system

Abstract

We provide the system. [Solution] A means of collecting knowledge asset data from multiple departments within a group of companies, A means of cleaning up the collected data and converting it into an integrated database, A means of analyzing relationships using an integrated database and identifying potential collaborative relationships, A means of automatically generating business proposals based on identified collaborative relationships and creating feasible plans, A means of distributing proposals to relevant departments and tracking project progress, A system that includes this.

Description

Technical Field

[0001] The technology of this 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 a 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 many enterprise groups, there is a problem that each department has its own intellectual property and customer data individually, and it is difficult to effectively utilize them to maximize the company-wide synergy. Also, there is a lack of an efficient method for discovering potential cooperation relationships and quickly materializing new business opportunities. For this reason, there is a need to provide a process for quickly promoting cooperation between different departments, automatically generating business proposals, and implementing them into an execution plan.

Means for Solving the Problems

[0005] The present invention solves the aforementioned problems by providing means for collecting knowledge asset data from multiple departments within a group of companies, means for cleaning up the collected data and converting it into an integrated database, means for analyzing relationships using the integrated database and identifying potential collaborative relationships, means for automatically generating business proposals and creating actionable plans based on the identified collaborative relationships, and means for distributing the proposals to relevant departments and tracking project progress. Furthermore, by evaluating the execution status of projects and making suggestions for project improvements based on the evaluation results, the invention enables efficient execution and continuous improvement of operations within the group of companies.

[0006] A "group of companies" refers to a collection of multiple companies or departments that collaborate and function as a single organizational entity.

[0007] "Knowledge asset data" is a general term for know-how, experience, customer information, and other related information accumulated within a company or department.

[0008] "Cleanup" refers to the process of removing duplicates and inconsistencies from collected data to ensure data integrity.

[0009] An "integrated database" refers to a data system that centrally manages data collected from different departments and stores it in a format that allows for analysis.

[0010] "Relationship analysis" refers to the process of using integrated data to detect patterns and correlations between data points and to reveal potential cooperative relationships.

[0011] "Cooperative relationship" refers to a relationship between different departments that aims to enhance business opportunities and operational efficiency through collaboration.

[0012] A "business proposal" refers to a document that presents a specific business plan or implementation plan based on identified business opportunities and areas for improvement.

[0013] A "feasible plan" refers to a plan document that concretizes a business proposal and outlines a detailed schedule, resource allocation, and assigned personnel for its implementation.

[0014] "Progress tracking" refers to the process of monitoring how a project is progressing and making corrections or adjustments as needed.

[0015] "Evaluating the execution status" refers to an analysis that assesses the degree of project success based on progress and results, and identifies areas for future improvement. [Brief explanation of the drawing]

[0016] [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. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the language used in the following description will be explained.

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Also, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] 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.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception 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 reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] The 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.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention is a system that integrates knowledge asset data collected from various departments within a group of companies and uses that data to maximize the utilization of collaborative relationships. This system operates with a server at the center, performing various data processing tasks, with users and terminals providing support.

[0038] The server first automatically collects knowledge asset data from each department within the group of companies. This data includes customer information, operational know-how, and management strategy information. Since the collected data is often diverse and fragmented, the server cleans it up, removes duplicates, and converts it into a unified format. The cleaned-up data is then stored in an integrated database.

[0039] Next, the server analyzes the relationships between data using an integrated database. Generative AI technology is used to analyze patterns between data and discover potential collaborative relationships between departments. This makes it possible to uncover new business opportunities and ideas for improving the efficiency of existing operations.

[0040] For example, analyzing data from a communications services department and an energy management department might reveal a synergy in providing smart home services to customers of both departments. In this case, the server would create a business proposal based on this synergy.

[0041] The generated business proposals are created along with detailed implementation plans. These plans include project objectives, required resources, and schedules. These plans are distributed via a server to the terminals of the relevant departments, allowing users to review them and proceed with concrete project preparations.

[0042] Project progress is periodically reported to the server by users via their terminals. The server analyzes this data and can suggest improvements to the project as needed. This ensures that the project progresses according to plan and can be flexibly adjusted when necessary.

[0043] This system maximizes synergistic effects within the group of companies, enabling them to carry out operations quickly and efficiently.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server automatically requests knowledge asset data from each department within the group of companies and collects the corresponding datasets. The data is provided in various formats, such as customer information and business know-how.

[0047] Step 2:

[0048] The server cleans up the collected data, eliminating duplicates, correcting inconsistencies, and formatting it into a standard format. This enables efficient data entry into the integrated database.

[0049] Step 3:

[0050] The server stores the cleaned-up data in a unified database. The data is structured and ready for later analysis.

[0051] Step 4:

[0052] The server performs pattern detection using an integrated database. Generative AI is used to analyze correlations between data and discover potential cooperative relationships.

[0053] Step 5:

[0054] The server automatically generates business proposals based on the discovered collaborative relationships. These proposals include new business opportunities and suggestions for improving existing processes.

[0055] Step 6:

[0056] The server distributes the business proposal to the terminals of the relevant departments. Each department can then receive the proposal and begin preparing a concrete implementation plan.

[0057] Step 7:

[0058] Users evaluate the received proposals and develop detailed plans for project implementation. Server support is available as needed to facilitate project progress.

[0059] Step 8:

[0060] Users record project progress on their devices. Progress data is periodically sent to the server.

[0061] Step 9:

[0062] The server analyzes the collected progress data and evaluates the project. If necessary, it automatically generates improvement suggestions and notifies the relevant departments.

[0063] Step 10:

[0064] The terminal receives improvement suggestions from the server and adjusts the project accordingly. This ensures the project progresses according to plan, or according to the revised plan.

[0065] (Example 1)

[0066] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0067] There is a need for means to effectively utilize the vast and fragmented business information held by each department within a group of companies, and to discover new collaborative relationships, thereby enabling operational efficiency and the creation of new businesses. In particular, the challenge lies in building systems that automate these processes and can respond quickly and effectively.

[0068] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0069] In this invention, the server includes means for collecting business information, means for organizing the collected information and converting it into an integrated storage device, and means for analyzing the relationships between the information using the integrated storage device. This makes it possible to identify potential cooperative relationships between departments and automatically propose ways to improve operational efficiency and new business opportunities.

[0070] "Business information" refers to diverse and fragmented data collected from various departments within a group of companies, such as customer information, business know-how, and management strategy information.

[0071] "Preparation" refers to the process of removing duplicates from collected information and standardizing it by unifying the format.

[0072] An "integrated storage device" refers to a database system for centrally storing and managing organized information.

[0073] "Means for analyzing relationships" refers to technologies that use integrated memory devices to analyze patterns and relationships between business information and identify potential collaborative relationships.

[0074] "Cooperative relationships" refer to effective collaborations that can arise from interaction and cooperation between different departments.

[0075] "Automated generation" refers to the process of creating business proposals and plans using generative models without requiring human intervention.

[0076] An "operation screen" refers to a screen that provides an interface for users to approve or modify proposals.

[0077] This invention is a system that supports companies in improving operational efficiency and developing new businesses by integrating business information collected from various departments within a group of companies and discovering new collaborative relationships. At the heart of the system is a server with the functions of collecting, organizing, and analyzing data.

[0078] The server first automatically collects business information from each department using APIs and database connections. At this stage, scripts are executed using programming languages ​​such as Python and Java (registered trademark) to periodically retrieve data. The collected data includes customer information, business know-how, and management strategy information.

[0079] Next, the server organizes the collected information. This involves removing data duplication and arranging it into a consistent format using data cleansing tools and Python data analysis libraries (e.g., Pandas). The organized data is then stored in integrated storage using an SQL database management system (e.g., MySQL® or PostgreSQL).

[0080] Based on the information stored in the integrated storage device, the server uses a generative AI model to analyze the data. This allows for the analysis of relationships between data points and the identification of potential collaborative relationships between departments. This analysis is typically performed by running machine learning algorithms in Python scripts.

[0081] For example, analyzing data from the communications and energy management departments can generate proposals for smart home services. In this case, a prompt such as "Analyze how to discover synergistic effects using data from the communications and energy management departments" is input to the generated AI model.

[0082] This system allows the server to automatically generate business proposals and distribute them to terminals in the relevant departments. The terminals provide users with a screen to review the details of the proposals and approve or modify them. Users then proceed with project preparation based on the proposals and report project progress to the server from their terminals. The server analyzes the reported data and can generate project improvement suggestions as needed. This ensures efficient project progress and allows for flexible adjustments to align with the implementation plan.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The server collects business information from each department. Specifically, it uses APIs and database connections to extract customer information, business know-how, and management strategy information from various data sources. Input requires access information and queries from departments, and output is raw business information data.

[0086] Step 2:

[0087] The server processes the collected raw data. This involves removing duplicates and standardizing the format using Python data analysis libraries and data cleansing tools. The input is raw business information data, and the output is processed and standardized business information. Specifically, this includes detecting inconsistent entries and formatting them into a standard format.

[0088] Step 3:

[0089] The server stores the prepared data in integrated storage. A new table is created using the database management system, and the cleaned data is imported. The input is the prepared data, and the output is the set of information stored in the database. Specifically, this involves connecting to the database and adding data.

[0090] Step 4:

[0091] The server analyzes the relationships between information using integrated storage. It uses generative AI models to discover patterns and relationships between data. The input is integrated data, and the output is insights into potential collaborations between departments. Specifically, its operation includes applying machine learning algorithms to quantify these relationships.

[0092] Step 5:

[0093] The server automatically generates business proposals based on the analysis results. It utilizes a generation AI model to create business proposals based on new collaborative relationships. The input is the analysis results, and the output is a business proposal document including feasibility. Specifically, prompts are set, and the AI ​​generation process begins.

[0094] Step 6:

[0095] The terminal delivers business proposals received from the server to the user. It displays the details of the proposal through the user interface. The input is the business proposal document, and the output is visual information for the user. Specifically, this involves the process of displaying the proposal document on the terminal screen.

[0096] Step 7:

[0097] Users report project progress based on business proposals using a terminal. The server receives data on project progress and develops improvement suggestions as needed. The input is project progress data, and the output is improvement suggestions. Specifically, report data is entered from the terminal, and the server performs analysis and generates suggestions.

[0098] (Application Example 1)

[0099] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0100] The knowledge assets and data held by each department within a group of companies are diverse, making it difficult to integrate and utilize this data to maximize interdepartmental collaboration. In particular, there are challenges in efficiently arranging and optimizing the operation of information processing equipment within factories. To solve this problem, it is necessary to integrate data from each department and realize more efficient and autonomous business processes.

