summary generation unit generates a summary of the RFP by reading the RFP using the generation AI. The QA sheet generation part generates a QA sheet for the RFP. The proposal generation unit generates a proposal based on the RFP. The presentation generator generates a presentation based on the proposal. The work plan generation unit generates a work plan based on the RFP.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, creating proposals and work plans based on RFPs was time-consuming and labor-intensive, making it difficult to do so efficiently.

[0005] The system according to the embodiment aims to efficiently create proposals and work plans based on RFPs. [Means for solving the problem]

[0006] The system according to the embodiment includes a summary generation unit, a QA sheet generation unit, a proposal generation unit, a presentation generation unit, and a work plan generation unit. The summary generation unit generates a summary of the RFP by reading the RFP using a generation AI. The QA sheet generation unit generates a QA sheet for the RFP. The proposal generation unit generates a proposal based on the RFP. The presentation generation unit generates a presentation based on the proposal. The work plan generation unit generates a work plan based on the RFP. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently create proposals and work plans based on RFPs. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The automatic generation system according to an embodiment of the present invention reads an RFP and uses a generation AI to automatically generate summaries, QA sheets, proposals, presentations, and work plans. This allows the automatic generation system to streamline responses to RFPs and quickly and accurately create deliverables.

[0029] An automatic generation system according to an embodiment includes a summary generation unit, a QA sheet generation unit, a proposal generation unit, a presentation generation unit, and a work plan generation unit. The summary generation unit reads an RFP, extracts key points, and generates a summary. For example, the generation AI receives the full text of the RFP as input and summarizes information such as the project's objectives, requirements, schedule, and budget. The QA sheet generation unit creates a QA sheet for the customer based on the RFP's contents. For example, the generation AI receives the full text of the RFP and questions from the customer as input, lists questions and confirmations, and generates answers to those questions. The proposal generation unit creates a proposal based on the RFP's contents. For example, the generation AI receives the full text of the RFP and a proposal template as input and outputs a proposal including RFP responses, solutions, cost estimates, prerequisites, and a project schedule. The presentation generation unit creates a presentation based on the proposal's contents. For example, the generation AI receives the proposal's contents and a presentation template as input and outputs a presentation with automatic audio and animation. The work plan generation unit creates a work plan based on the contents of the RFP. For example, the generation AI receives the full text of the RFP and a work plan template as input, and outputs a work plan including a WBS and input plan. This enables the automatic generation system according to the embodiment to streamline responses to RFPs and quickly and accurately create deliverables. For example, quickly creating an RFP summary makes it easier to grasp the overall picture of the project. Automatically creating QA sheets and proposals facilitates communication with customers. Automatically creating presentations and work plans helps projects progress more smoothly.

[0030] In addition to summarizing the RFP, the summary generation unit can score the importance of the summary content and prioritize the summaries based on importance. For example, the summary generation unit uses generative AI to score the importance of each section of the RFP and prioritize summarizing the sections with higher importance. For example, the project's objectives and main requirements are given high scores and reflected in the summary. In addition, an algorithm is developed to analyze the contents of the RFP and quantify the importance of each item. For example, information related to the budget and schedule is included in the summary with a high score. Furthermore, a system is built to determine the priority of summaries based on the importance score when generating summaries. For example, items with higher importance are summarized first, and the overall summary sentence is then constructed. In this way, by prioritizing the summary content based on its importance, important information can be grasped first.

[0031] The summary generation unit can automatically associate success stories and failure stories of similar past projects with the RFP summary and present them. The summary generation unit, for example, uses generation AI to automatically associate success stories of similar past projects with the RFP summary. For example, success stories of projects with similar requirements are included in the summary. In addition, a system can be built that analyzes the contents of the RFP and automatically associates and presents past failure stories. For example, failure stories of projects with similar risks are included in the summary. Furthermore, when generating the summary, a database of past projects is referenced, and examples of similar projects are automatically extracted and reflected in the summary. For example, factors behind success and failure are included in the summary. This allows more specific information to be provided by associating past success stories and failure stories.

[0032] The summary generation unit converts the RFP summary into a format that is easy to understand for experts in different industries and fields, making it possible to incorporate knowledge from different fields. The summary generation unit, for example, uses generative AI to convert the RFP summary into a format that is easy to understand for experts in different industries and fields. For example, technical terms are replaced with more general expressions. In addition, to incorporate knowledge from different fields, a system is built to make the RFP summary multilingual. For example, it is translated into multiple languages ​​such as English and Chinese. Furthermore, the RFP summary is visualized so that it is easy to understand for experts in different industries. For example, the summary content is displayed visually using infographics and charts. This allows the summary to be converted into a format that is easy to understand for experts in different industries and fields, making it possible to incorporate knowledge from different fields.

[0033] The summary generation unit can visualize the summary content and provide it as an infographic to make it easier to understand visually. For example, the summary generation unit uses generative AI to build a system that visualizes the summary content of an RFP as an infographic. For example, it displays the project schedule and budget using graphs and charts. It also indicates important points with icons and diagrams to make the summary content easier to understand visually. For example, it visually highlights major requirements and risks. Furthermore, it develops a tool that automatically generates infographics, allowing users to easily visualize the summary content. For example, it provides a function to convert summary text into an infographic with drag and drop. This allows the summary content to be visualized and provided as an infographic, making it easier to understand visually.

[0034] The QA sheet generation unit can analyze past customer feedback on QA sheets and optimize the content of the QA sheet based on the feedback. The QA sheet generation unit can, for example, use generation AI to analyze past customer feedback on QA sheets and optimize the content of the questions based on the feedback. For example, it can improve frequently pointed out problems. It can also build a system to adjust the content of the answers in the QA sheet based on customer feedback data. For example, it can provide specific answers that meet customer requests. It can also analyze past feedback and optimize the structure and format of the QA sheet. For example, it can change the format to make it easier for customers to understand. This makes it possible to analyze past customer feedback and optimize the content of the QA sheet.

