system

Abstract

The system according to this embodiment aims to efficiently generate budget application forms when a new proposal is being drafted. [Solution] The system according to the embodiment comprises a collection unit, a learning unit, a reception unit, a generation unit, and an identification unit. The collection unit collects past budget applications. The learning unit learns from the budget applications collected by the collection unit. The reception unit receives the outline of a new proposal. The generation unit generates a budget application based on the outline of the proposal received by the reception unit. The identification unit identifies any deficiencies in the input information based on the budget application generated by the generation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it takes time and effort to create a budget application form at the time of new proposal, and it is difficult to perform efficiently.

[0005] The system according to the embodiment aims to efficiently generate a budget application form at the time of new proposal.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a learning unit, a reception unit, a generation unit, and an identification unit. The collection unit collects past budget applications. The learning unit learns from the budget applications collected by the collection unit. The reception unit receives the outline of a new application. The generation unit generates a budget application based on the outline of the application received by the reception unit. The identification unit identifies any deficiencies in the input information based on the budget application generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently generate budget application forms when a new proposal is being drafted. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment. <​​​​​​​​​​The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The budget application generation system according to an embodiment of the present invention is a system that shortens the time to budget approval by utilizing a generation AI. The budget application generation system uses past budget applications as training data and learns whether or not a budget can be obtained and what the rejection points are. The budget application generation system receives the outline of a new project as input and outputs a draft budget application. This reduces the time lag from proposal to project launch and enables smooth budget approval. For example, the budget application generation system collects past budget applications as training data, and the generation AI learns from this. At this time, it also learns whether or not a budget can be obtained and what the rejection points are. Next, the budget application generation system receives the outline of a new project as input. For example, this includes information such as project name, responsible department, start date, budget, users, fees, and service overview. Based on this input information, the generation AI generates a draft budget application. The generated draft budget application also points out any deficiencies in the input information based on past budget approval results. For example, issues may be pointed out if the evidence for return on investment is weak or if the feasibility of systemization is not sufficiently considered. This allows applicants to supplement these shortcomings and create budget applications that are more likely to be approved. As a result, budget applications will be submitted more quickly, reducing the time lag from proposal to project launch. Furthermore, the creation of drafts and simplified reviews by the generation AI will shorten the time to budget approval, enabling smoother budget approval. In this way, the budget application generation system can automate the generation and critique of budget applications, shortening the time to budget approval.

[0029] The budget application generation system according to this embodiment comprises a collection unit, a learning unit, a reception unit, a generation unit, and an identification unit. The collection unit collects past budget applications. The collection unit collects budget applications in various formats and types, such as by fiscal year, project, or department. The collection unit can automatically collect past budget applications using AI. The learning unit learns from the budget applications collected by the collection unit. The learning unit learns from the collected budget applications using, for example, a machine learning algorithm. The learning unit can also learn whether or not a budget can be obtained and what the rejection points are. The learning unit can learn from budget applications using AI. The reception unit receives the outline of a new proposal. The reception unit receives information such as the project name, responsible department, start date, budget, user, fee, and service outline. The reception unit can automatically receive the outline of a new proposal using AI. The generation unit generates a budget application based on the outline received by the reception unit. The generation unit can perform template-based generation or automated generation using AI. The generation unit can generate budget applications using generation AI. The feedback unit identifies deficiencies in the input information based on the budget applications generated by the generation unit. The feedback unit can identify omissions of required items or inconsistencies in information, for example. The feedback unit can automatically identify deficiencies in the input information using AI. As a result, the budget application generation system according to this embodiment can automate the generation and feedback of budget applications, thereby shortening the time to budget approval.

[0030] The data collection unit collects past budget requests. The unit collects budget requests in various formats and types, such as by year, project, or department. Specifically, the unit searches for past budget requests in the company's databases and cloud storage and extracts the necessary data. The unit can also use AI to automatically collect past budget requests. The AI ​​uses natural language processing technology to analyze keywords and context within documents and identify relevant budget requests. For example, by entering a specific year or project name, the AI ​​can quickly search for and collect budget requests that match those criteria. The unit also has a conversion function to process documents in different formats and styles uniformly. This ensures that collected data is centrally managed and stored in a format easily usable for subsequent processing. Furthermore, the unit can automatically detect data duplication and inconsistencies and cleanse the data as needed. This allows the unit to provide accurate and reliable data, improving the overall accuracy of the system.

[0031] The learning unit learns from the budget requests collected by the collection unit. For example, the learning unit uses machine learning algorithms to learn from the collected budget requests. Specifically, the learning unit analyzes the text data of the collected budget requests and builds a model to understand their structure and content. The learning unit can also learn about the feasibility of budget acquisition and points of rejection. For example, it compares approved and rejected budget requests from the past to extract characteristics of requests that are likely to be approved and points of rejection. The learning unit can use AI to learn from budget requests. The AI ​​uses deep learning technology to extract patterns and trends from large amounts of data, accumulating knowledge useful for generating budget requests. Furthermore, the learning unit can regularly incorporate new data to continuously improve the accuracy of its model. This allows the learning unit to always support the generation of highly accurate budget requests based on the latest information.

[0032] The reception department receives project outlines for new proposals. The reception department accepts information such as project name, responsible department, start date, budget, users, fees, and service overview. Specifically, the reception department automatically analyzes the information entered by the user and extracts the necessary items. The reception department can automatically receive project outlines for new proposals using AI. The AI ​​uses natural language processing technology to analyze the text entered by the user and accurately extract the necessary information. For example, when a user enters the project name and budget, the AI ​​automatically recognizes this information and stores it in the database. The reception department also has a function to check the consistency of the entered information and detect missing items or inconsistent data. This allows the reception department to receive accurate and complete project outlines, enabling smooth subsequent processing. Furthermore, the reception department can provide input guides and feedback through the user interface, creating an environment where users can easily enter accurate information.

[0033] The generation unit generates budget application forms based on the project summaries received by the reception unit. The generation unit can perform template-based generation or automated generation using AI. Specifically, it generates budget application forms by selecting an appropriate template and filling in the necessary information based on the project summaries received from the reception unit. The generation unit can also generate budget application forms using generation AI. The generation AI learns from past budget application data and automatically generates the optimal format and content. For example, the generation AI automatically adds appropriate items and details according to the type and scale of the project, improving the completeness of the budget application form. Furthermore, the generation unit has a function to check the consistency and coherence of the generated budget application forms and make corrections as needed. This allows the generation unit to generate budget application forms quickly and accurately, reducing the burden on users. In addition, the generation unit provides users with a preview of the generated budget application form and an interface for making necessary corrections and additions.