[0101] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0102] In this invention, the server includes means for collecting knowledge asset data from multiple departments within a group of companies, means for cleaning up the collected data and converting it into an integrated database, means for analyzing relationships using the integrated database and identifying potential collaborative relationships, and means for optimizing the placement and operation schedule of information processing devices based on feasible business proposals. This enables the discovery of collaborative relationships between departments and the maximization of the placement and operation efficiency of information processing devices within a factory.

[0103] A "group of companies" refers to an organization in which multiple related companies or business divisions come together to conduct business as a unified entity.

[0104] "Knowledge asset data" is a general term for valuable data held by a company, such as customer information, business know-how, and management strategy information.

[0105] "Cleanup" refers to the data processing steps that remove duplicates and noise from collected data and organize it into a unified format.

[0106] An "integrated database" is a database that centralizes and stores cleaned-up data from various departments in an accessible format.

[0107] "Means for analyzing relationships" refers to devices or software that use data analysis techniques to find relationships between data within an integrated database.

[0108] "Potential collaboration" refers to operational efficiency improvements and new business opportunities that can be made possible through inter-departmental cooperation that is not yet apparent.

[0109] A "business proposal" is a plan for specific business improvements or new projects that is automatically generated based on analyzed data.

[0110] An "information processing device" refers to hardware and software equipment used in factories and businesses for inputting, processing, and outputting data.

[0111] "Means for optimizing placement and operation schedules" refer to techniques and methods for planning and adjusting the placement and operating time of information processing devices in order to use them effectively.

[0112] To implement this invention, a server for collecting data from each department within a group of companies, user terminals for displaying the data, and a network environment for them to work together are required. The server collects knowledge asset data from each department within the group of companies and cleans up this data. Specifically, it uses the Python Pandas library to remove duplicate data and convert it into a neat format.

[0113] Subsequently, this cleaned-up data is stored in an integrated database, and the server analyzes the relationships between the data using a generative AI model based on TENSORFLOW® to discover potential collaborative relationships. Based on the discovered collaborative relationships, the server automatically generates business proposals and creates feasible plans. If necessary, the proposals can be further refined using machine learning models with Scikit-learn.

[0114] The user terminal distributes generated business proposals to employees, optimizing the placement and operation schedule of information processing devices. Users are expected to review the proposals on their terminals and implement them according to the instructions. This could improve efficiency within factories and companies, and potentially increase the success rate of new projects.

[0115] As a concrete example, one factory faces the challenge of coordinating different production lines. This system addresses this by analyzing production data from each department and proposing an optimal production line schedule, thereby resolving bottlenecks. An example of a prompt message used in this process is: "Based on the current production speed and assembly time, please propose a production schedule that maximizes the overall efficiency of the manufacturing line." This enables efficient production management.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The server collects knowledge asset data from each department within a group of companies. Inputs are departmental databases and CSV files, and output is a raw dataset. This dataset encompasses a wide range of information held by the companies. The server has the capability to automatically import this data using APIs and FTP.

[0119] Step 2:

[0120] The server cleans up the collected data. The input is the raw dataset collected in step 1, and the output is the cleaned, unified formatted dataset. It uses the Python Pandas library to remove duplicates and unify the formatting, including actions such as formatting dates and numerical units.

[0121] Step 3:

[0122] The server stores the cleaned dataset in a unified database. The input is a unified format dataset, and the output is storage in the database. This process uses an SQL database and also indexes the data. This provides a foundation for efficient subsequent processing.

[0123] Step 4:

[0124] The server performs data analysis using generative AI with an integrated database. The input is the integrated database, and the output is the results of the cooperative relationship analysis. TensorFlow is used to analyze the relationships between data and identify potential cooperative relationships. In this process, a model is built to detect data correlations and trends.

[0125] Step 5:

[0126] The server automatically generates business proposals and creates plans based on the analysis results. The input is the analysis results from step 4, and the output is the business proposal document. This process utilizes NLP technology to assemble insights obtained from the AI ​​model generated by Scikit-learn into natural language text.

[0127] Step 6:

[0128] The server distributes the generated business proposals to the terminals of the relevant departments. The input is the business proposal itself, and the output is the email or document distributed to the department. The server distributes information via a mail server or shared drive, and the terminals provide a user interface (UI) to facilitate document viewing.

[0129] Step 7:

[0130] The user terminal optimizes the placement and operation schedule of information processing equipment based on the proposal. Inputs are the proposal and on-site information, while output is the optimized schedule and layout plan. The user operates the terminal's UI and takes action to implement specific instructions.

[0131] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0132] This invention is a system that integrates and analyzes knowledge asset data collected from various departments within a group of companies, and combines an emotion engine with automatically generated business proposals. In this system, the server, terminals, and users work together to support the entire process from data collection to proposal generation, evaluation, and improvement.

[0133] First, the server collects knowledge asset data from each department within the group of companies, cleans it up, and aggregates it into an integrated database. Based on this data, the server performs analysis using generative AI to discover collaborative relationships between departments and new business opportunities. Subsequently, based on these analysis results, it automatically generates business proposals and detailed implementation plans.

[0134] Here, the newly integrated emotion engine recognizes the user's emotions and analyzes their response to the business proposal. Based on the results of the emotion engine, the server can dynamically adjust the proposal and plan. For example, if the user's response to the proposal is negative, the server re-evaluates the proposal and attempts to revise it to meet the user's expectations.

[0135] As a concrete example, in an evaluation meeting for a new business proposal, the server uses an emotion engine to grasp the participants' real-time emotions. The terminal visualizes the user's positive or negative emotions towards the proposal as graphs and recommendation lists, and the server adjusts the proposal based on this. This function aims to make proposals more acceptable to each department and project team.

[0136] As the project progresses, the server collects user feedback and continuously refines suggestions and plans as needed. The emotion engine monitors changes in user emotions, providing information to determine if the project is progressing properly. Throughout this entire process, the goal is to maximize synergies within the group of companies and improve operational efficiency.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The server sends data collection requests to each department within the group of companies. Once knowledge asset data has been collected from each department, the server receives this data and begins processing it.

[0140] Step 2:

[0141] The server cleans up the received data. It removes duplicate data, converts inconsistent data to a standard format, and organizes it into a unified database.

[0142] Step 3:

[0143] The server analyzes the integrated database. Using generative AI, it identifies relationships between data and pinpoints new collaborative relationships and business opportunities. Based on these results, it automatically generates business proposals.

[0144] Step 4:

[0145] The server activates the emotion engine and collects user emotion data in real time. Through the terminal, it recognizes emotions from the user's facial expressions and voice data and analyzes their response to the suggested content.

[0146] Step 5:

[0147] Based on the analysis of emotional data, the server dynamically adjusts business proposals. If the response to a proposal is negative, the plan is revised and changed to better align with the user's expectations.

[0148] Step 6:

[0149] The terminal presents the user with a revised business proposal and implementation plan. The user can review it and either approve the proposal or request additional revisions.

[0150] Step 7:

[0151] Users periodically record their progress and emotional responses using their devices during project implementation. This data is sent to a server and used to evaluate the project.

[0152] Step 8:

[0153] The server analyzes the received progress and sentiment data to evaluate the project. Based on the analysis, it generates suggestions for project improvement as needed and provides feedback to the project team.

[0154] Step 9:

[0155] The terminal receives feedback from the server and notifies the user. Based on the feedback, the user adjusts the project and takes action to achieve the best possible outcome.

[0156] (Example 2)

[0157] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0158] Conventional business proposal systems have problems in that they cannot adequately reflect users' feelings and opinions during the analysis of data collected from each department and in the proposal creation process. Furthermore, the generated proposals do not always meet the expectations of each user and may not be well-received. In addition, progress management during project execution and flexible revision of proposals are difficult.

[0159] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0160] In this invention, the server includes means for collecting information assets from multiple departments within a group of companies, means for formatting the collected information and converting it into integrated data storage, means for automatically generating business proposals and creating actionable plans based on identified collaborative relationships using a generative AI model, and means for analyzing the user's emotions towards the proposals using an emotion analysis engine and dynamically adjusting the proposal content. This enables the provision of business proposals that are easily accepted by each department and project team, as well as flexible project management that reflects the user's emotions in real time.

[0161] "Information assets" refer to the collective knowledge, data, and information accumulated within a group of companies. These are documents and digital content that are managed integrally and utilized to create value.

[0162] "Integrated data storage" refers to a database or data warehouse for organizing and integrating information assets collected from multiple departments, providing a foundation for consistent and efficient data analysis.

[0163] A "generative AI model" refers to artificial intelligence technology used to derive patterns and insights from data and generate new business proposals and solutions. These models utilize natural language processing and machine learning algorithms.

[0164] An "emotion analysis engine" is a technology that analyzes emotions and intentions from a user's text or voice, and adjusts the suggested content based on the results. It is an important tool for reflecting user feedback in real time.

[0165] A "business proposal" is a document that outlines plans and strategies for companies and departments to efficiently and effectively carry out their operations, based on the results of analysis by a generative AI model.

[0166] A description of embodiments for carrying out the present invention will be provided.

[0167] The server collects information assets from various departments within the corporate group. This information includes business reports, project progress data, and customer feedback. Remote access technologies and APIs are used for information collection. The collected data is formatted using data cleansing software (e.g., data cleansing tools), unnecessary information is removed, and then it is stored in integrated data storage.

[0168] Based on integrated data storage, the server performs data analysis using a generative AI model. This analysis uncovers potential collaborations between departments and new business opportunities. Specifically, it uses algorithms with natural language processing technology (e.g., the GPT-4® model) as the generative AI model to extract useful patterns from vast amounts of data. Based on the analysis results, the server automatically generates business proposals and actionable plans.

[0169] On the other hand, when a user receives a business proposal, the terminal uses an emotion analysis engine to analyze the user's emotions in real time. This emotion analysis engine (e.g., an emotion analysis tool) identifies emotions from the user's text and voice, and adjusts the proposal content based on the results. The server receives emotional feedback from the user, dynamically improves the proposal content, and creates a more acceptable proposal.

[0170] As a concrete example, when proposing a new marketing strategy, the generative AI model analyzes past success stories and uses the factors that contributed to those successes to construct a new strategy. Furthermore, it uses an emotion analysis engine to analyze the emotions users have towards the strategy and corrects any parts that do not meet expectations.

[0171] As an example of a prompt, you would input something like, "Please tell me how to use a generative AI model to analyze past success stories and discover new business opportunities in order to propose a new marketing strategy," and give instructions to the generative AI.

[0172] Through this series of processes, it is possible to realize a system that maximizes the use of information assets within a group of companies, enabling improved operational efficiency and the creation of new business opportunities.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The server collects information assets from various departments within the corporate group. Inputs include business reports and project progress data, which are received via APIs. The server analyzes this data, formats it using data cleansing tools to remove inconsistencies and duplicates, and stores it in integrated data storage. The output is a clean and consistent dataset.