[0035] The QA sheet generation unit automatically reflects terminology and trends specific to the customer's industry in the QA sheet, making it possible to provide more specific answers. The QA sheet generation unit, for example, uses generation AI to build a system that automatically reflects terminology specific to the customer's industry in the QA sheet. For example, it provides answers that include technical terms and industry standards. It also analyzes trends in the customer's industry and reflects them in the content of the QA sheet. For example, it generates specific answers based on the latest technological trends and market needs. Furthermore, it develops a system that automatically collects industry-specific terminology and trends and reflects them in the QA sheet. For example, it generates answers by referring to industry news and reports. This makes it possible to reflect terminology and trends specific to the customer's industry and provide specific answers.

[0036] The QA sheet generation unit can automatically translate QA sheets into different languages, making it possible to accommodate international customers. For example, the QA sheet generation unit uses generation AI to build a system that automatically translates QA sheets into different languages. For example, it can support multiple languages ​​such as English, French, and Chinese. It can also develop a system that collects feedback from international customers based on the automatically translated QA sheets. For example, it can provide a feedback form that supports multiple languages. Furthermore, it can provide specific answers to international customers based on the QA sheets translated into different languages. For example, it can use technical terms and expressions that correspond to each language. This makes it possible to automatically translate QA sheets into different languages, making it possible to accommodate international customers.

[0037] The QA sheet generation unit can provide the contents of the QA sheet in audio or video format, converting it into a format that is easy for customers to view. The QA sheet generation unit, for example, uses generative AI to build a system that provides the contents of the QA sheet in audio format. For example, it converts text into audio, making it easier for customers to listen to. It can also provide the contents of the QA sheet in video format, making it easier to understand visually. For example, it can display questions and answers using animations or slides. It can also develop tools that automatically generate QA sheets in audio or video format, making them easier for customers to view. For example, it can provide voice synthesis and video editing functions. This makes it possible to provide the contents of the QA sheet in audio or video format, converting it into a format that is easy for customers to view.

[0038] The proposal generation unit can analyze past customer feedback on each section of the proposal and optimize the content of the proposal based on the feedback. The proposal generation unit can, for example, use generative AI to analyze past customer feedback on each section of the proposal and optimize the content based on the feedback. For example, it can improve frequently pointed out problems. It can also build a system to adjust the content of each section of the proposal based on customer feedback data. For example, it can provide specific proposals that meet customer requests. It can also analyze past feedback and optimize the structure and format of the proposal. For example, it can change the format to one that is easier for the customer to understand. In this way, it can analyze past customer feedback and optimize the content of the proposal.

[0039] The proposal generation unit can automatically associate and present success stories and failure stories of similar past projects with the proposal. The proposal generation unit, for example, uses generation AI to automatically associate success stories of similar past projects with the proposal. For example, success stories of projects with similar requirements are included in the proposal. In addition, a system is built that analyzes the contents of the proposal and automatically associates and presents past failure stories. For example, failure stories of projects with similar risks are included in the proposal. Furthermore, when creating a proposal, a database of past projects is referenced, and examples of similar projects are automatically extracted and reflected in the proposal. For example, factors for success and failure are included in the proposal. This makes it possible to provide more specific information by associating past success stories and failure stories.

[0040] The proposal generation unit converts the proposal into a format that is easy to understand for experts in different industries and fields, making it possible to incorporate knowledge from different fields. The proposal generation unit, for example, uses generative AI to convert the proposal into a format that is easy to understand for experts in different industries and fields. For example, technical terms are replaced with more general expressions. In addition, a system is built to make the proposal multilingual so that knowledge from different fields can be incorporated. For example, the proposal is translated into multiple languages ​​such as English and Chinese. Furthermore, the proposal is visualized so that it can be easily understood by experts in different industries. For example, the proposal contents are visually displayed using infographics and charts. This allows the proposal to be converted into a format that is easy to understand for experts in different industries and fields, making it possible to incorporate knowledge from different fields.

[0041] The proposal generation unit can visualize the contents of a proposal and provide it as an infographic to make it easier to understand visually. The proposal generation unit, for example, uses generative AI to build a system that visualizes the contents of a proposal as an infographic. For example, it displays the project schedule and budget in graphs and charts. It also indicates important points with icons and diagrams to make the contents of the proposal easier to understand visually. For example, it visually highlights major requirements and risks. Furthermore, it develops a tool that automatically generates infographics, allowing users to easily visualize the contents of a proposal. For example, it provides a function to convert a proposal into an infographic with drag and drop. This allows the contents of a proposal to be visualized and provided as an infographic, making it easier to understand visually.

[0042] The presentation generation unit can analyze past customer feedback on each slide in the presentation and optimize the content of the slide based on the feedback. The presentation generation unit can, for example, use a generation AI to analyze past customer feedback on each slide in the presentation and optimize the content based on the feedback. For example, it can improve frequently pointed out problems. It can also build a system that adjusts the content of each slide in the presentation based on customer feedback data. For example, it can provide specific slides that meet customer requests. It can also analyze past feedback and optimize the structure and format of the presentation. For example, it can change the format to one that is easier for customers to understand. This makes it possible to analyze past customer feedback and optimize the content of the slides in the presentation.

[0043] The presentation generation unit can automatically associate success stories and failure stories of similar past projects with the presentation and present them. The presentation generation unit, for example, uses generation AI to automatically associate success stories of similar past projects with the presentation. For example, success stories of projects with similar requirements are included in the slides. In addition, a system can be built that analyzes the content of the presentation and automatically associates and presents past failure stories. For example, failure stories of projects with similar risks are included in the slides. Furthermore, when creating a presentation, a database of past projects can be referenced and examples of similar projects can be automatically extracted and reflected in the slides. For example, factors behind success and failure can be included in the slides. In this way, more specific information can be provided by associating past success stories and failure stories.

[0044] The presentation generation unit can automatically translate presentations into different languages, making them suitable for international customers. The presentation generation unit, for example, uses a generation AI to build a system that automatically translates presentations into different languages. For example, it can support multiple languages ​​such as English, French, and Chinese. It also develops a system that collects feedback from international customers based on the automatically translated presentations. For example, it provides a feedback form that supports multiple languages. Furthermore, it provides specific proposals to international customers based on the presentations translated into different languages. For example, it uses technical terms and expressions that correspond to each language. This makes it possible to automatically translate presentations into different languages, making it suitable for international customers.