[0034] The feedback unit identifies deficiencies in input information based on the budget application generated by the generation unit. For example, the feedback unit can identify missing required fields or inconsistencies in information. Specifically, it analyzes the generated budget application and checks whether all required fields are filled in and whether the information is consistent. The feedback unit can also use AI to automatically identify deficiencies in input information. The AI ​​uses rule-based algorithms and machine learning models to verify the content of the budget application and identify missing information or inconsistent data. For example, the AI ​​checks whether budget items are properly listed and whether amounts are calculated accurately, and notifies the user if there are problems. Furthermore, the feedback unit provides users with specific correction instructions and advice to help improve the quality of the budget application. This allows the feedback unit to improve the quality of budget applications and streamline the approval process. In addition, based on past feedback history, the feedback unit can analyze common problems and areas for improvement, continuously improving the accuracy and efficiency of the entire system.

[0035] The data collection unit can prioritize the collection of past budget requests that are related to specific projects or departments. For example, the data collection unit can prioritize the collection of requests related to specific projects to understand the progress of those projects. The data collection unit can prioritize the collection of requests related to specific departments to streamline departmental budget management. The data collection unit can prioritize the collection of requests submitted in a concentrated period to analyze budget trends for each period. This enables efficient data collection by prioritizing the collection of requests related to specific projects or departments. Some or all of the above processes in the data collection unit may be performed using AI or not. For example, the data collection unit can input data from requests related to specific projects or departments into a generating AI and have the generating AI select the requests to be collected preferentially.

[0036] The data collection unit can collect budget application approval history and reasons for rejection at the time of collection. For example, the data collection unit can collect budget application approval history and analyze past approval trends. The data collection unit can collect budget application rejection reasons and identify the causes of rejection. The data collection unit can collect budget application approval history and rejection reasons in combination and perform a comprehensive analysis. This makes it easier to analyze past trends by including approval history and rejection reasons in the collection. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on budget application approval history and rejection reasons into a generating AI and have the generating AI select the data to collect.

[0037] The collection unit can collect budget applications while considering the attribute information of the applicant. For example, the collection unit can prioritize the collection of high-priority applications by considering the applicant's position and department. The collection unit can prioritize the collection of highly reliable applications by considering the applicant's past application history. The collection unit can determine priority by considering the applicant's performance and evaluation. In this way, by considering the applicant's attribute information during collection, important applications can be collected preferentially. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input the applicant's attribute information into a generating AI and have the generating AI determine the priority of the applications to be collected.

[0038] The data collection unit can simultaneously collect relevant literature and reference materials for the budget application. For example, the data collection unit can automatically collect literature related to the budget application to enhance its reliability. The data collection unit can collect reference materials related to the budget application to strengthen the support for the application's content. The data collection unit can collect historical data related to the budget application to verify its validity. By simultaneously collecting relevant literature and reference materials, the reliability of the application can be enhanced. Some or all of the above-described processes in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on relevant literature and reference materials into a generating AI and have the generating AI select the materials to collect.

[0039] The learning unit can learn by analyzing in detail the approval history and reasons for rejection of budget applications during the learning process. For example, the learning unit can analyze the approval history in detail to learn the characteristics of applications that are likely to be approved. The learning unit can also analyze the reasons for rejection in detail to learn the characteristics of applications that are likely to be rejected. The learning unit can combine the analysis of the approval history and reasons for rejection to perform comprehensive learning. This allows for more accurate learning by analyzing the approval history and reasons for rejection in detail. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit can input data on the approval history and reasons for rejection of budget applications into a generating AI and have the generating AI perform a detailed analysis.

[0040] The learning unit can focus on learning data related to specific projects or departments during the learning process. For example, the learning unit can focus on learning data related to a specific project to understand the success factors of that project. The learning unit can focus on learning data related to a specific department to streamline the department's budget management. The learning unit can focus on learning data submitted intensively during a specific period to analyze budget trends for each period. This enables efficient learning by focusing on learning data related to specific projects or departments. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit can input data related to a specific project or department into a generating AI and have the generating AI select the data to focus on learning.

[0041] The learning unit can weight the training data based on the submission dates of budget requests during the training process. For example, the learning unit can prioritize data with recent submission dates to grasp the latest trends. It can also downplay data with distant submission dates to reduce the impact of outdated information. The learning unit can adjust the data weighting according to the submission dates to achieve balanced training. This makes it easier to grasp the latest trends by weighting the training data based on the submission dates. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can have a generating AI perform data weighting based on the submission dates of budget requests.

[0042] The learning unit can learn by referring to relevant literature and reference materials related to the budget application during the learning process. For example, the learning unit can improve the reliability of the application by referring to literature related to the budget application. The learning unit can strengthen the supporting evidence for the application by referring to reference materials related to the budget application. The learning unit can verify the validity of the application by referring to past data related to the budget application. In this way, the reliability of the application can be improved by learning by referring to relevant literature and reference materials. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit can input data of relevant literature and reference materials into a generating AI and have the generating AI select the materials to refer to for learning.

[0043] The reception department can determine the priority of applications based on the level of detail in the application summary. For example, the reception department can prioritize detailed application summaries for quick processing. It can also prioritize detailed applications and postpone simplified ones. The reception department can adjust priorities according to the importance of the application summary, enabling efficient application processing. This allows for efficient application processing by determining priorities based on the level of detail in the application summary. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can input the level of detail in the application summary into a generating AI and have the generating AI determine the priority of applications.

[0044] The reception department can apply different reception algorithms depending on the category of the case summary at the time of reception. For example, the reception department can select an appropriate reception algorithm depending on the project category. The reception department can apply different reception algorithms depending on the department category. The reception department can select the optimal reception algorithm depending on the importance of the case. This enables efficient reception by applying different reception algorithms depending on the category of the case summary. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can input the category of the case summary into a generating AI and have the generating AI select the reception algorithm to apply.

[0045] The reception department can determine the priority of applications based on the submission date of the application summary. For example, the reception department can prioritize applications with upcoming submission dates and process them quickly. The reception department can adjust the priority by postponing applications with later submission dates. The reception department can adjust the priority according to the submission date and process applications efficiently. This enables efficient application processing by determining the priority of applications based on the submission date. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can input the submission date of the application summary into a generating AI and have the generating AI determine the priority of applications.

[0046] The reception department can improve the accuracy of the reception process by referring to relevant information in the case summary at the time of reception. For example, the reception department can improve the accuracy of the reception process by referring to information related to the case summary. The reception department can improve the accuracy of the reception process by referring to past data related to the case summary. The reception department can improve the accuracy of the reception process by referring to literature related to the case summary. This enables efficient reception by improving the accuracy of the reception process by referring to relevant information. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can input relevant information in the case summary into a generating AI and have the generating AI select information to improve the accuracy of the reception process.