[0176] Step 2:

[0177] The server analyzes data stored in integrated data storage using a generative AI model. The input is an organized dataset. The server sends prompts to the generative AI model (e.g., GPT-4) to discover data relationships and patterns. This data analysis reveals potential inter-departmental collaborations and business opportunities. The output is a list of discovered patterns and insights.

[0178] Step 3:

[0179] The server automatically generates business proposals and actionable plans based on the analysis results. The input for this stage is the patterns and insights obtained in Step 2. The server uses the generated AI model to concretize the proposals and formalize them as feasible strategies. The output consists of a business proposal document and an action plan document.

[0180] Step 4:

[0181] The terminal collects user responses to generated business proposals. Input includes user voice and text, which are fed into an emotion analysis engine. The terminal analyzes the user's text and voice input and sends the emotion data to the server. The output is the user's emotional state.

[0182] Step 5:

[0183] The server dynamically adjusts the business proposal based on the sentiment analysis results. Using the sentiment data from Step 4 as input, it analyzes which parts were received favorably or negatively by the user. The server re-examines the proposal and modifies it as needed. The output is a business proposal optimized for the user.

[0184] Step 6:

[0185] Users evaluate the final proposal and provide feedback via their terminal. They receive the refined business proposal as input and send their opinions and expectations as feedback to the server. The server receives this feedback and uses it to further improve the project progress and the proposal. The output includes user evaluations and suggestions for improvement to the proposal.

[0186] (Application Example 2)

[0187] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0188] In a corporate environment, a key challenge is effectively utilizing large amounts of knowledge data obtained from multiple departments to efficiently and quickly generate business proposals. Furthermore, dynamic adjustments to these proposals, taking user sentiment into account, are necessary to ensure they are readily accepted by relevant departments and customers. Ultimately, this is required to optimize corporate resources and improve operational efficiency.

[0189] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0190] In this invention, the server includes means for collecting knowledge asset data from multiple departments within a group of companies, means for cleaning up the collected data and converting it into an integrated database, means for analyzing relationships using the integrated database and identifying potential collaborative relationships, means for automatically generating business proposals and creating feasible plans based on the identified collaborative relationships, means for recognizing users' emotions towards the proposals and dynamically adjusting the proposal content based on those emotions, and means for distributing the adjusted proposals to relevant departments, tracking project progress, and improving the proposals based on feedback. This maximizes knowledge sharing and synergy effects among departments and enables business proposals tailored to individual user needs.

[0191] A "group of companies" is a group of companies that collaborate as an organization, sharing their resources and information to carry out their activities.

[0192] "Knowledge asset data" refers to a collection of data with intellectual value, such as documents, information, and know-how, generated within a company.

[0193] "Cleanup" is the process of removing noise and redundant information from collected data and preparing it in a format that can be analyzed.

[0194] An "integrated database" is a database that centrally manages information collected from multiple data sources and is built to allow easy access and analysis.

[0195] "Relationship analysis" is the process of finding relationships and patterns between data and revealing potential meanings and dependencies.

[0196] A "business proposal" is a proposal that presents the optimal solution or action plan for a specific business challenge.

[0197] "Emotion recognition" is a technology that determines a user's emotional state from their facial expressions, voice, and actions, and extracts that information.

[0198] "Dynamic adjustment" refers to the process of continuously modifying and optimizing pre-determined plans and proposals based on real-time situations and new information.

[0199] "Improving based on feedback" refers to the act of improving the system's functions and suggestions by reflecting actual operational results and opinions from users.

[0200] In an embodiment of this invention, the server collects knowledge asset data from each department within a group of companies. The collected data undergoes a cleanup process and is converted into an integrated database. Using this database, the server utilizes a generative AI model to analyze the relationships between the data. The purpose of the analysis is to identify potential collaborative relationships and discover new business opportunities. Based on the results, business proposals are automatically generated and concrete implementation plans are formulated.

[0201] The server also utilizes data provided by the terminal to recognize the user's emotions towards the proposal. Emotion recognition uses an emotion engine that analyzes the user's voice and facial expressions. The emotion engine determines the emotional state in real time and provides feedback to the server. Based on this feedback, the server dynamically adjusts the proposal to create a better one. For example, during an evaluation meeting, the server analyzes participants' reactions through the emotion engine and immediately modifies the proposal if it is being received negatively.

[0202] The server distributes the revised proposal to terminals, allowing relevant departments to approve or revise it on their own devices. This process is expected to improve the acceptability of proposals and promote more synergistic progress in projects within the group of companies.

[0203] As a concrete example, let's consider generating suggestions when a customer is relaxing. The generating AI model can use prompts like the following: "Please suggest products that are suitable for a customer who is relaxing. You can purchase the latest relaxation products at a 10% discount."

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The server collects knowledge asset data from each department within a group of companies. The input is raw data provided by each department, and the output is a collection of the collected data. This data includes documents, numerical data, project reports, etc. The server stores this data in a database and prepares it for the next step.

[0207] Step 2:

[0208] The server cleans up the collected data and builds an integrated database. The input is a collection of raw data, which includes unnecessary and duplicate data. The server uses cleansing tools to remove noise and processes the data to ensure data integrity. The output is an integrated dataset suitable for analysis.

[0209] Step 3:

[0210] The server analyzes relationships using an integrated database. The input is a cleaned-up dataset, and the output is the potential collaborations and business opportunities discovered. The server utilizes generative AI models to perform pattern recognition and relationship analysis to explore new business possibilities.

[0211] Step 4:

[0212] The server automatically generates business proposals based on the analysis results. The input is the discovered collaborative relationships and business opportunities, and the output is the automatically generated business proposals and implementation plans. The server inputs prompt messages into the AI ​​model to create a detailed proposal document and execution plan.

[0213] Step 5:

[0214] The server interacts with the terminal to recognize the user's emotions in response to a suggestion. Input is the user's voice and facial expressions, and output is analyzed emotion data. The terminal uses an emotion engine to analyze emotions in real time and sends the results to the server.

[0215] Step 6:

[0216] The server dynamically adjusts the proposal based on sentiment data. The input is sentiment data, and the output is an adjusted proposal. The server reviews the proposal, makes improvements to meet user expectations, and enhances its acceptability.

[0217] Step 7:

[0218] The server delivers the revised proposal to the terminal. The input is the revised proposal document, and the output is the delivery status to the relevant department head. The department head can then review the proposal on their terminal and use the interface to approve or revise it as needed.

[0219] 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.

[0220] Data generation model 58 is a 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0221] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] 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.

[0225] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0226] 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.

[0227] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0228] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0229] 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.

[0230] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0231] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0232] The 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.

[0233] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0234] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0235] This invention is a system that integrates knowledge asset data collected from various departments within a group of companies and uses that data to maximize the utilization of collaborative relationships. This system operates with a server at the center, performing various data processing tasks, with users and terminals providing support.

[0236] The server first automatically collects knowledge asset data from each department within the group of companies. This data includes customer information, operational know-how, and management strategy information. Since the collected data is often diverse and fragmented, the server cleans it up, removes duplicates, and converts it into a unified format. The cleaned-up data is then stored in an integrated database.

[0237] Next, the server analyzes the relationships between data using an integrated database. Generative AI technology is used to analyze patterns between data and discover potential collaborative relationships between departments. This makes it possible to uncover new business opportunities and ideas for improving the efficiency of existing operations.

[0238] For example, analyzing data from a communications services department and an energy management department might reveal a synergy in providing smart home services to customers of both departments. In this case, the server would create a business proposal based on this synergy.

[0239] The generated business proposals are created along with detailed implementation plans. These plans include project objectives, required resources, and schedules. These plans are distributed via a server to the terminals of the relevant departments, allowing users to review them and proceed with concrete project preparations.

[0240] Project progress is periodically reported to the server by users via their terminals. The server analyzes this data and can suggest improvements to the project as needed. This ensures that the project progresses according to plan and can be flexibly adjusted when necessary.

[0241] This system maximizes synergistic effects within the group of companies, enabling them to carry out operations quickly and efficiently.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The server automatically requests knowledge asset data from each department within the group of companies and collects the corresponding datasets. The data is provided in various formats, such as customer information and business know-how.

[0245] Step 2:

[0246] The server cleans up the collected data, eliminating duplicates, correcting inconsistencies, and formatting it into a standard format. This enables efficient data entry into the integrated database.

[0247] Step 3:

[0248] The server stores the cleaned-up data in a unified database. The data is structured and ready for later analysis.

[0249] Step 4:

[0250] The server performs pattern detection using an integrated database. Generative AI is used to analyze correlations between data and discover potential cooperative relationships.

[0251] Step 5:

[0252] The server automatically generates business proposals based on the discovered collaborative relationships. These proposals include new business opportunities and suggestions for improving existing processes.

[0253] Step 6:

[0254] The server distributes the business proposal to the terminals of the relevant departments. Each department can then receive the proposal and begin preparing a concrete implementation plan.

[0255] Step 7:

[0256] Users evaluate the received proposals and develop detailed plans for project implementation. Server support is available as needed to facilitate project progress.

[0257] Step 8:

[0258] Users record project progress on their devices. Progress data is periodically sent to the server.

[0259] Step 9:

[0260] The server analyzes the collected progress data and evaluates the project. If necessary, it automatically generates improvement suggestions and notifies the relevant departments.

[0261] Step 10:

[0262] The terminal receives improvement suggestions from the server and adjusts the project accordingly. This ensures the project progresses according to plan, or according to the revised plan.

[0263] (Example 1)

[0264] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0265] There is a need for means to effectively utilize the vast and fragmented business information held by each department within a group of companies, and to discover new collaborative relationships, thereby enabling operational efficiency and the creation of new businesses. In particular, the challenge lies in building systems that automate these processes and can respond quickly and effectively.

[0266] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0267] In this invention, the server includes means for collecting business information, means for organizing the collected information and converting it into an integrated storage device, and means for analyzing the relationships between the information using the integrated storage device. This makes it possible to identify potential cooperative relationships between departments and automatically propose ways to improve operational efficiency and new business opportunities.

[0268] "Business information" refers to diverse and fragmented data collected from various departments within a group of companies, such as customer information, business know-how, and management strategy information.

[0269] "Preparation" refers to the process of removing duplicates from collected information and standardizing it by unifying the format.

[0270] An "integrated storage device" refers to a database system for centrally storing and managing organized information.

[0271] "Means for analyzing relationships" refers to technologies that use integrated memory devices to analyze patterns and relationships between business information and identify potential collaborative relationships.

[0272] "Cooperative relationships" refer to effective collaborations that can arise from interaction and cooperation between different departments.