[0045] The presentation generation unit can visualize the contents of a presentation and provide them as infographics to make them easier to understand visually. The presentation generation unit, for example, uses generative AI to build a system that visualizes the contents of a presentation as infographics. For example, it displays project schedules and budgets using graphs and charts. It also indicates important points with icons and diagrams to make the contents of the presentation easier to understand visually. For example, it visually highlights major requirements and risks. Furthermore, it develops tools that automatically generate infographics, allowing users to easily visualize the contents of presentations. For example, it provides a function to convert presentations into infographics with drag and drop. This allows the contents of a presentation to be visualized and provided as infographics, making them easier to understand visually.

[0046] The work plan generation unit can analyze past customer feedback on each section of the work plan and optimize the content of the plan based on the feedback. The work plan generation unit can, for example, use generation AI to analyze past customer feedback on each section of the work plan and optimize the content based on the feedback. For example, it can improve frequently pointed out problems. It can also build a system to adjust the content of each section of the work plan based on customer feedback data. For example, it can provide a specific plan that meets customer requests. It can also analyze past feedback and optimize the structure and format of the work plan. For example, it can change the format to one that is easy for customers to understand. In this way, it can analyze past customer feedback and optimize the content of the work plan.

[0047] The work plan generation unit can automatically associate and present success stories and failure stories of similar past projects with the work plan. The work plan generation unit, for example, uses generation AI to automatically associate success stories of similar past projects with the work plan. For example, success stories of projects with similar requirements are included in the plan. In addition, a system can be built that analyzes the contents of the work plan and automatically associates and presents past failure stories. For example, failure stories of projects with similar risks are included in the plan. Furthermore, when creating a work plan, a database of past projects can be referenced and examples of similar projects can be automatically extracted and reflected in the plan. For example, factors behind success and failure can be included in the plan. In this way, more specific information can be provided by associating past success stories and failure stories.

[0048] The work plan generation unit converts the work plan into a format that is easy to understand for experts in different industries and fields, making it possible to incorporate knowledge from different fields. The work plan generation unit, for example, uses generative AI to convert the work plan into a format that is easy to understand for experts in different industries and fields. For example, technical terms are replaced with general expressions. In addition, to incorporate knowledge from different fields, a system is built to make the work plan multilingual. For example, it is translated into multiple languages ​​such as English and Chinese. Furthermore, the work plan is visualized so that it is easy to understand for experts in different industries. For example, the plan contents are visually displayed using infographics and charts. This allows the work plan to be converted into a format that is easy to understand for experts in different industries and fields, making it possible to incorporate knowledge from different fields.

[0049] The work plan generation unit can visualize the contents of the work plan and provide them as infographics to make them easier to understand visually. The work plan generation unit, for example, uses generation AI to build a system that visualizes the contents of the work plan as infographics. For example, it displays the project schedule and resource allocation in graphs and charts. It also indicates important points with icons and diagrams to make the contents of the work plan easier to understand visually. For example, it visually highlights major tasks and risks. Furthermore, it develops a tool that automatically generates infographics, allowing users to easily visualize the contents of the work plan. For example, it provides a function to convert a plan into an infographic with drag and drop. This allows the contents of the work plan to be visualized and provided as an infographic, making it easier to understand visually.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The automatic generation system can further include a data analysis unit. The data analysis unit can analyze the contents of the RFP and compare it with past project data to perform risk assessment. For example, it can extract problems that occurred in past projects and assess the risks for the current RFP. The data analysis unit can also predict market trends based on the contents of the RFP and reflect them in the proposal. For example, it can analyze current market trends and incorporate the latest technologies and solutions into the proposal. Furthermore, the data analysis unit can analyze the trends of competitors based on the contents of the RFP and create competitive proposals. For example, it can analyze the contents of competitors' past proposals and reflect strategies to counter them in the proposal. By adding a data analysis unit, more specific and competitive proposals can be created.

[0052] The summary generation unit can further include a natural language processing unit. The natural language processing unit can analyze the content of the RFP and automatically detect and correct ambiguous expressions or unclear parts. For example, it can clarify ambiguous requirements and convert them into specific proposal content. The natural language processing unit can also automatically generate questions based on the content of the RFP and ask the customer for confirmation. For example, it generates questions to request additional information about unclear parts. Furthermore, the natural language processing unit can automatically create a draft proposal based on the content of the RFP and complete the final proposal in cooperation with the summary generation unit. Thus, adding a natural language processing unit makes it possible to more accurately understand the content of the RFP and create specific proposals.

[0053] The processing flow of the first embodiment will be briefly explained below.

[0054] Step 1: The summary generator reads the RFP, extracts its key points, and generates a summary. For example, the generator AI takes the entire RFP as input and summarizes information such as the project's objectives, requirements, schedule, and budget. Step 2: The QA sheet generator creates a QA sheet for the customer based on the contents of the RFP. For example, the generation AI receives the full text of the RFP and questions from the customer as input, lists questions and confirmations, and generates answers to them. Step 3: The proposal generator creates a proposal based on the RFP content. For example, the generator receives the full RFP and a proposal template as input, and outputs a proposal that includes the RFP response, solution, cost estimate, prerequisites, project schedule, etc. Step 4: The presentation generation unit creates a presentation based on the proposal content. For example, the generation AI receives the proposal content and a presentation template as input, and outputs a presentation with audio and animation automatically added. Step 5: The work plan generator creates a work plan based on the contents of the RFP. For example, the generation AI receives the full text of the RFP and a work plan template as input, and outputs a work plan including a WBS and input plan.

[0055] (Example 2) The automatic generation system according to an embodiment of the present invention reads an RFP and uses a generation AI to automatically generate summaries, QA sheets, proposals, presentations, and work plans. This allows the automatic generation system to streamline responses to RFPs and quickly and accurately create deliverables.