[0047] The generation unit can adjust the level of detail in the budget application based on the importance of the project overview during generation. For example, the generation unit can generate a detailed budget application for high-importance projects. For low-importance projects, the generation unit can generate a simplified budget application. The generation unit can adjust the level of detail in the budget application according to the importance of the project. This allows for efficient application generation by adjusting the level of detail in the budget application according to the importance of the project. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the importance of the project overview into the generation AI and have the generation AI determine the level of detail in the budget application.

[0048] The generation unit can apply different generation algorithms depending on the category of the case summary during generation. For example, the generation unit can select an appropriate generation algorithm depending on the project category. The generation unit can apply different generation algorithms depending on the department category. The generation unit can select the optimal generation algorithm depending on the importance of the case. This enables efficient application generation by applying the optimal generation algorithm according to the case category. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input the category of the case summary into the generation AI and have the generation AI select the generation algorithm to apply.

[0049] The generation unit can determine the priority of budget applications based on the submission dates of the project summaries during the generation process. For example, the generation unit can prioritize generating applications with upcoming submission dates and process them quickly. The generation unit can also adjust the priority by postponing applications with later submission dates. By adjusting the priority according to the submission dates, the generation unit can efficiently generate budget applications. This enables efficient application generation by determining priorities based on submission dates. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input the submission dates of the project summaries into the generation AI and have the generation AI determine the priority of the budget applications.

[0050] The generation unit can improve the accuracy of the budget application by referring to relevant information in the project overview during generation. For example, the generation unit can improve the accuracy of the budget application by referring to information related to the project overview. The generation unit can improve the accuracy of the budget application by referring to past data related to the project overview. The generation unit can improve the accuracy of the budget application by referring to literature related to the project overview. As a result, a more accurate application is generated by improving the accuracy of the application by referring to relevant information. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input relevant information in the project overview into the generation AI and have the generation AI select information to improve the accuracy of the budget application.

[0051] The feedback function can identify shortcomings by referring to the approval history and reasons for rejection of past budget applications. For example, the feedback function can refer to the approval history to identify characteristics of applications that are likely to be approved. The feedback function can also refer to the reasons for rejection to identify characteristics of applications that are likely to be rejected. The feedback function can refer to the approval history and reasons for rejection in combination to provide comprehensive feedback. This allows for more accurate feedback by referring to past approval history and reasons for rejection. Some or all of the above processing in the feedback function may be performed using AI or not. For example, the feedback function can input data on the approval history and reasons for rejection of budget applications into a generating AI and have the generating AI select the shortcomings to be identified.

[0052] The feedback function can apply different feedback algorithms depending on the category of the case summary when providing feedback. For example, the feedback function can select an appropriate feedback algorithm depending on the project category. The feedback function can apply different feedback algorithms depending on the department category. The feedback function can select the optimal feedback algorithm depending on the importance of the case. This enables efficient feedback by applying the optimal feedback algorithm according to the case category. Some or all of the above processes in the feedback function may be performed using AI or not. For example, the feedback function can input the category of the case summary into a generating AI and have the generating AI select the feedback algorithm to apply.

[0053] The feedback unit can identify deficiencies based on the submission date of the project summary. For example, the feedback unit can prioritize and process projects with upcoming submission dates quickly. It can also adjust priorities by postponing projects with later submission dates. By adjusting priorities according to submission dates, the feedback unit can provide feedback efficiently. This enables efficient feedback by providing feedback based on submission dates. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can input the submission dates of project summaries into a generating AI and have the generating AI determine the priority of identifying deficiencies.

[0054] The feedback function can improve the accuracy of its feedback by referring to relevant information in the project overview when providing feedback. For example, the feedback function can improve the accuracy of its feedback by referring to information related to the project overview. The feedback function can improve the accuracy of its feedback by referring to past data related to the project overview. The feedback function can improve the accuracy of its feedback by referring to literature related to the project overview. By improving the accuracy of feedback by referring to relevant information, more accurate feedback becomes possible. Some or all of the above processing in the feedback function may be performed using AI or not. For example, the feedback function can input relevant information from the project overview into a generating AI and have the generating AI select information to improve the accuracy of the feedback.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The budget application generation system also includes a notification unit. The notification unit can notify relevant parties of the draft budget application and any issues pointed out. For example, the notification unit can send the draft budget application to relevant parties via email or chat tools. The notification unit can also notify relevant parties of any shortcomings pointed out by the issues unit and encourage them to make corrections. The notification unit can also notify relevant parties of the progress of the budget application in real time, enabling smooth communication. This facilitates information sharing among stakeholders and allows for quick revisions and approvals of the budget application.

[0057] The budget application generation system also includes an analysis unit. This unit analyzes the data from the generated budget applications and can predict the success rate of budget approval. For example, the analysis unit scores the success rate of the generated budget applications based on past budget application data. It can also analyze the content and structure of the budget applications and suggest improvements to increase the success rate. Before the budget application is submitted, the analysis unit can predict the success rate and provide feedback to the applicant. This allows applicants to improve the quality of their budget applications and increase their chances of approval.

[0058] The budget application generation system also includes an archiving section. The archiving section can save generated budget applications and their comments for later reference. For example, the archiving section can classify and save generated budget applications by project or year. The archiving section also saves deficiencies and correction history pointed out by the comments section for later reference. The archiving section can search past budget applications and comments and provide them as reference information for similar cases. This allows for effective use of past data to aid in the creation and revision of budget applications.

[0059] The budget application generation system also includes a feedback unit. The feedback unit collects feedback from stakeholders on the generated budget applications and uses this feedback to improve the system. For example, the feedback unit collects stakeholders' evaluations and comments on the generated budget applications. The feedback unit can also collect stakeholders' opinions on shortcomings pointed out by the feedback unit and incorporate them into system improvements. Furthermore, the feedback unit can survey stakeholders' satisfaction with the budget application generation process and identify areas for system improvement. This enables system improvements that reflect stakeholder feedback, thereby improving the quality of budget applications.