[0273] "Automated generation" refers to the process of creating business proposals and plans using generative models without requiring human intervention.

[0274] An "operation screen" refers to a screen that provides an interface for users to approve or modify proposals.

[0275] This invention is a system that supports companies in improving operational efficiency and developing new businesses by integrating business information collected from various departments within a group of companies and discovering new collaborative relationships. At the heart of the system is a server with the functions of collecting, organizing, and analyzing data.

[0276] The server first automatically collects business information from each department using APIs and database connections. At this stage, scripts are executed using programming languages ​​such as Python and Java to periodically retrieve data. The collected data includes customer information, business know-how, and management strategy information.

[0277] Next, the server organizes the collected information. This involves removing duplicate data and arranging it into a consistent format using data cleansing tools and Python data analysis libraries (e.g., Pandas). The organized data is then stored in integrated storage using a SQL database management system (e.g., MySQL or PostgreSQL).

[0278] Based on the information stored in the integrated storage device, the server uses a generative AI model to analyze the data. This allows for the analysis of relationships between data points and the identification of potential collaborative relationships between departments. This analysis is typically performed by running machine learning algorithms in Python scripts.

[0279] For example, analyzing data from the communications and energy management departments can generate proposals for smart home services. In this case, a prompt such as "Analyze how to discover synergistic effects using data from the communications and energy management departments" is input to the generated AI model.

[0280] This system allows the server to automatically generate business proposals and distribute them to terminals in the relevant departments. The terminals provide users with a screen to review the details of the proposals and approve or modify them. Users then proceed with project preparation based on the proposals and report project progress to the server from their terminals. The server analyzes the reported data and can generate project improvement suggestions as needed. This ensures efficient project progress and allows for flexible adjustments to align with the implementation plan.

[0281] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0282] Step 1:

[0283] The server collects the business information of each department. Specifically, it extracts customer information, business know-how, and business strategy information from various data sources using APIs and database connections. Access information and queries from the department are required as input, and raw business information data can be obtained as output.

[0284] Step 2:

[0285] The server cleans the collected raw data. This is a process of removing duplicates and unifying formats using Python's data analysis libraries and data cleansing tools. The input is raw business information data, and the output is cleansed and standardized business information. Specific operations include detecting inconsistent entries and formatting them into a standard form.

[0286] Step 3:

[0287] The server stores the cleansed data in an integrated storage device. A new table is created using a database management system, and the cleansed data is imported. The input is the cleansed data, and the output is a series of information stored in the database. Specific operations include connecting to the database and adding data.

[0288] Step 4:

[0289] The server analyzes the relevance of information using the integrated storage device. A generative AI model is used to discover patterns and relationships between data. The input is the integrated data, and the output is insights regarding potential cooperation relationships between departments. Specific operations include applying machine learning algorithms to quantify the relevance.

[0290] Step 5:

[0291] The server automatically generates business proposals based on the analysis results. It utilizes a generation AI model to create business proposals based on new collaborative relationships. The input is the analysis results, and the output is a business proposal document including feasibility. Specifically, prompts are set, and the AI ​​generation process begins.

[0292] Step 6:

[0293] The terminal delivers business proposals received from the server to the user. It displays the details of the proposal through the user interface. The input is the business proposal document, and the output is visual information for the user. Specifically, this involves the process of displaying the proposal document on the terminal screen.

[0294] Step 7:

[0295] Users report project progress based on business proposals using a terminal. The server receives data on project progress and develops improvement suggestions as needed. The input is project progress data, and the output is improvement suggestions. Specifically, report data is entered from the terminal, and the server performs analysis and generates suggestions.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] The knowledge assets and data held by each department within a group of companies are diverse, making it difficult to integrate and utilize this data to maximize interdepartmental collaboration. In particular, there are challenges in efficiently arranging and optimizing the operation of information processing equipment within factories. To solve this problem, it is necessary to integrate data from each department and realize more efficient and autonomous business processes.

[0299] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0300] In this invention, the server includes means for collecting intellectual property data from a large number of departments within a group of enterprises, means for cleaning up the collected data and converting it into an integrated database, means for analyzing the relevance using the integrated database and identifying potential cooperation relationships, and means for optimizing the arrangement and operation schedule of information processing devices based on feasible business proposals. Thereby, it becomes possible to discover cooperation relationships among departments and maximize the arrangement and operation efficiency of information processing devices within the factory.

[0301] A "group of enterprises" refers to an organizational entity in which a plurality of related enterprises or business departments gather and conduct business as a single entity.

[0302] "Intellectual property data" is a general term for valuable data such as customer information, business know-how, and business strategy information held by an enterprise.

[0303] "Cleaning up" refers to a data processing process of removing duplicates and noise from the collected data and arranging it in a unified format.

[0304] An "integrated database" refers to a database that unifies the cleaned-up data from various departments and stores it in a usable form.

[0305] "Means for analyzing relevance" refers to a device or software that uses data analysis techniques to find the relationships between data in the integrated database.

[0306] "Potential cooperation relationship" refers to business efficiency improvement and new business opportunities that are made possible by cooperation between departments that has not yet surfaced.

[0307] A "business proposal" refers to a plan for specific business improvement or a new project automatically generated based on the analyzed data.

[0308] An "information processing device" refers to hardware and software equipment used in factories and businesses for inputting, processing, and outputting data.

[0309] "Means for optimizing placement and operation schedules" refer to techniques and methods for planning and adjusting the placement and operating time of information processing devices in order to use them effectively.

[0310] To implement this invention, a server for collecting data from each department within a group of companies, user terminals for displaying the data, and a network environment for them to work together are required. The server collects knowledge asset data from each department within the group of companies and cleans up this data. Specifically, it uses the Python Pandas library to remove duplicate data and convert it into a neat format.

[0311] Subsequently, this cleaned-up data is stored in an integrated database, and the server uses a generative AI model with TensorFlow to analyze the relationships between the data and discover potential collaborative relationships. Based on the discovered collaborative relationships, the server automatically generates business proposals and creates feasible plans. If necessary, the proposals can be further refined using machine learning models with Scikit-learn.

[0312] The user terminal distributes generated business proposals to employees, optimizing the placement and operation schedule of information processing devices. Users are expected to review the proposals on their terminals and implement them according to the instructions. This could improve efficiency within factories and companies, and potentially increase the success rate of new projects.

[0313] As a concrete example, one factory faces the challenge of coordinating different production lines. This system addresses this by analyzing production data from each department and proposing an optimal production line schedule, thereby resolving bottlenecks. An example of a prompt message used in this process is: "Based on the current production speed and assembly time, please propose a production schedule that maximizes the overall efficiency of the manufacturing line." This enables efficient production management.

[0314] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0315] Step 1:

[0316] The server collects knowledge asset data from each department within a group of companies. Inputs are departmental databases and CSV files, and output is a raw dataset. This dataset encompasses a wide range of information held by the companies. The server has the capability to automatically import this data using APIs and FTP.

[0317] Step 2:

[0318] The server cleans up the collected data. The input is the raw dataset collected in step 1, and the output is the cleaned, unified formatted dataset. It uses the Python Pandas library to remove duplicates and unify the formatting, including actions such as formatting dates and numerical units.

[0319] Step 3:

[0320] The server stores the cleaned dataset in a unified database. The input is a unified format dataset, and the output is storage in the database. This process uses an SQL database and also indexes the data. This provides a foundation for efficient subsequent processing.

[0321] Step 4:

[0322] The server performs data analysis using generative AI with an integrated database. The input is the integrated database, and the output is the results of the cooperative relationship analysis. TensorFlow is used to analyze the relationships between data and identify potential cooperative relationships. In this process, a model is built to detect data correlations and trends.

[0323] Step 5:

[0324] The server automatically generates business proposals and creates plans based on the analysis results. The input is the analysis results from step 4, and the output is the business proposal document. This process utilizes NLP technology to assemble insights obtained from the AI ​​model generated by Scikit-learn into natural language text.

[0325] Step 6:

[0326] The server distributes the generated business proposals to the terminals of the relevant departments. The input is the business proposal itself, and the output is the email or document distributed to the department. The server distributes information via a mail server or shared drive, and the terminals provide a user interface (UI) to facilitate document viewing.

[0327] Step 7:

[0328] The user terminal optimizes the placement and operation schedule of information processing equipment based on the proposal. Inputs are the proposal and on-site information, while output is the optimized schedule and layout plan. The user operates the terminal's UI and takes action to implement specific instructions.

[0329] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0330] This invention is a system that integrates and analyzes knowledge asset data collected from various departments within a group of companies, and combines an emotion engine with automatically generated business proposals. In this system, the server, terminals, and users work together to support the entire process from data collection to proposal generation, evaluation, and improvement.

[0331] First, the server collects knowledge asset data from each department within the group of companies, cleans it up, and aggregates it into an integrated database. Based on this data, the server performs analysis using generative AI to discover collaborative relationships between departments and new business opportunities. Subsequently, based on these analysis results, it automatically generates business proposals and detailed implementation plans.

[0332] Here, the newly integrated emotion engine recognizes the user's emotions and analyzes their response to the business proposal. Based on the results of the emotion engine, the server can dynamically adjust the proposal and plan. For example, if the user's response to the proposal is negative, the server re-evaluates the proposal and attempts to revise it to meet the user's expectations.

[0333] As a concrete example, in an evaluation meeting for a new business proposal, the server uses an emotion engine to grasp the participants' real-time emotions. The terminal visualizes the user's positive or negative emotions towards the proposal as graphs and recommendation lists, and the server adjusts the proposal based on this. This function aims to make proposals more acceptable to each department and project team.

[0334] As the project progresses, the server collects user feedback and continuously refines suggestions and plans as needed. The emotion engine monitors changes in user emotions, providing information to determine if the project is progressing properly. Throughout this entire process, the goal is to maximize synergies within the group of companies and improve operational efficiency.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The server sends data collection requests to each department within the group of companies. Once knowledge asset data has been collected from each department, the server receives this data and begins processing it.

[0338] Step 2:

[0339] The server cleans up the received data. It removes duplicate data, converts inconsistent data to a standard format, and organizes it into a unified database.

[0340] Step 3:

[0341] The server analyzes the integrated database. Using generative AI, it identifies relationships between data and pinpoints new collaborative relationships and business opportunities. Based on these results, it automatically generates business proposals.

[0342] Step 4:

[0343] The server activates the emotion engine and collects user emotion data in real time. Through the terminal, it recognizes emotions from the user's facial expressions and voice data and analyzes their response to the suggested content.

[0344] Step 5:

[0345] Based on the analysis of emotional data, the server dynamically adjusts business proposals. If the response to a proposal is negative, the plan is revised and changed to better align with the user's expectations.