[0056] An automatic generation system according to an embodiment includes a summary generation unit, a QA sheet generation unit, a proposal generation unit, a presentation generation unit, and a work plan generation unit. The summary generation unit reads an RFP, extracts key points, and generates a summary. For example, the generation AI receives the full text of the RFP as input and summarizes information such as the project's objectives, requirements, schedule, and budget. The QA sheet generation unit creates a QA sheet for the customer based on the RFP's contents. For example, the generation AI receives the full text of the RFP and questions from the customer as input, lists questions and confirmations, and generates answers to those questions. The proposal generation unit creates a proposal based on the RFP's contents. For example, the generation AI receives the full text of the RFP and a proposal template as input and outputs a proposal including RFP responses, solutions, cost estimates, prerequisites, and a project schedule. The presentation generation unit creates a presentation based on the proposal's contents. For example, the generation AI receives the proposal's contents and a presentation template as input and outputs a presentation with automatic audio and animation. The work plan generation unit creates a work plan based on the contents of the RFP. For example, the generation AI receives the full text of the RFP and a work plan template as input, and outputs a work plan including a WBS and input plan. This enables the automatic generation system according to the embodiment to streamline responses to RFPs and quickly and accurately create deliverables. For example, quickly creating an RFP summary makes it easier to grasp the overall picture of the project. Automatically creating QA sheets and proposals facilitates communication with customers. Automatically creating presentations and work plans helps projects progress more smoothly.

[0057] In addition to summarizing the RFP, the summary generation unit can score the importance of the summary content and prioritize the summaries based on importance. For example, the summary generation unit uses generative AI to score the importance of each section of the RFP and prioritize summarizing the sections with higher importance. For example, the project's objectives and main requirements are given high scores and reflected in the summary. In addition, an algorithm is developed to analyze the contents of the RFP and quantify the importance of each item. For example, information related to the budget and schedule is included in the summary with a high score. Furthermore, a system is built to determine the priority of summaries based on the importance score when generating summaries. For example, items with higher importance are summarized first, and the overall summary sentence is then constructed. In this way, by prioritizing the summary content based on its importance, important information can be grasped first.

[0058] The summary generation unit can automatically associate success stories and failure stories of similar past projects with the RFP summary and present them. The summary generation unit, for example, uses generation AI to automatically associate success stories of similar past projects with the RFP summary. For example, success stories of projects with similar requirements are included in the summary. In addition, a system can be built that analyzes the contents of the RFP and automatically associates and presents past failure stories. For example, failure stories of projects with similar risks are included in the summary. Furthermore, when generating the summary, a database of past projects is referenced, and examples of similar projects are automatically extracted and reflected in the summary. For example, factors behind success and failure are included in the summary. This allows more specific information to be provided by associating past success stories and failure stories.

[0059] The summary generation unit can use the emotion estimation function to predict customers' emotional reactions to the RFP summary and generate summary content that will elicit a positive reaction. The summary generation unit, for example, uses the emotion estimation function to build a system that predicts customers' emotional reactions to the RFP summary. For example, to elicit a positive reaction, it emphasizes success stories and positive elements. It also develops an algorithm that predicts customers' emotional reactions and eliminates negative elements when generating summaries. For example, it uses expressions that reduce risks and problems. It also builds a system that automatically generates summary content that will elicit a positive reaction from customers based on the emotion estimation data. For example, it emphasizes elements that meet customer expectations. This makes it possible to predict customers' emotional reactions and generate summary content that will elicit a positive reaction.

[0060] The summary generation unit converts the RFP summary into a format that is easy to understand for experts in different industries and fields, making it possible to incorporate knowledge from different fields. The summary generation unit, for example, uses generative AI to convert the RFP summary into a format that is easy to understand for experts in different industries and fields. For example, technical terms are replaced with more general expressions. In addition, to incorporate knowledge from different fields, a system is built to make the RFP summary multilingual. For example, it is translated into multiple languages ​​such as English and Chinese. Furthermore, the RFP summary is visualized so that it is easy to understand for experts in different industries. For example, the summary content is displayed visually using infographics and charts. This allows the summary to be converted into a format that is easy to understand for experts in different industries and fields, making it possible to incorporate knowledge from different fields.

[0061] The summary generation unit can visualize the summary content and provide it as an infographic to make it easier to understand visually. For example, the summary generation unit uses generative AI to build a system that visualizes the summary content of an RFP as an infographic. For example, it displays the project schedule and budget using graphs and charts. It also indicates important points with icons and diagrams to make the summary content easier to understand visually. For example, it visually highlights major requirements and risks. Furthermore, it develops a tool that automatically generates infographics, allowing users to easily visualize the summary content. For example, it provides a function to convert summary text into an infographic with drag and drop. This allows the summary content to be visualized and provided as an infographic, making it easier to understand visually.

[0062] The summary generation unit uses the emotion estimation function to collect team members' emotional reactions to the summary content, thereby improving the overall team's level of understanding. The summary generation unit, for example, uses the emotion estimation function to build a system that collects team members' emotional reactions to the summary content in real time. For example, the summary content is adjusted based on each member's emotion score. In addition, to improve the overall team's level of understanding, the summary content is improved based on the emotion estimation data. For example, parts that receive many negative reactions are revised. Furthermore, the emotion estimation function is used to collect feedback on the summary content and develop a system that reflects the opinions of the entire team. For example, summary sentences that receive many positive reactions are preferentially adopted. This allows the emotional reactions of team members to be collected and the overall team's level of understanding to be improved.

[0063] The QA sheet generation unit can analyze past customer feedback on QA sheets and optimize the content of the QA sheet based on the feedback. The QA sheet generation unit can, for example, use generation AI to analyze past customer feedback on QA sheets and optimize the content of the questions based on the feedback. For example, it can improve frequently pointed out problems. It can also build a system to adjust the content of the answers in the QA sheet based on customer feedback data. For example, it can provide specific answers that meet customer requests. It can also analyze past feedback and optimize the structure and format of the QA sheet. For example, it can change the format to make it easier for customers to understand. This makes it possible to analyze past customer feedback and optimize the content of the QA sheet.