[0060] The budget request generation system also includes a customization section. This section allows users to customize budget request templates and generation methods according to their needs. For example, the customization section creates budget request templates based on user-specified formats and items. It can also propose the optimal generation method based on the user's industry and business operations. Based on user feedback, the customization section can adjust the budget request generation process to provide a more user-friendly system. This enables flexible budget request generation tailored to user needs, thereby improving user satisfaction.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The collection unit collects past budget requests. The collection unit can collect budget requests in various formats and types, such as by year, project, or department, and can do so automatically using AI. Step 2: The learning unit learns from the budget requests collected by the collection unit. The learning unit uses machine learning algorithms to learn whether or not a budget can be obtained and what the rejection points are, and can use AI to learn from budget requests. Step 3: The reception department receives the project outline for new proposals. The reception department receives information such as the project name, responsible department, start date, budget, users, fees, and service overview, and can automatically process the information using AI. Step 4: The generation unit generates a budget application form based on the case summary received by the reception unit. The generation unit can perform template-based generation or automated generation using AI, and can generate the budget application form using the generation AI. Step 5: The feedback unit identifies deficiencies in the input information based on the budget request form generated by the generation unit. The feedback unit can identify missing required items, inconsistencies in information, etc., and can automatically identify these issues using AI.

[0063] (Example of form 2) The budget application generation system according to an embodiment of the present invention is a system that shortens the time to budget approval by utilizing a generation AI. The budget application generation system uses past budget applications as training data and learns whether or not a budget can be obtained and what the rejection points are. The budget application generation system receives the outline of a new project as input and outputs a draft budget application. This reduces the time lag from proposal to project launch and enables smooth budget approval. For example, the budget application generation system collects past budget applications as training data, and the generation AI learns from this. At this time, it also learns whether or not a budget can be obtained and what the rejection points are. Next, the budget application generation system receives the outline of a new project as input. For example, this includes information such as project name, responsible department, start date, budget, users, fees, and service overview. Based on this input information, the generation AI generates a draft budget application. The generated draft budget application also points out any deficiencies in the input information based on past budget approval results. For example, issues may be pointed out if the evidence for return on investment is weak or if the feasibility of systemization is not sufficiently considered. This allows applicants to supplement these shortcomings and create budget applications that are more likely to be approved. As a result, budget applications will be submitted more quickly, reducing the time lag from proposal to project launch. Furthermore, the creation of drafts and simplified reviews by the generation AI will shorten the time to budget approval, enabling smoother budget approval. In this way, the budget application generation system can automate the generation and critique of budget applications, shortening the time to budget approval.

[0064] The budget application generation system according to this embodiment comprises a collection unit, a learning unit, a reception unit, a generation unit, and an identification unit. The collection unit collects past budget applications. The collection unit collects budget applications in various formats and types, such as by fiscal year, project, or department. The collection unit can automatically collect past budget applications using AI. The learning unit learns from the budget applications collected by the collection unit. The learning unit learns from the collected budget applications using, for example, a machine learning algorithm. The learning unit can also learn whether or not a budget can be obtained and what the rejection points are. The learning unit can learn from budget applications using AI. The reception unit receives the outline of a new proposal. The reception unit receives information such as the project name, responsible department, start date, budget, user, fee, and service outline. The reception unit can automatically receive the outline of a new proposal using AI. The generation unit generates a budget application based on the outline received by the reception unit. The generation unit can perform template-based generation or automated generation using AI. The generation unit can generate budget applications using generation AI. The feedback unit identifies deficiencies in the input information based on the budget applications generated by the generation unit. The feedback unit can identify omissions of required items or inconsistencies in information, for example. The feedback unit can automatically identify deficiencies in the input information using AI. As a result, the budget application generation system according to this embodiment can automate the generation and feedback of budget applications, thereby shortening the time to budget approval.

[0065] The data collection unit collects past budget requests. The unit collects budget requests in various formats and types, such as by year, project, or department. Specifically, the unit searches for past budget requests in the company's databases and cloud storage and extracts the necessary data. The unit can also use AI to automatically collect past budget requests. The AI ​​uses natural language processing technology to analyze keywords and context within documents and identify relevant budget requests. For example, by entering a specific year or project name, the AI ​​can quickly search for and collect budget requests that match those criteria. The unit also has a conversion function to process documents in different formats and styles uniformly. This ensures that collected data is centrally managed and stored in a format easily usable for subsequent processing. Furthermore, the unit can automatically detect data duplication and inconsistencies and cleanse the data as needed. This allows the unit to provide accurate and reliable data, improving the overall accuracy of the system.

[0066] The learning unit learns from the budget requests collected by the collection unit. For example, the learning unit uses machine learning algorithms to learn from the collected budget requests. Specifically, the learning unit analyzes the text data of the collected budget requests and builds a model to understand their structure and content. The learning unit can also learn about the feasibility of budget acquisition and points of rejection. For example, it compares approved and rejected budget requests from the past to extract characteristics of requests that are likely to be approved and points of rejection. The learning unit can use AI to learn from budget requests. The AI ​​uses deep learning technology to extract patterns and trends from large amounts of data, accumulating knowledge useful for generating budget requests. Furthermore, the learning unit can regularly incorporate new data to continuously improve the accuracy of its model. This allows the learning unit to always support the generation of highly accurate budget requests based on the latest information.

[0067] The reception department receives project outlines for new proposals. The reception department accepts information such as project name, responsible department, start date, budget, users, fees, and service overview. Specifically, the reception department automatically analyzes the information entered by the user and extracts the necessary items. The reception department can automatically receive project outlines for new proposals using AI. The AI ​​uses natural language processing technology to analyze the text entered by the user and accurately extract the necessary information. For example, when a user enters the project name and budget, the AI ​​automatically recognizes this information and stores it in the database. The reception department also has a function to check the consistency of the entered information and detect missing items or inconsistent data. This allows the reception department to receive accurate and complete project outlines, enabling smooth subsequent processing. Furthermore, the reception department can provide input guides and feedback through the user interface, creating an environment where users can easily enter accurate information.

[0068] The generation unit generates budget application forms based on the project summaries received by the reception unit. The generation unit can perform template-based generation or automated generation using AI. Specifically, it generates budget application forms by selecting an appropriate template and filling in the necessary information based on the project summaries received from the reception unit. The generation unit can also generate budget application forms using generation AI. The generation AI learns from past budget application data and automatically generates the optimal format and content. For example, the generation AI automatically adds appropriate items and details according to the type and scale of the project, improving the completeness of the budget application form. Furthermore, the generation unit has a function to check the consistency and coherence of the generated budget application forms and make corrections as needed. This allows the generation unit to generate budget application forms quickly and accurately, reducing the burden on users. In addition, the generation unit provides users with a preview of the generated budget application form and an interface for making necessary corrections and additions.

[0069] The feedback unit identifies deficiencies in input information based on the budget application generated by the generation unit. For example, the feedback unit can identify missing required fields or inconsistencies in information. Specifically, it analyzes the generated budget application and checks whether all required fields are filled in and whether the information is consistent. The feedback unit can also use AI to automatically identify deficiencies in input information. The AI ​​uses rule-based algorithms and machine learning models to verify the content of the budget application and identify missing information or inconsistent data. For example, the AI ​​checks whether budget items are properly listed and whether amounts are calculated accurately, and notifies the user if there are problems. Furthermore, the feedback unit provides users with specific correction instructions and advice to help improve the quality of the budget application. This allows the feedback unit to improve the quality of budget applications and streamline the approval process. In addition, based on past feedback history, the feedback unit can analyze common problems and areas for improvement, continuously improving the accuracy and efficiency of the entire system.