[0346] Step 6:

[0347] The terminal presents the user with a revised business proposal and implementation plan. The user can review it and either approve the proposal or request additional revisions.

[0348] Step 7:

[0349] Users periodically record their progress and emotional responses using their devices during project implementation. This data is sent to a server and used to evaluate the project.

[0350] Step 8:

[0351] The server analyzes the received progress and sentiment data to evaluate the project. Based on the analysis, it generates suggestions for project improvement as needed and provides feedback to the project team.

[0352] Step 9:

[0353] The terminal receives feedback from the server and notifies the user. Based on the feedback, the user adjusts the project and takes action to achieve the best possible outcome.

[0354] (Example 2)

[0355] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0356] Conventional business proposal systems have problems in that they cannot adequately reflect users' feelings and opinions during the analysis of data collected from each department and in the proposal creation process. Furthermore, the generated proposals do not always meet the expectations of each user and may not be well-received. In addition, progress management during project execution and flexible revision of proposals are difficult.

[0357] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0358] In this invention, the server includes means for collecting information assets from multiple departments within a group of companies, means for formatting the collected information and converting it into integrated data storage, means for automatically generating business proposals and creating actionable plans based on identified collaborative relationships using a generative AI model, and means for analyzing the user's emotions towards the proposals using an emotion analysis engine and dynamically adjusting the proposal content. This enables the provision of business proposals that are easily accepted by each department and project team, as well as flexible project management that reflects the user's emotions in real time.

[0359] "Information assets" refer to the collective knowledge, data, and information accumulated within a group of companies. These are documents and digital content that are managed integrally and utilized to create value.

[0360] "Integrated data storage" refers to a database or data warehouse for organizing and integrating information assets collected from multiple departments, providing a foundation for consistent and efficient data analysis.

[0361] A "generative AI model" refers to artificial intelligence technology used to derive patterns and insights from data and generate new business proposals and solutions. These models utilize natural language processing and machine learning algorithms.

[0362] An "emotion analysis engine" is a technology that analyzes emotions and intentions from a user's text or voice, and adjusts the suggested content based on the results. It is an important tool for reflecting user feedback in real time.

[0363] A "business proposal" is a document that outlines plans and strategies for companies and departments to efficiently and effectively carry out their operations, based on the results of analysis by a generative AI model.

[0364] A description of embodiments for carrying out the present invention will be provided.

[0365] The server collects information assets from various departments within the corporate group. This information includes business reports, project progress data, and customer feedback. Remote access technologies and APIs are used for information collection. The collected data is formatted using data cleansing software (e.g., data cleansing tools), unnecessary information is removed, and then it is stored in integrated data storage.

[0366] Based on integrated data storage, the server performs data analysis using a generative AI model. This analysis uncovers potential collaborations between departments and new business opportunities. Specifically, it uses algorithms with natural language processing technology (e.g., the GPT-4 model) as the generative AI model to extract useful patterns from vast amounts of data. Based on the analysis results, the server automatically generates business proposals and actionable plans.

[0367] On the other hand, when a user receives a business proposal, the terminal uses an emotion analysis engine to analyze the user's emotions in real time. This emotion analysis engine (e.g., an emotion analysis tool) identifies emotions from the user's text and voice, and adjusts the proposal content based on the results. The server receives emotional feedback from the user, dynamically improves the proposal content, and creates a more acceptable proposal.

[0368] As a concrete example, when proposing a new marketing strategy, the generative AI model analyzes past success stories and uses the factors that contributed to those successes to construct a new strategy. Furthermore, it uses an emotion analysis engine to analyze the emotions users have towards the strategy and corrects any parts that do not meet expectations.

[0369] As an example of a prompt, you would input something like, "Please tell me how to use a generative AI model to analyze past success stories and discover new business opportunities in order to propose a new marketing strategy," and give instructions to the generative AI.

[0370] Through this series of processes, it is possible to realize a system that maximizes the use of information assets within a group of companies, enabling improved operational efficiency and the creation of new business opportunities.

[0371] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0372] Step 1:

[0373] The server collects information assets from various departments within the corporate group. Inputs include business reports and project progress data, which are received via APIs. The server analyzes this data, formats it using data cleansing tools to remove inconsistencies and duplicates, and stores it in integrated data storage. The output is a clean and consistent dataset.

[0374] Step 2:

[0375] The server analyzes data stored in integrated data storage using a generative AI model. The input is an organized dataset. The server sends prompts to the generative AI model (e.g., GPT-4) to discover data relationships and patterns. This data analysis reveals potential inter-departmental collaborations and business opportunities. The output is a list of discovered patterns and insights.

[0376] Step 3:

[0377] The server automatically generates business proposals and actionable plans based on the analysis results. The input for this stage is the patterns and insights obtained in Step 2. The server uses the generated AI model to concretize the proposals and formalize them as feasible strategies. The output consists of a business proposal document and an action plan document.

[0378] Step 4:

[0379] The terminal collects user responses to generated business proposals. Input includes user voice and text, which are fed into an emotion analysis engine. The terminal analyzes the user's text and voice input and sends the emotion data to the server. The output is the user's emotional state.

[0380] Step 5:

[0381] The server dynamically adjusts the business proposal based on the sentiment analysis results. Using the sentiment data from Step 4 as input, it analyzes which parts were received favorably or negatively by the user. The server re-examines the proposal and modifies it as needed. The output is a business proposal optimized for the user.

[0382] Step 6:

[0383] Users evaluate the final proposal and provide feedback via their terminal. They receive the refined business proposal as input and send their opinions and expectations as feedback to the server. The server receives this feedback and uses it to further improve the project progress and the proposal. The output includes user evaluations and suggestions for improvement to the proposal.

[0384] (Application Example 2)

[0385] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0386] In a corporate environment, a key challenge is effectively utilizing large amounts of knowledge data obtained from multiple departments to efficiently and quickly generate business proposals. Furthermore, dynamic adjustments to these proposals, taking user sentiment into account, are necessary to ensure they are readily accepted by relevant departments and customers. Ultimately, this is required to optimize corporate resources and improve operational efficiency.

[0387] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0388] In this invention, the server includes means for collecting knowledge asset data from multiple departments within a group of companies, means for cleaning up the collected data and converting it into an integrated database, means for analyzing relationships using the integrated database and identifying potential collaborative relationships, means for automatically generating business proposals and creating feasible plans based on the identified collaborative relationships, means for recognizing users' emotions towards the proposals and dynamically adjusting the proposal content based on those emotions, and means for distributing the adjusted proposals to relevant departments, tracking project progress, and improving the proposals based on feedback. This maximizes knowledge sharing and synergy effects among departments and enables business proposals tailored to individual user needs.

[0389] A "group of companies" is a group of companies that collaborate as an organization, sharing their resources and information to carry out their activities.

[0390] "Knowledge asset data" refers to a collection of data with intellectual value, such as documents, information, and know-how, generated within a company.

[0391] "Cleanup" is the process of removing noise and redundant information from collected data and preparing it in a format that can be analyzed.

[0392] An "integrated database" is a database that centrally manages information collected from multiple data sources and is built to allow easy access and analysis.

[0393] "Relationship analysis" is the process of finding relationships and patterns between data and revealing potential meanings and dependencies.

[0394] A "business proposal" is a proposal that presents the optimal solution or action plan for a specific business challenge.

[0395] "Emotion recognition" is a technology that determines a user's emotional state from their facial expressions, voice, and actions, and extracts that information.

[0396] "Dynamic adjustment" refers to the process of continuously modifying and optimizing pre-determined plans and proposals based on real-time situations and new information.

[0397] "Improving based on feedback" refers to the act of improving the system's functions and suggestions by reflecting actual operational results and opinions from users.

[0398] In an embodiment of this invention, the server collects knowledge asset data from each department within a group of companies. The collected data undergoes a cleanup process and is converted into an integrated database. Using this database, the server utilizes a generative AI model to analyze the relationships between the data. The purpose of the analysis is to identify potential collaborative relationships and discover new business opportunities. Based on the results, business proposals are automatically generated and concrete implementation plans are formulated.

[0399] The server also utilizes data provided by the terminal to recognize the user's emotions towards the proposal. Emotion recognition uses an emotion engine that analyzes the user's voice and facial expressions. The emotion engine determines the emotional state in real time and provides feedback to the server. Based on this feedback, the server dynamically adjusts the proposal to create a better one. For example, during an evaluation meeting, the server analyzes participants' reactions through the emotion engine and immediately modifies the proposal if it is being received negatively.

[0400] The server distributes the revised proposal to terminals, allowing relevant departments to approve or revise it on their own devices. This process is expected to improve the acceptability of proposals and promote more synergistic progress in projects within the group of companies.

[0401] As a concrete example, let's consider generating suggestions when a customer is relaxing. The generating AI model can use prompts like the following: "Please suggest products that are suitable for a customer who is relaxing. You can purchase the latest relaxation products at a 10% discount."

[0402] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0403] Step 1:

[0404] The server collects knowledge asset data from each department within a group of companies. The input is raw data provided by each department, and the output is a collection of the collected data. This data includes documents, numerical data, project reports, etc. The server stores this data in a database and prepares it for the next step.

[0405] Step 2:

[0406] The server cleans up the collected data and builds an integrated database. The input is a collection of raw data, which includes unnecessary and duplicate data. The server uses cleansing tools to remove noise and processes the data to ensure data integrity. The output is an integrated dataset suitable for analysis.

[0407] Step 3:

[0408] The server analyzes relationships using an integrated database. The input is a cleaned-up dataset, and the output is the potential collaborations and business opportunities discovered. The server utilizes generative AI models to perform pattern recognition and relationship analysis to explore new business possibilities.

[0409] Step 4:

[0410] The server automatically generates business proposals based on the analysis results. The input is the discovered collaborative relationships and business opportunities, and the output is the automatically generated business proposals and implementation plans. The server inputs prompt messages into the AI ​​model to create a detailed proposal document and execution plan.

[0411] Step 5:

[0412] The server interacts with the terminal to recognize the user's emotions in response to a suggestion. Input is the user's voice and facial expressions, and output is analyzed emotion data. The terminal uses an emotion engine to analyze emotions in real time and sends the results to the server.

[0413] Step 6:

[0414] The server dynamically adjusts the proposal based on sentiment data. The input is sentiment data, and the output is an adjusted proposal. The server reviews the proposal, makes improvements to meet user expectations, and enhances its acceptability.

[0415] Step 7:

[0416] The server delivers the revised proposal to the terminal. The input is the revised proposal document, and the output is the delivery status to the relevant department head. The department head can then review the proposal on their terminal and use the interface to approve or revise it as needed.

[0417] 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.

[0418] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0419] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0420] [Third Embodiment]

[0421] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0422] 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.