[0064] The QA sheet generation unit automatically reflects terminology and trends specific to the customer's industry in the QA sheet, making it possible to provide more specific answers. The QA sheet generation unit, for example, uses generation AI to build a system that automatically reflects terminology specific to the customer's industry in the QA sheet. For example, it provides answers that include technical terms and industry standards. It also analyzes trends in the customer's industry and reflects them in the content of the QA sheet. For example, it generates specific answers based on the latest technological trends and market needs. Furthermore, it develops a system that automatically collects industry-specific terminology and trends and reflects them in the QA sheet. For example, it generates answers by referring to industry news and reports. This makes it possible to reflect terminology and trends specific to the customer's industry and provide specific answers.

[0065] The QA sheet generation unit can use the emotion estimation function to predict a customer's emotional response to questions on the QA sheet and generate answers that will elicit a positive response. The QA sheet generation unit, for example, uses the emotion estimation function to build a system that predicts a customer's emotional response to questions on the QA sheet. For example, positive expressions are used to elicit a positive response. The QA sheet generation unit also develops an algorithm that predicts a customer's emotional response and generates answers that will avoid negative responses. For example, expressions that reduce risks and problems are used. Furthermore, a system is built that automatically generates answers that will elicit a positive response from customers based on the emotion estimation data. For example, specific answers that meet customer expectations are provided. This makes it possible to predict a customer's emotional response and generate answers that will elicit a positive response.

[0066] The QA sheet generation unit can automatically translate QA sheets into different languages, making it possible to accommodate international customers. For example, the QA sheet generation unit uses generation AI to build a system that automatically translates QA sheets into different languages. For example, it can support multiple languages ​​such as English, French, and Chinese. It can also develop a system that collects feedback from international customers based on the automatically translated QA sheets. For example, it can provide a feedback form that supports multiple languages. Furthermore, it can provide specific answers to international customers based on the QA sheets translated into different languages. For example, it can use technical terms and expressions that correspond to each language. This makes it possible to automatically translate QA sheets into different languages, making it possible to accommodate international customers.

[0067] The QA sheet generation unit can provide the contents of the QA sheet in audio or video format, converting it into a format that is easy for customers to view. The QA sheet generation unit, for example, uses generative AI to build a system that provides the contents of the QA sheet in audio format. For example, it converts text into audio, making it easier for customers to listen to. It can also provide the contents of the QA sheet in video format, making it easier to understand visually. For example, it can display questions and answers using animations or slides. It can also develop tools that automatically generate QA sheets in audio or video format, making them easier for customers to view. For example, it can provide voice synthesis and video editing functions. This makes it possible to provide the contents of the QA sheet in audio or video format, converting it into a format that is easy for customers to view.

[0068] The QA sheet generation unit uses the emotion estimation function to collect team members' emotional responses to the content of the QA sheet, thereby improving the overall team's level of understanding. For example, the QA sheet generation unit uses the emotion estimation function to build a system that collects team members' emotional responses to the content of the QA sheet in real time. For example, the QA sheet content is adjusted based on each member's emotion score. In addition, to improve the overall team's level of understanding, the QA sheet content is improved based on the emotion estimation data. For example, parts that receive a lot of negative responses are corrected. Furthermore, the emotion estimation function is used to collect feedback on the content of the QA sheet and develop a system that reflects the opinions of the entire team. For example, answers that receive a lot of positive responses are prioritized. This makes it possible to collect team members' emotional responses and improve the overall team's level of understanding.

[0069] The proposal generation unit can analyze past customer feedback on each section of the proposal and optimize the content of the proposal based on the feedback. The proposal generation unit can, for example, use generative AI to analyze past customer feedback on each section of the proposal and optimize the content based on the feedback. For example, it can improve frequently pointed out problems. It can also build a system to adjust the content of each section of the proposal based on customer feedback data. For example, it can provide specific proposals that meet customer requests. It can also analyze past feedback and optimize the structure and format of the proposal. For example, it can change the format to one that is easier for the customer to understand. In this way, it can analyze past customer feedback and optimize the content of the proposal.

[0070] The proposal generation unit can automatically associate and present success stories and failure stories of similar past projects with the proposal. The proposal generation unit, for example, uses generation AI to automatically associate success stories of similar past projects with the proposal. For example, success stories of projects with similar requirements are included in the proposal. In addition, a system is built that analyzes the contents of the proposal and automatically associates and presents past failure stories. For example, failure stories of projects with similar risks are included in the proposal. Furthermore, when creating a proposal, a database of past projects is referenced, and examples of similar projects are automatically extracted and reflected in the proposal. For example, factors for success and failure are included in the proposal. This makes it possible to provide more specific information by associating past success stories and failure stories.

[0071] The proposal generation unit can use the emotion estimation function to predict the customer's emotional reaction to the proposal content and generate content that will elicit a positive reaction. The proposal generation unit, for example, uses the emotion estimation function to build a system that predicts the customer's emotional reaction to the proposal content. For example, to elicit a positive reaction, it emphasizes success stories and positive elements. It also develops an algorithm that predicts the customer's emotional reaction and eliminates negative elements when creating a proposal. For example, it uses expressions that reduce risks and problems. It also builds a system that automatically generates proposal content that will elicit a positive reaction from the customer based on the emotion estimation data. For example, it emphasizes elements that meet the customer's expectations. This makes it possible to predict the customer's emotional reaction and generate content that will elicit a positive reaction.

[0072] The proposal generation unit converts the proposal into a format that is easy to understand for experts in different industries and fields, making it possible to incorporate knowledge from different fields. The proposal generation unit, for example, uses generative AI to convert the proposal into a format that is easy to understand for experts in different industries and fields. For example, technical terms are replaced with more general expressions. In addition, a system is built to make the proposal multilingual so that knowledge from different fields can be incorporated. For example, the proposal is translated into multiple languages ​​such as English and Chinese. Furthermore, the proposal is visualized so that it can be easily understood by experts in different industries. For example, the proposal contents are visually displayed using infographics and charts. This allows the proposal to be converted into a format that is easy to understand for experts in different industries and fields, making it possible to incorporate knowledge from different fields.

[0073] The proposal generation unit can visualize the contents of a proposal and provide it as an infographic to make it easier to understand visually. The proposal generation unit, for example, uses generative AI to build a system that visualizes the contents of a proposal as an infographic. For example, it displays the project schedule and budget in graphs and charts. It also indicates important points with icons and diagrams to make the contents of the proposal easier to understand visually. For example, it visually highlights major requirements and risks. Furthermore, it develops a tool that automatically generates infographics, allowing users to easily visualize the contents of a proposal. For example, it provides a function to convert a proposal into an infographic with drag and drop. This allows the contents of a proposal to be visualized and provided as an infographic, making it easier to understand visually.