[0070] The data collection unit can estimate the user's emotions and adjust the timing of budget request collection based on the estimated emotions. For example, if the user is stressed, the data collection unit can delay the collection timing to reduce the user's burden. If the user is relaxed, the data collection unit can accelerate the collection timing to collect data efficiently. If the user is in a hurry, the data collection unit can start urgently and acquire data quickly. This reduces the user's burden by adjusting the collection timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0071] The data collection unit can prioritize the collection of past budget requests that are related to specific projects or departments. For example, the data collection unit can prioritize the collection of requests related to specific projects to understand the progress of those projects. The data collection unit can prioritize the collection of requests related to specific departments to streamline departmental budget management. The data collection unit can prioritize the collection of requests submitted in a concentrated period to analyze budget trends for each period. This enables efficient data collection by prioritizing the collection of requests related to specific projects or departments. Some or all of the above processes in the data collection unit may be performed using AI or not. For example, the data collection unit can input data from requests related to specific projects or departments into a generating AI and have the generating AI select the requests to be collected preferentially.

[0072] The data collection unit can collect budget application approval history and reasons for rejection at the time of collection. For example, the data collection unit can collect budget application approval history and analyze past approval trends. The data collection unit can collect budget application rejection reasons and identify the causes of rejection. The data collection unit can collect budget application approval history and rejection reasons in combination and perform a comprehensive analysis. This makes it easier to analyze past trends by including approval history and rejection reasons in the collection. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on budget application approval history and rejection reasons into a generating AI and have the generating AI select the data to collect.

[0073] The data collection unit can estimate the user's emotions and determine the priority of budget requests to collect based on the estimated emotions. For example, if the user is stressed, the data collection unit will postpone collecting less important requests. If the user is relaxed, the data collection unit can prioritize collecting more important requests. If the user is in a hurry, the data collection unit can prioritize collecting urgent requests. This enables efficient data collection by prioritizing budget requests according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0074] The collection unit can collect budget applications while considering the attribute information of the applicant. For example, the collection unit can prioritize the collection of high-priority applications by considering the applicant's position and department. The collection unit can prioritize the collection of highly reliable applications by considering the applicant's past application history. The collection unit can determine priority by considering the applicant's performance and evaluation. In this way, by considering the applicant's attribute information during collection, important applications can be collected preferentially. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input the applicant's attribute information into a generating AI and have the generating AI determine the priority of the applications to be collected.

[0075] The data collection unit can simultaneously collect relevant literature and reference materials for the budget application. For example, the data collection unit can automatically collect literature related to the budget application to enhance its reliability. The data collection unit can collect reference materials related to the budget application to strengthen the support for the application's content. The data collection unit can collect historical data related to the budget application to verify its validity. By simultaneously collecting relevant literature and reference materials, the reliability of the application can be enhanced. Some or all of the above-described processes in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on relevant literature and reference materials into a generating AI and have the generating AI select the materials to collect.

[0076] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is stressed, the learning unit will prioritize learning simple and easy-to-understand data. If the user is relaxed, the learning unit can learn detailed and complex data. If the user is in a hurry, the learning unit can select data that can be learned quickly. This enables efficient learning by selecting training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0077] The learning unit can learn by analyzing in detail the approval history and reasons for rejection of budget applications during the learning process. For example, the learning unit can analyze the approval history in detail to learn the characteristics of applications that are likely to be approved. The learning unit can also analyze the reasons for rejection in detail to learn the characteristics of applications that are likely to be rejected. The learning unit can combine the analysis of the approval history and reasons for rejection to perform comprehensive learning. This allows for more accurate learning by analyzing the approval history and reasons for rejection in detail. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit can input data on the approval history and reasons for rejection of budget applications into a generating AI and have the generating AI perform a detailed analysis.

[0078] The learning unit can focus on learning data related to specific projects or departments during the learning process. For example, the learning unit can focus on learning data related to a specific project to understand the success factors of that project. The learning unit can focus on learning data related to a specific department to streamline the department's budget management. The learning unit can focus on learning data submitted intensively during a specific period to analyze budget trends for each period. This enables efficient learning by focusing on learning data related to specific projects or departments. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit can input data related to a specific project or department into a generating AI and have the generating AI select the data to focus on learning.

[0079] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can reduce the learning frequency to alleviate the burden. If the user is relaxed, the learning unit can increase the learning frequency to learn data more efficiently. If the user is in a hurry, the learning unit can adjust the learning frequency to learn data quickly. This allows for efficient learning by adjusting the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0080] The learning unit can weight the training data based on the submission dates of budget requests during the training process. For example, the learning unit can prioritize data with recent submission dates to grasp the latest trends. It can also downplay data with distant submission dates to reduce the impact of outdated information. The learning unit can adjust the data weighting according to the submission dates to achieve balanced training. This makes it easier to grasp the latest trends by weighting the training data based on the submission dates. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can have a generating AI perform data weighting based on the submission dates of budget requests.

[0081] The learning unit can learn by referring to relevant literature and reference materials related to the budget application during the learning process. For example, the learning unit can improve the reliability of the application by referring to literature related to the budget application. The learning unit can strengthen the supporting evidence for the application by referring to reference materials related to the budget application. The learning unit can verify the validity of the application by referring to past data related to the budget application. In this way, the reliability of the application can be improved by learning by referring to relevant literature and reference materials. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit can input data of relevant literature and reference materials into a generating AI and have the generating AI select the materials to refer to for learning.

[0082] The reception desk can estimate the user's emotions and adjust the process of receiving the case summary based on the estimated emotions. For example, if the user is stressed, the reception desk can provide a simple interface and minimize the input steps. If the user is relaxed, the reception desk can provide detailed input options and suggest a customizable input method. If the user is in a hurry, the reception desk can prioritize voice input to allow for quick entry of the case summary. This reduces the burden on the user by adjusting the reception process according to their emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0083] The reception department can determine the priority of applications based on the level of detail in the application summary. For example, the reception department can prioritize detailed application summaries for quick processing. It can also prioritize detailed applications and postpone simplified ones. The reception department can adjust priorities according to the importance of the application summary, enabling efficient application processing. This allows for efficient application processing by determining priorities based on the level of detail in the application summary. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can input the level of detail in the application summary into a generating AI and have the generating AI determine the priority of applications.