[0423] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0424] 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.

[0425] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0426] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0427] 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.

[0428] 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.

[0429] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0430] The 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.

[0431] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0432] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0433] This invention is a system that integrates knowledge asset data collected from various departments within a group of companies and uses that data to maximize the utilization of collaborative relationships. This system operates with a server at the center, performing various data processing tasks, with users and terminals providing support.

[0434] The server first automatically collects knowledge asset data from each department within the group of companies. This data includes customer information, operational know-how, and management strategy information. Since the collected data is often diverse and fragmented, the server cleans it up, removes duplicates, and converts it into a unified format. The cleaned-up data is then stored in an integrated database.

[0435] Next, the server analyzes the relationships between data using an integrated database. Generative AI technology is used to analyze patterns between data and discover potential collaborative relationships between departments. This makes it possible to uncover new business opportunities and ideas for improving the efficiency of existing operations.

[0436] For example, analyzing data from a communications services department and an energy management department might reveal a synergy in providing smart home services to customers of both departments. In this case, the server would create a business proposal based on this synergy.

[0437] The generated business proposals are created along with detailed implementation plans. These plans include project objectives, required resources, and schedules. These plans are distributed via a server to the terminals of the relevant departments, allowing users to review them and proceed with concrete project preparations.

[0438] Project progress is periodically reported to the server by users via their terminals. The server analyzes this data and can suggest improvements to the project as needed. This ensures that the project progresses according to plan and can be flexibly adjusted when necessary.

[0439] This system maximizes synergistic effects within the group of companies, enabling them to carry out operations quickly and efficiently.

[0440] The following describes the processing flow.

[0441] Step 1:

[0442] The server automatically requests knowledge asset data from each department within the group of companies and collects the corresponding datasets. The data is provided in various formats, such as customer information and business know-how.

[0443] Step 2:

[0444] The server cleans up the collected data, eliminating duplicates, correcting inconsistencies, and formatting it into a standard format. This enables efficient data entry into the integrated database.

[0445] Step 3:

[0446] The server stores the cleaned-up data in a unified database. The data is structured and ready for later analysis.

[0447] Step 4:

[0448] The server performs pattern detection using an integrated database. Generative AI is used to analyze correlations between data and discover potential cooperative relationships.

[0449] Step 5:

[0450] The server automatically generates business proposals based on the discovered collaborative relationships. These proposals include new business opportunities and suggestions for improving existing processes.

[0451] Step 6:

[0452] The server distributes the business proposal to the terminals of the relevant departments. Each department can then receive the proposal and begin preparing a concrete implementation plan.

[0453] Step 7:

[0454] Users evaluate the received proposals and develop detailed plans for project implementation. Server support is available as needed to facilitate project progress.

[0455] Step 8:

[0456] Users record project progress on their devices. Progress data is periodically sent to the server.

[0457] Step 9:

[0458] The server analyzes the collected progress data and evaluates the project. If necessary, it automatically generates improvement suggestions and notifies the relevant departments.

[0459] Step 10:

[0460] The terminal receives improvement suggestions from the server and adjusts the project accordingly. This ensures the project progresses according to plan, or according to the revised plan.

[0461] (Example 1)

[0462] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0463] There is a need for means to effectively utilize the vast and fragmented business information held by each department within a group of companies, and to discover new collaborative relationships, thereby enabling operational efficiency and the creation of new businesses. In particular, the challenge lies in building systems that automate these processes and can respond quickly and effectively.

[0464] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0465] In this invention, the server includes means for collecting business information, means for organizing the collected information and converting it into an integrated storage device, and means for analyzing the relationships between the information using the integrated storage device. This makes it possible to identify potential cooperative relationships between departments and automatically propose ways to improve operational efficiency and new business opportunities.

[0466] "Business information" refers to diverse and fragmented data collected from various departments within a group of companies, such as customer information, business know-how, and management strategy information.

[0467] "Preparation" refers to the process of removing duplicates from collected information and standardizing it by unifying the format.

[0468] An "integrated storage device" refers to a database system for centrally storing and managing organized information.

[0469] "Means for analyzing relationships" refers to technologies that use integrated memory devices to analyze patterns and relationships between business information and identify potential collaborative relationships.

[0470] "Cooperative relationships" refer to effective collaborations that can arise from interaction and cooperation between different departments.

[0471] "Automated generation" refers to the process of creating business proposals and plans using generative models without requiring human intervention.

[0472] An "operation screen" refers to a screen that provides an interface for users to approve or modify proposals.

[0473] This invention is a system that supports companies in improving operational efficiency and developing new businesses by integrating business information collected from various departments within a group of companies and discovering new collaborative relationships. At the heart of the system is a server with the functions of collecting, organizing, and analyzing data.

[0474] The server first automatically collects business information from each department using APIs and database connections. At this stage, scripts are executed using programming languages ​​such as Python and Java to periodically retrieve data. The collected data includes customer information, business know-how, and management strategy information.

[0475] Next, the server organizes the collected information. This involves removing duplicate data and arranging it into a consistent format using data cleansing tools and Python data analysis libraries (e.g., Pandas). The organized data is then stored in integrated storage using a SQL database management system (e.g., MySQL or PostgreSQL).

[0476] Based on the information stored in the integrated storage device, the server uses a generative AI model to analyze the data. This allows for the analysis of relationships between data points and the identification of potential collaborative relationships between departments. This analysis is typically performed by running machine learning algorithms in Python scripts.

[0477] For example, analyzing data from the communications and energy management departments can generate proposals for smart home services. In this case, a prompt such as "Analyze how to discover synergistic effects using data from the communications and energy management departments" is input to the generated AI model.

[0478] This system allows the server to automatically generate business proposals and distribute them to terminals in the relevant departments. The terminals provide users with a screen to review the details of the proposals and approve or modify them. Users then proceed with project preparation based on the proposals and report project progress to the server from their terminals. The server analyzes the reported data and can generate project improvement suggestions as needed. This ensures efficient project progress and allows for flexible adjustments to align with the implementation plan.

[0479] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0480] Step 1:

[0481] The server collects business information from each department. Specifically, it uses APIs and database connections to extract customer information, business know-how, and management strategy information from various data sources. Input requires access information and queries from departments, and output is raw business information data.

[0482] Step 2:

[0483] The server processes the collected raw data. This involves removing duplicates and standardizing the format using Python data analysis libraries and data cleansing tools. The input is raw business information data, and the output is processed and standardized business information. Specifically, this includes detecting inconsistent entries and formatting them into a standard format.

[0484] Step 3:

[0485] The server stores the prepared data in integrated storage. A new table is created using the database management system, and the cleaned data is imported. The input is the prepared data, and the output is the set of information stored in the database. Specifically, this involves connecting to the database and adding data.

[0486] Step 4:

[0487] The server analyzes the relationships between information using integrated storage. It uses generative AI models to discover patterns and relationships between data. The input is integrated data, and the output is insights into potential collaborations between departments. Specifically, its operation includes applying machine learning algorithms to quantify these relationships.

[0488] Step 5:

[0489] The server automatically generates business proposals based on the analysis results. It utilizes a generation AI model to create business proposals based on new collaborative relationships. The input is the analysis results, and the output is a business proposal document including feasibility. Specifically, prompts are set, and the AI ​​generation process begins.

[0490] Step 6:

[0491] The terminal delivers business proposals received from the server to the user. It displays the details of the proposal through the user interface. The input is the business proposal document, and the output is visual information for the user. Specifically, this involves the process of displaying the proposal document on the terminal screen.

[0492] Step 7:

[0493] Users report project progress based on business proposals using a terminal. The server receives data on project progress and develops improvement suggestions as needed. The input is project progress data, and the output is improvement suggestions. Specifically, report data is entered from the terminal, and the server performs analysis and generates suggestions.

[0494] (Application Example 1)

[0495] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0496] The knowledge assets and data held by each department within a group of companies are diverse, making it difficult to integrate and utilize this data to maximize interdepartmental collaboration. In particular, there are challenges in efficiently arranging and optimizing the operation of information processing equipment within factories. To solve this problem, it is necessary to integrate data from each department and realize more efficient and autonomous business processes.

[0497] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0498] In this invention, the server includes means for collecting knowledge asset data from multiple departments within a group of companies, means for cleaning up the collected data and converting it into an integrated database, means for analyzing relationships using the integrated database and identifying potential collaborative relationships, and means for optimizing the placement and operation schedule of information processing devices based on feasible business proposals. This enables the discovery of collaborative relationships between departments and the maximization of the placement and operation efficiency of information processing devices within a factory.

[0499] A "group of companies" refers to an organization in which multiple related companies or business divisions come together to conduct business as a unified entity.

[0500] "Knowledge asset data" is a general term for valuable data held by a company, such as customer information, business know-how, and management strategy information.

[0501] "Cleanup" refers to the data processing steps that remove duplicates and noise from collected data and organize it into a unified format.

[0502] An "integrated database" is a database that centralizes and stores cleaned-up data from various departments in an accessible format.

[0503] "Means for analyzing relationships" refers to devices or software that use data analysis techniques to find relationships between data within an integrated database.

[0504] "Potential collaboration" refers to operational efficiency improvements and new business opportunities that can be made possible through inter-departmental cooperation that is not yet apparent.

[0505] A "business proposal" is a plan for specific business improvements or new projects that is automatically generated based on analyzed data.

[0506] An "information processing device" refers to hardware and software equipment used in factories and businesses for inputting, processing, and outputting data.

[0507] "Means for optimizing placement and operation schedules" refer to techniques and methods for planning and adjusting the placement and operating time of information processing devices in order to use them effectively.

[0508] To implement this invention, a server for collecting data from each department within a group of companies, user terminals for displaying the data, and a network environment for them to work together are required. The server collects knowledge asset data from each department within the group of companies and cleans up this data. Specifically, it uses the Python Pandas library to remove duplicate data and convert it into a neat format.

[0509] Subsequently, this cleaned-up data is stored in an integrated database, and the server uses a generative AI model with TensorFlow to analyze the relationships between the data and discover potential collaborative relationships. Based on the discovered collaborative relationships, the server automatically generates business proposals and creates feasible plans. If necessary, the proposals can be further refined using machine learning models with Scikit-learn.

[0510] The user terminal distributes generated business proposals to employees, optimizing the placement and operation schedule of information processing devices. Users are expected to review the proposals on their terminals and implement them according to the instructions. This could improve efficiency within factories and companies, and potentially increase the success rate of new projects.

[0511] As a concrete example, one factory faces the challenge of coordinating different production lines. This system addresses this by analyzing production data from each department and proposing an optimal production line schedule, thereby resolving bottlenecks. An example of a prompt message used in this process is: "Based on the current production speed and assembly time, please propose a production schedule that maximizes the overall efficiency of the manufacturing line." This enables efficient production management.