[0074] The proposal generation unit can use the emotion estimation function to collect team members' emotional reactions to the proposal content, thereby improving the overall team's level of understanding. The proposal generation unit, for example, uses the emotion estimation function to build a system that collects team members' emotional reactions to the proposal content in real time. For example, the proposal content is adjusted based on each member's emotion score. In addition, to improve the overall team's level of understanding, the proposal content is improved based on the emotion estimation data. For example, parts that receive a lot of negative reactions are revised. Furthermore, the emotion estimation function is used to collect feedback on the proposal content and develop a system that reflects the opinions of the entire team. For example, proposal content that receives a lot of positive reactions is preferentially adopted. In this way, the emotional reactions of team members can be collected and the overall team's level of understanding can be improved.

[0075] The presentation generation unit can analyze past customer feedback on each slide in the presentation and optimize the content of the slide based on the feedback. The presentation generation unit can, for example, use a generation AI to analyze past customer feedback on each slide in the presentation and optimize the content based on the feedback. For example, it can improve frequently pointed out problems. It can also build a system that adjusts the content of each slide in the presentation based on customer feedback data. For example, it can provide specific slides that meet customer requests. It can also analyze past feedback and optimize the structure and format of the presentation. For example, it can change the format to one that is easier for customers to understand. This makes it possible to analyze past customer feedback and optimize the content of the slides in the presentation.

[0076] The presentation generation unit can automatically associate success stories and failure stories of similar past projects with the presentation and present them. The presentation generation unit, for example, uses generation AI to automatically associate success stories of similar past projects with the presentation. For example, success stories of projects with similar requirements are included in the slides. In addition, a system can be built that analyzes the content of the presentation and automatically associates and presents past failure stories. For example, failure stories of projects with similar risks are included in the slides. Furthermore, when creating a presentation, a database of past projects can be referenced and examples of similar projects can be automatically extracted and reflected in the slides. For example, factors behind success and failure can be included in the slides. In this way, more specific information can be provided by associating past success stories and failure stories.

[0077] The presentation generation unit can use the emotion estimation function to predict customers' emotional reactions to the presentation content and generate content that will elicit a positive reaction. The presentation generation unit, for example, uses the emotion estimation function to build a system that predicts customers' emotional reactions to the presentation content. For example, to elicit a positive reaction, it emphasizes success stories and positive elements. It also develops an algorithm that predicts customers' emotional reactions and eliminates negative elements when creating a presentation. For example, it uses expressions that reduce risks and problems. It also builds a system that automatically generates presentation content that will elicit a positive reaction from customers based on the emotion estimation data. For example, it emphasizes elements that meet customer expectations. This makes it possible to predict customers' emotional reactions and generate content that will elicit a positive reaction.

[0078] The presentation generation unit can automatically translate presentations into different languages, making them suitable for international customers. The presentation generation unit, for example, uses a generation AI to build a system that automatically translates presentations into different languages. For example, it can support multiple languages ​​such as English, French, and Chinese. It also develops a system that collects feedback from international customers based on the automatically translated presentations. For example, it provides a feedback form that supports multiple languages. Furthermore, it provides specific proposals to international customers based on the presentations translated into different languages. For example, it uses technical terms and expressions that correspond to each language. This makes it possible to automatically translate presentations into different languages, making it suitable for international customers.

[0079] The presentation generation unit can visualize the contents of a presentation and provide them as infographics to make them easier to understand visually. The presentation generation unit, for example, uses generative AI to build a system that visualizes the contents of a presentation as infographics. For example, it displays project schedules and budgets using graphs and charts. It also indicates important points with icons and diagrams to make the contents of the presentation easier to understand visually. For example, it visually highlights major requirements and risks. Furthermore, it develops tools that automatically generate infographics, allowing users to easily visualize the contents of presentations. For example, it provides a function to convert presentations into infographics with drag and drop. This allows the contents of a presentation to be visualized and provided as infographics, making them easier to understand visually.

[0080] The presentation generation unit uses the emotion estimation function to collect team members' emotional reactions to the presentation content, thereby improving the overall team's understanding. The presentation generation unit, for example, uses the emotion estimation function to build a system that collects team members' emotional reactions to the presentation content in real time. For example, the presentation content is adjusted based on each member's emotion score. Furthermore, to improve the overall team's understanding, the presentation content is improved based on the emotion estimation data. For example, parts that receive a lot of negative reactions are revised. Furthermore, the emotion estimation function is used to collect feedback on the presentation content and develop a system that reflects the opinions of the entire team. For example, presentation content that receives a lot of positive reactions is preferentially adopted. This makes it possible to collect team members' emotional reactions and improve the overall team's understanding.

[0081] The work plan generation unit can analyze past customer feedback on each section of the work plan and optimize the content of the plan based on the feedback. The work plan generation unit can, for example, use generation AI to analyze past customer feedback on each section of the work plan and optimize the content based on the feedback. For example, it can improve frequently pointed out problems. It can also build a system to adjust the content of each section of the work plan based on customer feedback data. For example, it can provide a specific plan that meets customer requests. It can also analyze past feedback and optimize the structure and format of the work plan. For example, it can change the format to one that is easy for customers to understand. In this way, it can analyze past customer feedback and optimize the content of the work plan.

[0082] The work plan generation unit can automatically associate and present success stories and failure stories of similar past projects with the work plan. The work plan generation unit, for example, uses generation AI to automatically associate success stories of similar past projects with the work plan. For example, success stories of projects with similar requirements are included in the plan. In addition, a system can be built that analyzes the contents of the work plan and automatically associates and presents past failure stories. For example, failure stories of projects with similar risks are included in the plan. Furthermore, when creating a work plan, a database of past projects can be referenced and examples of similar projects can be automatically extracted and reflected in the plan. For example, factors behind success and failure can be included in the plan. In this way, more specific information can be provided by associating past success stories and failure stories.