[0084] The reception department can apply different reception algorithms depending on the category of the case summary at the time of reception. For example, the reception department can select an appropriate reception algorithm depending on the project category. The reception department can apply different reception algorithms depending on the department category. The reception department can select the optimal reception algorithm depending on the importance of the case. This enables efficient reception by applying different reception algorithms depending on the category of the case summary. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can input the category of the case summary into a generating AI and have the generating AI select the reception algorithm to apply.

[0085] The reception desk can estimate the user's emotions and adjust the length of the reception based on the estimated emotions. For example, if the user is stressed, the reception desk can shorten the reception time and process the call quickly. If the user is relaxed, the reception desk can extend the reception time and collect more detailed information. If the user is in a hurry, the reception desk can adjust the reception time and process the call quickly. This reduces the user's burden by adjusting the reception time according to their emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the user's facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0086] The reception department can determine the priority of applications based on the submission date of the application summary. For example, the reception department can prioritize applications with upcoming submission dates and process them quickly. The reception department can adjust the priority by postponing applications with later submission dates. The reception department can adjust the priority according to the submission date and process applications efficiently. This enables efficient application processing by determining the priority of applications based on the submission date. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can input the submission date of the application summary into a generating AI and have the generating AI determine the priority of applications.

[0087] The reception department can improve the accuracy of the reception process by referring to relevant information in the case summary at the time of reception. For example, the reception department can improve the accuracy of the reception process by referring to information related to the case summary. The reception department can improve the accuracy of the reception process by referring to past data related to the case summary. The reception department can improve the accuracy of the reception process by referring to literature related to the case summary. This enables efficient reception by improving the accuracy of the reception process by referring to relevant information. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can input relevant information in the case summary into a generating AI and have the generating AI select information to improve the accuracy of the reception process.

[0088] The generation unit can estimate the user's emotions and adjust the budget request generation method based on the estimated user emotions. For example, if the user is stressed, the generation unit can generate a simple and easy-to-understand budget request. If the user is relaxed, the generation unit can generate a detailed and complex budget request. If the user is in a hurry, the generation unit can create a budget request that can be generated quickly. This reduces the user's burden by adjusting the generation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using or without a generation AI. For example, the generation unit can input user facial expression data into a generation AI and have the generation AI perform the user's emotion estimation.

[0089] The generation unit can adjust the level of detail in the budget application based on the importance of the project overview during generation. For example, the generation unit can generate a detailed budget application for high-importance projects. For low-importance projects, the generation unit can generate a simplified budget application. The generation unit can adjust the level of detail in the budget application according to the importance of the project. This allows for efficient application generation by adjusting the level of detail in the budget application according to the importance of the project. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the importance of the project overview into the generation AI and have the generation AI determine the level of detail in the budget application.

[0090] The generation unit can apply different generation algorithms depending on the category of the case summary during generation. For example, the generation unit can select an appropriate generation algorithm depending on the project category. The generation unit can apply different generation algorithms depending on the department category. The generation unit can select the optimal generation algorithm depending on the importance of the case. This enables efficient application generation by applying the optimal generation algorithm according to the case category. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input the category of the case summary into the generation AI and have the generation AI select the generation algorithm to apply.

[0091] The generation unit can estimate the user's emotions and adjust the length of the budget request based on the estimated emotions. For example, if the user is stressed, the generation unit can generate a short, concise budget request. If the user is relaxed, the generation unit can generate a longer budget request with detailed explanations. If the user is in a hurry, the generation unit can create a short budget request that can be generated quickly. This reduces the user's burden by adjusting the length of the request according to their emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using or without a generation AI. For example, the generation unit can input user facial expression data into a generation AI and have the generation AI perform the estimation of the user's emotions.

[0092] The generation unit can determine the priority of budget applications based on the submission dates of the project summaries during the generation process. For example, the generation unit can prioritize generating applications with upcoming submission dates and process them quickly. The generation unit can also adjust the priority by postponing applications with later submission dates. By adjusting the priority according to the submission dates, the generation unit can efficiently generate budget applications. This enables efficient application generation by determining priorities based on submission dates. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input the submission dates of the project summaries into the generation AI and have the generation AI determine the priority of the budget applications.

[0093] The generation unit can improve the accuracy of the budget application by referring to relevant information in the project overview during generation. For example, the generation unit can improve the accuracy of the budget application by referring to information related to the project overview. The generation unit can improve the accuracy of the budget application by referring to past data related to the project overview. The generation unit can improve the accuracy of the budget application by referring to literature related to the project overview. As a result, a more accurate application is generated by improving the accuracy of the application by referring to relevant information. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input relevant information in the project overview into the generation AI and have the generation AI select information to improve the accuracy of the budget application.

[0094] The feedback unit can estimate the user's emotions and adjust how it points out shortcomings in the input information based on the estimated emotions. For example, if the user is stressed, the feedback unit can provide a simple and easy-to-understand feedback method. If the user is relaxed, the feedback unit can provide a detailed feedback method. If the user is in a hurry, the feedback unit can provide a method that allows for quick feedback. This reduces the burden on the user by adjusting the feedback method according to their emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0095] The feedback function can identify shortcomings by referring to the approval history and reasons for rejection of past budget applications. For example, the feedback function can refer to the approval history to identify characteristics of applications that are likely to be approved. The feedback function can also refer to the reasons for rejection to identify characteristics of applications that are likely to be rejected. The feedback function can refer to the approval history and reasons for rejection in combination to provide comprehensive feedback. This allows for more accurate feedback by referring to past approval history and reasons for rejection. Some or all of the above processing in the feedback function may be performed using AI or not. For example, the feedback function can input data on the approval history and reasons for rejection of budget applications into a generating AI and have the generating AI select the shortcomings to be identified.

[0096] The feedback function can apply different feedback algorithms depending on the category of the case summary when providing feedback. For example, the feedback function can select an appropriate feedback algorithm depending on the project category. The feedback function can apply different feedback algorithms depending on the department category. The feedback function can select the optimal feedback algorithm depending on the importance of the case. This enables efficient feedback by applying the optimal feedback algorithm according to the case category. Some or all of the above processes in the feedback function may be performed using AI or not. For example, the feedback function can input the category of the case summary into a generating AI and have the generating AI select the feedback algorithm to apply.

[0097] The feedback unit can estimate the user's emotions and prioritize the criticisms of shortcomings based on those emotions. For example, if the user is stressed, the feedback unit will postpone less important criticisms. If the user is relaxed, the feedback unit can prioritize more important criticisms. If the user is in a hurry, the feedback unit can prioritize urgent criticisms. This allows for efficient feedback by prioritizing criticisms according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can input user facial expression data into a generative AI and have the generative AI perform the user's emotion estimation.