[0512] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0513] Step 1:

[0514] The server collects knowledge asset data from each department within a group of companies. Inputs are departmental databases and CSV files, and output is a raw dataset. This dataset encompasses a wide range of information held by the companies. The server has the capability to automatically import this data using APIs and FTP.

[0515] Step 2:

[0516] The server cleans up the collected data. The input is the raw dataset collected in step 1, and the output is the cleaned, unified formatted dataset. It uses the Python Pandas library to remove duplicates and unify the formatting, including actions such as formatting dates and numerical units.

[0517] Step 3:

[0518] The server stores the cleaned dataset in a unified database. The input is a unified format dataset, and the output is storage in the database. This process uses an SQL database and also indexes the data. This provides a foundation for efficient subsequent processing.

[0519] Step 4:

[0520] The server performs data analysis using generative AI with an integrated database. The input is the integrated database, and the output is the results of the cooperative relationship analysis. TensorFlow is used to analyze the relationships between data and identify potential cooperative relationships. In this process, a model is built to detect data correlations and trends.

[0521] Step 5:

[0522] The server automatically generates business proposals and creates plans based on the analysis results. The input is the analysis results from step 4, and the output is the business proposal document. This process utilizes NLP technology to assemble insights obtained from the AI ​​model generated by Scikit-learn into natural language text.

[0523] Step 6:

[0524] The server distributes the generated business proposals to the terminals of the relevant departments. The input is the business proposal itself, and the output is the email or document distributed to the department. The server distributes information via a mail server or shared drive, and the terminals provide a user interface (UI) to facilitate document viewing.

[0525] Step 7:

[0526] The user terminal optimizes the placement and operation schedule of information processing equipment based on the proposal. Inputs are the proposal and on-site information, while output is the optimized schedule and layout plan. The user operates the terminal's UI and takes action to implement specific instructions.

[0527] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0528] This invention is a system that integrates and analyzes knowledge asset data collected from various departments within a group of companies, and combines an emotion engine with automatically generated business proposals. In this system, the server, terminals, and users work together to support the entire process from data collection to proposal generation, evaluation, and improvement.

[0529] First, the server collects knowledge asset data from each department within the group of companies, cleans it up, and aggregates it into an integrated database. Based on this data, the server performs analysis using generative AI to discover collaborative relationships between departments and new business opportunities. Subsequently, based on these analysis results, it automatically generates business proposals and detailed implementation plans.

[0530] Here, the newly integrated emotion engine recognizes the user's emotions and analyzes their response to the business proposal. Based on the results of the emotion engine, the server can dynamically adjust the proposal and plan. For example, if the user's response to the proposal is negative, the server re-evaluates the proposal and attempts to revise it to meet the user's expectations.

[0531] As a concrete example, in an evaluation meeting for a new business proposal, the server uses an emotion engine to grasp the participants' real-time emotions. The terminal visualizes the user's positive or negative emotions towards the proposal as graphs and recommendation lists, and the server adjusts the proposal based on this. This function aims to make proposals more acceptable to each department and project team.

[0532] As the project progresses, the server collects user feedback and continuously refines suggestions and plans as needed. The emotion engine monitors changes in user emotions, providing information to determine if the project is progressing properly. Throughout this entire process, the goal is to maximize synergies within the group of companies and improve operational efficiency.

[0533] The following describes the processing flow.

[0534] Step 1:

[0535] The server sends data collection requests to each department within the group of companies. Once knowledge asset data has been collected from each department, the server receives this data and begins processing it.

[0536] Step 2:

[0537] The server cleans up the received data. It removes duplicate data, converts inconsistent data to a standard format, and organizes it into a unified database.

[0538] Step 3:

[0539] The server analyzes the integrated database. Using generative AI, it identifies relationships between data and pinpoints new collaborative relationships and business opportunities. Based on these results, it automatically generates business proposals.

[0540] Step 4:

[0541] The server activates the emotion engine and collects user emotion data in real time. Through the terminal, it recognizes emotions from the user's facial expressions and voice data and analyzes their response to the suggested content.

[0542] Step 5:

[0543] Based on the analysis of emotional data, the server dynamically adjusts business proposals. If the response to a proposal is negative, the plan is revised and changed to better align with the user's expectations.

[0544] Step 6:

[0545] The terminal presents the user with a revised business proposal and implementation plan. The user can review it and either approve the proposal or request additional revisions.

[0546] Step 7:

[0547] Users periodically record their progress and emotional responses using their devices during project implementation. This data is sent to a server and used to evaluate the project.

[0548] Step 8:

[0549] The server analyzes the received progress and sentiment data to evaluate the project. Based on the analysis, it generates suggestions for project improvement as needed and provides feedback to the project team.

[0550] Step 9:

[0551] The terminal receives feedback from the server and notifies the user. Based on the feedback, the user adjusts the project and takes action to achieve the best possible outcome.

[0552] (Example 2)

[0553] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0554] Conventional business proposal systems have problems in that they cannot adequately reflect users' feelings and opinions during the analysis of data collected from each department and in the proposal creation process. Furthermore, the generated proposals do not always meet the expectations of each user and may not be well-received. In addition, progress management during project execution and flexible revision of proposals are difficult.

[0555] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0556] In this invention, the server includes means for collecting information assets from multiple departments within a group of companies, means for formatting the collected information and converting it into integrated data storage, means for automatically generating business proposals and creating actionable plans based on identified collaborative relationships using a generative AI model, and means for analyzing the user's emotions towards the proposals using an emotion analysis engine and dynamically adjusting the proposal content. This enables the provision of business proposals that are easily accepted by each department and project team, as well as flexible project management that reflects the user's emotions in real time.

[0557] "Information assets" refer to the collective knowledge, data, and information accumulated within a group of companies. These are documents and digital content that are managed integrally and utilized to create value.

[0558] "Integrated data storage" refers to a database or data warehouse for organizing and integrating information assets collected from multiple departments, providing a foundation for consistent and efficient data analysis.

[0559] A "generative AI model" refers to artificial intelligence technology used to derive patterns and insights from data and generate new business proposals and solutions. These models utilize natural language processing and machine learning algorithms.

[0560] An "emotion analysis engine" is a technology that analyzes emotions and intentions from a user's text or voice, and adjusts the suggested content based on the results. It is an important tool for reflecting user feedback in real time.

[0561] A "business proposal" is a document that outlines plans and strategies for companies and departments to efficiently and effectively carry out their operations, based on the results of analysis by a generative AI model.

[0562] A description of embodiments for carrying out the present invention will be provided.

[0563] The server collects information assets from various departments within the corporate group. This information includes business reports, project progress data, and customer feedback. Remote access technologies and APIs are used for information collection. The collected data is formatted using data cleansing software (e.g., data cleansing tools), unnecessary information is removed, and then it is stored in integrated data storage.

[0564] Based on integrated data storage, the server performs data analysis using a generative AI model. This analysis uncovers potential collaborations between departments and new business opportunities. Specifically, it uses algorithms with natural language processing technology (e.g., the GPT-4 model) as the generative AI model to extract useful patterns from vast amounts of data. Based on the analysis results, the server automatically generates business proposals and actionable plans.

[0565] On the other hand, when a user receives a business proposal, the terminal uses an emotion analysis engine to analyze the user's emotions in real time. This emotion analysis engine (e.g., an emotion analysis tool) identifies emotions from the user's text and voice, and adjusts the proposal content based on the results. The server receives emotional feedback from the user, dynamically improves the proposal content, and creates a more acceptable proposal.

[0566] As a concrete example, when proposing a new marketing strategy, the generative AI model analyzes past success stories and uses the factors that contributed to those successes to construct a new strategy. Furthermore, it uses an emotion analysis engine to analyze the emotions users have towards the strategy and corrects any parts that do not meet expectations.

[0567] As an example of a prompt, you would input something like, "Please tell me how to use a generative AI model to analyze past success stories and discover new business opportunities in order to propose a new marketing strategy," and give instructions to the generative AI.

[0568] Through this series of processes, it is possible to realize a system that maximizes the use of information assets within a group of companies, enabling improved operational efficiency and the creation of new business opportunities.

[0569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0570] Step 1:

[0571] The server collects information assets from various departments within the corporate group. Inputs include business reports and project progress data, which are received via APIs. The server analyzes this data, formats it using data cleansing tools to remove inconsistencies and duplicates, and stores it in integrated data storage. The output is a clean and consistent dataset.

[0572] Step 2:

[0573] The server analyzes data stored in integrated data storage using a generative AI model. The input is an organized dataset. The server sends prompts to the generative AI model (e.g., GPT-4) to discover data relationships and patterns. This data analysis reveals potential inter-departmental collaborations and business opportunities. The output is a list of discovered patterns and insights.

[0574] Step 3:

[0575] The server automatically generates business proposals and actionable plans based on the analysis results. The input for this stage is the patterns and insights obtained in Step 2. The server uses the generated AI model to concretize the proposals and formalize them as feasible strategies. The output consists of a business proposal document and an action plan document.

[0576] Step 4:

[0577] The terminal collects user responses to generated business proposals. Input includes user voice and text, which are fed into an emotion analysis engine. The terminal analyzes the user's text and voice input and sends the emotion data to the server. The output is the user's emotional state.

[0578] Step 5:

[0579] The server dynamically adjusts the business proposal based on the sentiment analysis results. Using the sentiment data from Step 4 as input, it analyzes which parts were received favorably or negatively by the user. The server re-examines the proposal and modifies it as needed. The output is a business proposal optimized for the user.

[0580] Step 6:

[0581] Users evaluate the final proposal and provide feedback via their terminal. They receive the refined business proposal as input and send their opinions and expectations as feedback to the server. The server receives this feedback and uses it to further improve the project progress and the proposal. The output includes user evaluations and suggestions for improvement to the proposal.

[0582] (Application Example 2)

[0583] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0584] In a corporate environment, a key challenge is effectively utilizing large amounts of knowledge data obtained from multiple departments to efficiently and quickly generate business proposals. Furthermore, dynamic adjustments to these proposals, taking user sentiment into account, are necessary to ensure they are readily accepted by relevant departments and customers. Ultimately, this is required to optimize corporate resources and improve operational efficiency.

[0585] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0586] In this invention, the server includes means for collecting knowledge asset data from multiple departments within a group of companies, means for cleaning up the collected data and converting it into an integrated database, means for analyzing relationships using the integrated database and identifying potential collaborative relationships, means for automatically generating business proposals and creating feasible plans based on the identified collaborative relationships, means for recognizing users' emotions towards the proposals and dynamically adjusting the proposal content based on those emotions, and means for distributing the adjusted proposals to relevant departments, tracking project progress, and improving the proposals based on feedback. This maximizes knowledge sharing and synergy effects among departments and enables business proposals tailored to individual user needs.