[0083] The work plan generation unit can use the emotion estimation function to predict the customer's emotional reaction to the content of the work plan and generate content that will elicit a positive reaction. The work plan generation unit, for example, uses the emotion estimation function to build a system that predicts the customer's emotional reaction to the content of the work plan. For example, to elicit a positive reaction, it emphasizes success stories and positive elements. It also develops an algorithm that predicts the customer's emotional reaction and eliminates negative elements when creating a work plan. For example, it uses expressions that reduce risks and problems. It also builds a system that automatically generates work plan content that will elicit a positive reaction from customers based on the emotion estimation data. For example, it emphasizes elements that meet customer expectations. This makes it possible to predict the customer's emotional reaction and generate content that will elicit a positive reaction.

[0084] The work plan generation unit converts the work plan into a format that is easy to understand for experts in different industries and fields, making it possible to incorporate knowledge from different fields. The work plan generation unit, for example, uses generative AI to convert the work plan into a format that is easy to understand for experts in different industries and fields. For example, technical terms are replaced with general expressions. In addition, to incorporate knowledge from different fields, a system is built to make the work plan multilingual. For example, it is translated into multiple languages ​​such as English and Chinese. Furthermore, the work plan is visualized so that it is easy to understand for experts in different industries. For example, the plan contents are visually displayed using infographics and charts. This allows the work plan to be converted into a format that is easy to understand for experts in different industries and fields, making it possible to incorporate knowledge from different fields.

[0085] The work plan generation unit can visualize the contents of the work plan and provide them as infographics to make them easier to understand visually. The work plan generation unit, for example, uses generation AI to build a system that visualizes the contents of the work plan as infographics. For example, it displays the project schedule and resource allocation in graphs and charts. It also indicates important points with icons and diagrams to make the contents of the work plan easier to understand visually. For example, it visually highlights major tasks and risks. Furthermore, it develops a tool that automatically generates infographics, allowing users to easily visualize the contents of the work plan. For example, it provides a function to convert a plan into an infographic with drag and drop. This allows the contents of the work plan to be visualized and provided as an infographic, making it easier to understand visually.

[0086] The work plan generation unit uses the emotion estimation function to collect the emotional reactions of team members to the contents of the work plan, thereby improving the overall team's level of understanding. The work plan generation unit, for example, uses the emotion estimation function to build a system that collects the emotional reactions of team members to the contents of the work plan in real time. For example, the work plan generation unit adjusts the contents of the plan based on each member's emotion score. In addition, to improve the overall team's level of understanding, the work plan content is improved based on the emotion estimation data. For example, parts that receive a lot of negative reactions are revised. Furthermore, the emotion estimation function is used to collect feedback on the contents of the work plan and develop a system that reflects the opinions of the entire team. For example, plan contents that receive a lot of positive reactions are preferentially adopted. In this way, the emotional reactions of team members can be collected and the overall team's level of understanding can be improved.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] The automatic generation system can further include a data analysis unit. The data analysis unit can analyze the contents of the RFP and compare it with past project data to perform risk assessment. For example, it can extract problems that occurred in past projects and assess the risks for the current RFP. The data analysis unit can also predict market trends based on the contents of the RFP and reflect them in the proposal. For example, it can analyze current market trends and incorporate the latest technologies and solutions into the proposal. Furthermore, the data analysis unit can analyze the trends of competitors based on the contents of the RFP and create competitive proposals. For example, it can analyze the contents of competitors' past proposals and reflect strategies to counter them in the proposal. By adding a data analysis unit, more specific and competitive proposals can be created.

[0089] The summary generation unit can further include a natural language processing unit. The natural language processing unit can analyze the content of the RFP and automatically detect and correct ambiguous expressions or unclear parts. For example, it can clarify ambiguous requirements and convert them into specific proposal content. The natural language processing unit can also automatically generate questions based on the content of the RFP and ask the customer for confirmation. For example, it generates questions to request additional information about unclear parts. Furthermore, the natural language processing unit can automatically create a draft proposal based on the content of the RFP and complete the final proposal in cooperation with the summary generation unit. Thus, adding a natural language processing unit makes it possible to more accurately understand the content of the RFP and create specific proposals.

[0090] The summary generation unit can further use the emotion estimation function to predict the customer's emotional response to the RFP summary and generate summary content that will elicit a positive response. For example, a system can be built using the emotion estimation function to predict the customer's emotional response to the RFP summary. For example, success stories and positive elements can be emphasized to elicit a positive response. An algorithm can also be developed to predict the customer's emotional response and eliminate negative elements when generating summaries. For example, expressions that reduce risks and problems can be used. Furthermore, a system can be built that automatically generates summary content that will elicit a positive response from customers based on the emotion estimation data. For example, elements that meet customer expectations can be emphasized. This makes it possible to predict the customer's emotional response and generate summary content that will elicit a positive response.

[0091] The summary generation unit can further use an emotion estimation function to collect team members' emotional reactions to the summary content, thereby improving the overall team's level of understanding. For example, a system can be built using the emotion estimation function to collect team members' emotional reactions to the summary content in real time. For example, the summary content can be adjusted based on each member's emotion score. Furthermore, to improve the overall team's level of understanding, the summary content can be improved based on the emotion estimation data. For example, parts that receive a lot of negative reactions can be revised. Furthermore, a system can be developed using the emotion estimation function to collect feedback on the summary content and reflect the opinions of the entire team. For example, summary sentences that receive a lot of positive reactions can be preferentially adopted. This allows the emotional reactions of team members to be collected and the overall team's level of understanding to be improved.

[0092] The summary generation unit can further use an emotion estimation function to predict customers' emotional reactions to the summary content and generate summary content that will elicit a positive response. For example, a system can be built using the emotion estimation function to predict customers' emotional reactions to RFP summaries. For example, success stories and positive elements can be emphasized to elicit a positive response. An algorithm can also be developed to predict customers' emotional reactions and eliminate negative elements when generating summaries. For example, expressions that reduce risks and problems can be used. Furthermore, a system can be built that automatically generates summary content that will elicit a positive response from customers based on the emotion estimation data. For example, elements that meet customer expectations can be emphasized. This makes it possible to predict customers' emotional reactions and generate summary content that will elicit a positive response.