[0098] The feedback unit can identify deficiencies based on the submission date of the project summary. For example, the feedback unit can prioritize and process projects with upcoming submission dates quickly. It can also adjust priorities by postponing projects with later submission dates. By adjusting priorities according to submission dates, the feedback unit can provide feedback efficiently. This enables efficient feedback by providing feedback based on submission dates. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can input the submission dates of project summaries into a generating AI and have the generating AI determine the priority of identifying deficiencies.

[0099] The feedback function can improve the accuracy of its feedback by referring to relevant information in the project overview when providing feedback. For example, the feedback function can improve the accuracy of its feedback by referring to information related to the project overview. The feedback function can improve the accuracy of its feedback by referring to past data related to the project overview. The feedback function can improve the accuracy of its feedback by referring to literature related to the project overview. By improving the accuracy of feedback by referring to relevant information, more accurate feedback becomes possible. Some or all of the above processing in the feedback function may be performed using AI or not. For example, the feedback function can input relevant information from the project overview into a generating AI and have the generating AI select information to improve the accuracy of the feedback.

[0100] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0101] The budget application generation system also includes a notification unit. The notification unit can notify relevant parties of the draft budget application and any issues pointed out. For example, the notification unit can send the draft budget application to relevant parties via email or chat tools. The notification unit can also notify relevant parties of any shortcomings pointed out by the issues unit and encourage them to make corrections. The notification unit can also notify relevant parties of the progress of the budget application in real time, enabling smooth communication. This facilitates information sharing among stakeholders and allows for quick revisions and approvals of the budget application.

[0102] The budget application generation system also includes an analysis unit. This unit analyzes the data from the generated budget applications and can predict the success rate of budget approval. For example, the analysis unit scores the success rate of the generated budget applications based on past budget application data. It can also analyze the content and structure of the budget applications and suggest improvements to increase the success rate. Before the budget application is submitted, the analysis unit can predict the success rate and provide feedback to the applicant. This allows applicants to improve the quality of their budget applications and increase their chances of approval.

[0103] The budget application generation system also includes an archiving section. The archiving section can save generated budget applications and their comments for later reference. For example, the archiving section can classify and save generated budget applications by project or year. The archiving section also saves deficiencies and correction history pointed out by the comments section for later reference. The archiving section can search past budget applications and comments and provide them as reference information for similar cases. This allows for effective use of past data to aid in the creation and revision of budget applications.

[0104] The budget application generation system also includes a feedback unit. The feedback unit collects feedback from stakeholders on the generated budget applications and uses this feedback to improve the system. For example, the feedback unit collects stakeholders' evaluations and comments on the generated budget applications. The feedback unit can also collect stakeholders' opinions on shortcomings pointed out by the feedback unit and incorporate them into system improvements. Furthermore, the feedback unit can survey stakeholders' satisfaction with the budget application generation process and identify areas for system improvement. This enables system improvements that reflect stakeholder feedback, thereby improving the quality of budget applications.

[0105] The budget request generation system also includes a customization section. This section allows users to customize budget request templates and generation methods according to their needs. For example, the customization section creates budget request templates based on user-specified formats and items. It can also propose the optimal generation method based on the user's industry and business operations. Based on user feedback, the customization section can adjust the budget request generation process to provide a more user-friendly system. This enables flexible budget request generation tailored to user needs, thereby improving user satisfaction.

[0106] The budget request generation system also includes an emotion estimation unit. This unit estimates the user's emotions and adjusts the budget request generation process based on the estimated emotions. For example, if the user is stressed, the emotion estimation unit generates a simple and easy-to-understand budget request. If the user is relaxed, the emotion estimation unit can generate a detailed and complex budget request. If the user is in a hurry, the emotion estimation unit can create a budget request that can be generated quickly. This reduces the user's burden by adjusting the generation process according to their emotions.

[0107] The budget request generation system also includes an emotional feedback unit. This unit collects user feedback on the generated budget requests and uses it to improve the system. For example, it collects user satisfaction and dissatisfaction with the generated budget requests. It also collects user feedback on shortcomings pointed out by the feedback unit and incorporates this feedback into system improvements. The emotional feedback unit investigates user feelings towards the budget request generation process and identifies areas for system improvement. This allows for system improvements that reflect user sentiment, thereby improving the quality of budget requests.

[0108] The budget request generation system also includes an emotion analysis unit. This unit analyzes the user's emotions and reflects them in the budget request generation process. For example, it collects user emotion data and analyzes stress levels and satisfaction levels. Based on the analysis results, the unit can adjust the budget request generation method and feedback methods. The emotion analysis unit optimizes the budget request generation process according to the user's emotions, reducing the user's burden. This enables the generation of budget requests that take user emotions into consideration, thereby improving user satisfaction.

[0109] The budget application generation system also includes an emotion monitoring unit. This unit can monitor the user's emotions in real time and reflect them in the budget application generation process. For example, it analyzes the user's facial expressions and voice data in real time to estimate their emotions. Based on the estimated emotions, the unit can adjust the budget application generation method and feedback methods in real time. The emotion monitoring unit optimizes the budget application generation process according to the user's emotions, reducing the user's burden. This enables the generation of budget applications that reflect the user's emotions in real time, thereby improving user satisfaction.

[0110] The budget application generation system further includes an emotion-adaptive unit. This unit can provide a budget application generation process that adapts to the user's emotions. For example, if the user is stressed, it provides a simple and easy-to-understand interface. If the user is relaxed, it can provide detailed input options and suggest a customizable generation process. If the user is in a hurry, it can prioritize voice input to enable rapid budget application generation. This reduces the user's burden by providing a budget application generation process that adapts to their emotions.

[0111] The following briefly describes the processing flow for example form 2.

[0112] Step 1: The collection unit collects past budget requests. The collection unit can collect budget requests in various formats and types, such as by year, project, or department, and can do so automatically using AI. Step 2: The learning unit learns from the budget requests collected by the collection unit. The learning unit uses machine learning algorithms to learn whether or not a budget can be obtained and what the rejection points are, and can use AI to learn from budget requests. Step 3: The reception department receives the project outline for new proposals. The reception department receives information such as the project name, responsible department, start date, budget, users, fees, and service overview, and can automatically process the information using AI. Step 4: The generation unit generates a budget application form based on the case summary received by the reception unit. The generation unit can perform template-based generation or automated generation using AI, and can generate the budget application form using the generation AI. Step 5: The feedback unit identifies deficiencies in the input information based on the budget request form generated by the generation unit. The feedback unit can identify missing required items, inconsistencies in information, etc., and can automatically identify these issues using AI.

[0113] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0114] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0115] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0116] Each of the multiple elements described above, including the collection unit, learning unit, reception unit, generation unit, and feedback unit, is implemented, for example, in at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects past budget applications using the camera 42 and microphone 38B of the smart device 14 and performs the collection process using the control unit 46A. The learning unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and learns from the collected budget applications. The reception unit is implemented, for example, by the control unit 46A of the smart device 14 and receives the outline of a new application. The generation unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and generates a budget application based on the outline received by the reception unit. The feedback unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and points out any deficiencies in the input information based on the generated budget application. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0117] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0118] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0123] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0124] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0125] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0126] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0127] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0129] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0131] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements described above, including the collection unit, learning unit, reception unit, generation unit, and identification unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit collects past budget applications using the camera 42 and microphone 238 of the smart glasses 214 and performs the collection process using the control unit 46A. The learning unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12 and learns from the collected budget applications. The reception unit is implemented, for example, in the control unit 46A of the smart glasses 214 and receives the outline of a new application. The generation unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12 and generates a budget application based on the outline of the application received by the reception unit. The identification unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12 and identifies any deficiencies in the input information based on the generated budget application. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0133] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0134] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0136] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the 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 image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0141] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0142] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0143] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0147] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] Each of the multiple elements described above, including the collection unit, learning unit, reception unit, generation unit, and feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects past budget applications using the camera 42 and microphone 238 of the headset terminal 314 and performs the collection process using the control unit 46A. The learning unit is implemented in the specific processing unit 290 of the data processing unit 12 and learns from the collected budget applications. The reception unit is implemented in the specific processing unit 46A of the headset terminal 314 and receives the outline of a new proposal. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12 and generates a budget application based on the outline received by the reception unit. The feedback unit is implemented in the specific processing unit 290 of the data processing unit 12 and points out any deficiencies in the input information based on the generated budget application. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0149] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0150] As shown in Figure 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.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0153] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0155] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0156] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0157] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0159] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0160] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0163] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0164] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] Each of the multiple elements described above, including the collection unit, learning unit, reception unit, generation unit, and identification unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects past budget applications using the camera 42 and microphone 238 of the robot 414 and performs the collection process using the control unit 46A. The learning unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12 and learns from the collected budget applications. The reception unit is implemented, for example, in the control unit 46A of the robot 414 and receives the outline of a new proposal. The generation unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12 and generates a budget application based on the outline of the application received by the reception unit. The identification unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12 and points out any deficiencies in the input information based on the generated budget application. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0166] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0167] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0168] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0169] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0170] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0171] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0174] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0175] 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.

[0176] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0177] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0178] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0179] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0180] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0181] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0182] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0183] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0184] (Note 1) The collection department collects past budget requests, A learning unit that studies the budget application forms collected by the aforementioned collection unit, The reception department accepts the outlines of new proposals, A generation unit that generates a budget application form based on the case summary received by the aforementioned reception unit, The system includes a reporting unit that identifies deficiencies in input information based on the budget application form generated by the generation unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is The system estimates user sentiment and adjusts the timing of budget request collection based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is When collecting past budget requests, prioritize collecting requests related to specific projects or departments. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is When collecting information, include the approval history and reasons for rejection of the budget application. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is It estimates user sentiment and prioritizes budget requests to be collected based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is When collecting data, consider the attribute information of the person who submitted the budget request. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is When collecting information, also collect related documents and reference materials for the budget application. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, During the learning process, study the approval history and reasons for rejection of budget requests in detail. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, During learning, focus on learning data related to specific projects or departments. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned learning unit, During training, the training data is weighted based on when the budget request was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned learning unit, When studying, refer to relevant literature and reference materials related to budget applications. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned reception unit is The system estimates the user's emotions and adjusts the method of receiving case summaries based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned reception unit is Upon receiving your application, we will determine the priority of submission based on the level of detail in your application summary. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned reception unit is When a case is submitted, a different submission algorithm is applied depending on the category of the case summary. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned reception unit is The system estimates the user's emotions and adjusts the length of the reception process based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned reception unit is At the time of application, priority will be determined based on when the project summary was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned reception unit is When receiving a case, we refer to relevant information in the case summary to improve the accuracy of the application process. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is The system estimates user sentiment and adjusts the budget request generation process based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is During generation, the level of detail in the budget request is adjusted based on the importance of the project overview. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is During generation, different generation algorithms are applied depending on the category of the project overview. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is The system estimates the user's emotions and adjusts the length of the budget request based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is During generation, the priority of budget requests is determined based on the submission timing of the project outlines. The system described in Appendix 1, characterized by the features described herein. (Note 25) The generating unit is During generation, the accuracy of the budget request is improved by referencing relevant information from the project overview. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned point is, It estimates the user's emotions and adjusts how it identifies shortcomings in the input information based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned point is, When pointing out shortcomings, refer to the approval history and reasons for rejection of past budget applications to identify deficiencies. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned point is, When issuing a report, a different reporting algorithm is applied depending on the category of the case summary. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned point is, The system estimates the user's emotions and prioritizes identifying shortcomings based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned point is, When providing feedback, we will point out any shortcomings based on when the project summary was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned point is, When providing feedback, refer to relevant information in the project overview to improve the accuracy of identifying shortcomings. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The collection department collects past budget requests, A learning unit that studies the budget application forms collected by the aforementioned collection unit, The reception department accepts the outlines of new proposals, A generation unit that generates a budget application form based on the case summary received by the aforementioned reception unit, The system includes a reporting unit that identifies deficiencies in input information based on the budget application form generated by the generation unit. A system characterized by the following features.

2. The aforementioned collection unit is The system estimates user sentiment and adjusts the timing of budget request collection based on the estimated user sentiment. The system according to feature 1.

3. The aforementioned collection unit is When collecting past budget requests, prioritize collecting requests related to specific projects or departments. The system according to feature 1.

4. The aforementioned collection unit is When collecting information, include the approval history and reasons for rejection of the budget application. The system according to feature 1.

5. The aforementioned collection unit is It estimates user sentiment and prioritizes budget requests to be collected based on the estimated user sentiment. The system according to feature 1.

6. The aforementioned collection unit is When collecting data, consider the attribute information of the person who submitted the budget request. The system according to feature 1.

7. The aforementioned collection unit is When collecting information, also collect related documents and reference materials for the budget application. The system according to feature 1.

8. The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system according to feature 1.

9. The aforementioned learning unit, During the learning process, study the approval history and reasons for rejection of budget requests in detail. The system according to feature 1.

10. The aforementioned learning unit, During learning, focus on learning data related to specific projects or departments. The system according to feature 1.

Images