[0093] The summary generation unit can further use an emotion estimation function to collect team members' emotional reactions to the summary content, thereby improving the overall team's level of understanding. For example, a system can be built using the emotion estimation function to collect team members' emotional reactions to the summary content in real time. For example, the summary content can be adjusted based on each member's emotion score. Furthermore, to improve the overall team's level of understanding, the summary content can be improved based on the emotion estimation data. For example, parts that receive a lot of negative reactions can be revised. Furthermore, a system can be developed using the emotion estimation function to collect feedback on the summary content and reflect the opinions of the entire team. For example, summary sentences that receive a lot of positive reactions can be preferentially adopted. This allows the emotional reactions of team members to be collected and the overall team's level of understanding to be improved.

[0094] The summary generation unit can further use an emotion estimation function to predict customers' emotional reactions to the summary content and generate summary content that will elicit a positive response. For example, a system can be built using the emotion estimation function to predict customers' emotional reactions to RFP summaries. For example, success stories and positive elements can be emphasized to elicit a positive response. An algorithm can also be developed to predict customers' emotional reactions and eliminate negative elements when generating summaries. For example, expressions that reduce risks and problems can be used. Furthermore, a system can be built that automatically generates summary content that will elicit a positive response from customers based on the emotion estimation data. For example, elements that meet customer expectations can be emphasized. This makes it possible to predict customers' emotional reactions and generate summary content that will elicit a positive response.

[0095] The summary generation unit can further use an emotion estimation function to collect team members' emotional reactions to the summary content, thereby improving the overall team's level of understanding. For example, a system can be built using the emotion estimation function to collect team members' emotional reactions to the summary content in real time. For example, the summary content can be adjusted based on each member's emotion score. Furthermore, to improve the overall team's level of understanding, the summary content can be improved based on the emotion estimation data. For example, parts that receive a lot of negative reactions can be revised. Furthermore, a system can be developed using the emotion estimation function to collect feedback on the summary content and reflect the opinions of the entire team. For example, summary sentences that receive a lot of positive reactions can be preferentially adopted. This allows the emotional reactions of team members to be collected and the overall team's level of understanding to be improved.

[0096] The summary generation unit can further use an emotion estimation function to predict customers' emotional reactions to the summary content and generate summary content that will elicit a positive response. For example, a system can be built using the emotion estimation function to predict customers' emotional reactions to RFP summaries. For example, success stories and positive elements can be emphasized to elicit a positive response. An algorithm can also be developed to predict customers' emotional reactions and eliminate negative elements when generating summaries. For example, expressions that reduce risks and problems can be used. Furthermore, a system can be built that automatically generates summary content that will elicit a positive response from customers based on the emotion estimation data. For example, elements that meet customer expectations can be emphasized. This makes it possible to predict customers' emotional reactions and generate summary content that will elicit a positive response.

[0097] The summary generation unit can further use an emotion estimation function to collect team members' emotional reactions to the summary content, thereby improving the overall team's level of understanding. For example, a system can be built using the emotion estimation function to collect team members' emotional reactions to the summary content in real time. For example, the summary content can be adjusted based on each member's emotion score. Furthermore, to improve the overall team's level of understanding, the summary content can be improved based on the emotion estimation data. For example, parts that receive a lot of negative reactions can be revised. Furthermore, a system can be developed using the emotion estimation function to collect feedback on the summary content and reflect the opinions of the entire team. For example, summary sentences that receive a lot of positive reactions can be preferentially adopted. This allows the emotional reactions of team members to be collected and the overall team's level of understanding to be improved.

[0098] The processing flow of the second embodiment will be briefly explained below.

[0099] Step 1: The summary generator reads the RFP, extracts its key points, and generates a summary. For example, the generator AI takes the entire RFP as input and summarizes information such as the project's objectives, requirements, schedule, and budget. Step 2: The QA sheet generator creates a QA sheet for the customer based on the contents of the RFP. For example, the generation AI receives the full text of the RFP and questions from the customer as input, lists questions and confirmations, and generates answers to them. Step 3: The proposal generator creates a proposal based on the RFP content. For example, the generator receives the full RFP and a proposal template as input, and outputs a proposal that includes the RFP response, solution, cost estimate, prerequisites, project schedule, etc. Step 4: The presentation generation unit creates a presentation based on the proposal content. For example, the generation AI receives the proposal content and a presentation template as input, and outputs a presentation with audio and animation automatically added. Step 5: The work plan generator creates a work plan based on the contents of the RFP. For example, the generation AI receives the full text of the RFP and a work plan template as input, and outputs a work plan including a WBS and input plan.

[0100] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0101] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0102] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0103] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0104] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0105] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0106] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0107] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0109] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0110] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0111] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0112] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0113] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0114] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0118] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0119] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0120] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0121] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0125] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0128] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0129] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0130] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0132] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0134] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0141] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0142] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0144] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0145] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0148] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0149] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0150] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0151] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0152] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0153] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0154] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0155] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0156] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0157] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0158] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0159] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0160] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0161] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0162] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0163] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0164] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0165] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0166] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0167] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. By using generation AI to read the RFP, a summary generator for generating a summary of the RFP; a QA sheet generation unit that generates a QA sheet for the RFP; a proposal generation unit that generates a proposal based on the RFP; a presentation generation unit that generates a presentation based on the proposal; a work plan generation unit that generates a work plan based on the RFP; A system characterized by:

2. The summary generation unit In addition to summarizing the RFP, score the importance of the abstract content and prioritize the abstracts based on the importance.

2. The system of claim 1.

3. The summary generation unit The RFP summary is automatically linked to examples of success and failure of similar projects in the past.

2. The system of claim 1.

4. The summary generation unit Predict customer emotional reactions to the RFP summary and generate summary content that will elicit a positive response 2. The system of claim 1.

5. The summary generation unit Convert the RFP summary into a format that is easy to understand for experts in different industries and fields, incorporating knowledge from different fields.

2. The system of claim 1.

6. The summary generation unit Visualize the summary and provide it as an infographic to make it easier to understand visually.

2. The system of claim 1.

Images