[0587] A "group of companies" is a group of companies that collaborate as an organization, sharing their resources and information to carry out their activities.

[0588] "Knowledge asset data" refers to a collection of data with intellectual value, such as documents, information, and know-how, generated within a company.

[0589] "Cleanup" is the process of removing noise and redundant information from collected data and preparing it in a format that can be analyzed.

[0590] An "integrated database" is a database that centrally manages information collected from multiple data sources and is built to allow easy access and analysis.

[0591] "Relationship analysis" is the process of finding relationships and patterns between data and revealing potential meanings and dependencies.

[0592] A "business proposal" is a proposal that presents the optimal solution or action plan for a specific business challenge.

[0593] "Emotion recognition" is a technology that determines a user's emotional state from their facial expressions, voice, and actions, and extracts that information.

[0594] "Dynamic adjustment" refers to the process of continuously modifying and optimizing pre-determined plans and proposals based on real-time situations and new information.

[0595] "Improving based on feedback" refers to the act of improving the system's functions and suggestions by reflecting actual operational results and opinions from users.

[0596] In an embodiment of this invention, the server collects knowledge asset data from each department within a group of companies. The collected data undergoes a cleanup process and is converted into an integrated database. Using this database, the server utilizes a generative AI model to analyze the relationships between the data. The purpose of the analysis is to identify potential collaborative relationships and discover new business opportunities. Based on the results, business proposals are automatically generated and concrete implementation plans are formulated.

[0597] The server also utilizes data provided by the terminal to recognize the user's emotions towards the proposal. Emotion recognition uses an emotion engine that analyzes the user's voice and facial expressions. The emotion engine determines the emotional state in real time and provides feedback to the server. Based on this feedback, the server dynamically adjusts the proposal to create a better one. For example, during an evaluation meeting, the server analyzes participants' reactions through the emotion engine and immediately modifies the proposal if it is being received negatively.

[0598] The server distributes the revised proposal to terminals, allowing relevant departments to approve or revise it on their own devices. This process is expected to improve the acceptability of proposals and promote more synergistic progress in projects within the group of companies.

[0599] As a concrete example, let's consider generating suggestions when a customer is relaxing. The generating AI model can use prompts like the following: "Please suggest products that are suitable for a customer who is relaxing. You can purchase the latest relaxation products at a 10% discount."

[0600] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0601] Step 1:

[0602] The server collects knowledge asset data from each department within a group of companies. The input is raw data provided by each department, and the output is a collection of the collected data. This data includes documents, numerical data, project reports, etc. The server stores this data in a database and prepares it for the next step.

[0603] Step 2:

[0604] The server cleans up the collected data and builds an integrated database. The input is a collection of raw data, which includes unnecessary and duplicate data. The server uses cleansing tools to remove noise and processes the data to ensure data integrity. The output is an integrated dataset suitable for analysis.

[0605] Step 3:

[0606] The server analyzes relationships using an integrated database. The input is a cleaned-up dataset, and the output is the potential collaborations and business opportunities discovered. The server utilizes generative AI models to perform pattern recognition and relationship analysis to explore new business possibilities.

[0607] Step 4:

[0608] The server automatically generates business proposals based on the analysis results. The input is the discovered collaborative relationships and business opportunities, and the output is the automatically generated business proposals and implementation plans. The server inputs prompt messages into the AI ​​model to create a detailed proposal document and execution plan.

[0609] Step 5:

[0610] The server interacts with the terminal to recognize the user's emotions in response to a suggestion. Input is the user's voice and facial expressions, and output is analyzed emotion data. The terminal uses an emotion engine to analyze emotions in real time and sends the results to the server.

[0611] Step 6:

[0612] The server dynamically adjusts the proposal based on sentiment data. The input is sentiment data, and the output is an adjusted proposal. The server reviews the proposal, makes improvements to meet user expectations, and enhances its acceptability.

[0613] Step 7:

[0614] The server delivers the revised proposal to the terminal. The input is the revised proposal document, and the output is the delivery status to the relevant department head. The department head can then review the proposal on their terminal and use the interface to approve or revise it as needed.

[0615] 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.

[0616] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0617] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0618] [Fourth Embodiment]

[0619] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0620] 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.

[0621] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0622] 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.

[0623] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0624] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0625] 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.

[0626] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0627] 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.

[0628] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0629] The 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.

[0630] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0631] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0632] This invention is a system that integrates knowledge asset data collected from various departments within a group of companies and uses that data to maximize the utilization of collaborative relationships. This system operates with a server at the center, performing various data processing tasks, with users and terminals providing support.

[0633] The server first automatically collects knowledge asset data from each department within the group of companies. This data includes customer information, operational know-how, and management strategy information. Since the collected data is often diverse and fragmented, the server cleans it up, removes duplicates, and converts it into a unified format. The cleaned-up data is then stored in an integrated database.

[0634] Next, the server analyzes the relationships between data using an integrated database. Generative AI technology is used to analyze patterns between data and discover potential collaborative relationships between departments. This makes it possible to uncover new business opportunities and ideas for improving the efficiency of existing operations.

[0635] For example, analyzing data from a communications services department and an energy management department might reveal a synergy in providing smart home services to customers of both departments. In this case, the server would create a business proposal based on this synergy.

[0636] The generated business proposals are created along with detailed implementation plans. These plans include project objectives, required resources, and schedules. These plans are distributed via a server to the terminals of the relevant departments, allowing users to review them and proceed with concrete project preparations.

[0637] Project progress is periodically reported to the server by users via their terminals. The server analyzes this data and can suggest improvements to the project as needed. This ensures that the project progresses according to plan and can be flexibly adjusted when necessary.

[0638] This system maximizes synergistic effects within the group of companies, enabling them to carry out operations quickly and efficiently.

[0639] The following describes the processing flow.

[0640] Step 1:

[0641] The server automatically requests knowledge asset data from each department within the group of companies and collects the corresponding datasets. The data is provided in various formats, such as customer information and business know-how.

[0642] Step 2:

[0643] The server cleans up the collected data, eliminating duplicates, correcting inconsistencies, and formatting it into a standard format. This enables efficient data entry into the integrated database.

[0644] Step 3:

[0645] The server stores the cleaned-up data in a unified database. The data is structured and ready for later analysis.

[0646] Step 4:

[0647] The server performs pattern detection using an integrated database. Generative AI is used to analyze correlations between data and discover potential cooperative relationships.

[0648] Step 5:

[0649] The server automatically generates business proposals based on the discovered collaborative relationships. These proposals include new business opportunities and suggestions for improving existing processes.

[0650] Step 6:

[0651] The server distributes the business proposal to the terminals of the relevant departments. Each department can then receive the proposal and begin preparing a concrete implementation plan.

[0652] Step 7:

[0653] Users evaluate the received proposals and develop detailed plans for project implementation. Server support is available as needed to facilitate project progress.

[0654] Step 8:

[0655] Users record project progress on their devices. Progress data is periodically sent to the server.

[0656] Step 9:

[0657] The server analyzes the collected progress data and evaluates the project. If necessary, it automatically generates improvement suggestions and notifies the relevant departments.

[0658] Step 10:

[0659] The terminal receives improvement suggestions from the server and adjusts the project accordingly. This ensures the project progresses according to plan, or according to the revised plan.

[0660] (Example 1)

[0661] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0662] There is a need for means to effectively utilize the vast and fragmented business information held by each department within a group of companies, and to discover new collaborative relationships, thereby enabling operational efficiency and the creation of new businesses. In particular, the challenge lies in building systems that automate these processes and can respond quickly and effectively.

[0663] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0664] In this invention, the server includes means for collecting business information, means for organizing the collected information and converting it into an integrated storage device, and means for analyzing the relationships between the information using the integrated storage device. This makes it possible to identify potential cooperative relationships between departments and automatically propose ways to improve operational efficiency and new business opportunities.

[0665] "Business information" refers to diverse and fragmented data collected from various departments within a group of companies, such as customer information, business know-how, and management strategy information.

[0666] "Preparation" refers to the process of removing duplicates from collected information and standardizing it by unifying the format.

[0667] An "integrated storage device" refers to a database system for centrally storing and managing organized information.

[0668] "Means for analyzing relationships" refers to technologies that use integrated memory devices to analyze patterns and relationships between business information and identify potential collaborative relationships.

[0669] "Cooperative relationships" refer to effective collaborations that can arise from interaction and cooperation between different departments.

[0670] "Automated generation" refers to the process of creating business proposals and plans using generative models without requiring human intervention.

[0671] An "operation screen" refers to a screen that provides an interface for users to approve or modify proposals.

[0672] This invention is a system that supports companies in improving operational efficiency and developing new businesses by integrating business information collected from various departments within a group of companies and discovering new collaborative relationships. At the heart of the system is a server with the functions of collecting, organizing, and analyzing data.

[0673] The server first automatically collects business information from each department using APIs and database connections. At this stage, scripts are executed using programming languages ​​such as Python and Java to periodically retrieve data. The collected data includes customer information, business know-how, and management strategy information.

[0674] Next, the server organizes the collected information. This involves removing duplicate data and arranging it into a consistent format using data cleansing tools and Python data analysis libraries (e.g., Pandas). The organized data is then stored in integrated storage using a SQL database management system (e.g., MySQL or PostgreSQL).

[0675] Based on the information stored in the integrated storage device, the server uses a generative AI model to analyze the data. This allows for the analysis of relationships between data points and the identification of potential collaborative relationships between departments. This analysis is typically performed by running machine learning algorithms in Python scripts.

[0676] For example, analyzing data from the communications and energy management departments can generate proposals for smart home services. In this case, a prompt such as "Analyze how to discover synergistic effects using data from the communications and energy management departments" is input to the generated AI model.

[0677] This system allows the server to automatically generate business proposals and distribute them to terminals in the relevant departments. The terminals provide users with a screen to review the details of the proposals and approve or modify them. Users then proceed with project preparation based on the proposals and report project progress to the server from their terminals. The server analyzes the reported data and can generate project improvement suggestions as needed. This ensures efficient project progress and allows for flexible adjustments to align with the implementation plan.

[0678] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0679] Step 1:

[0680] The server collects business information from each department. Specifically, it uses APIs and database connections to extract customer information, business know-how, and management strategy information from various data sources. Input requires access information and queries from departments, and output is raw business information data.

[0681] Step 2:

[0682] The server processes the collected raw data. This involves removing duplicates and standardizing the format using Python data analysis libraries and data cleansing tools. The input is raw business information data, and the output is processed and standardized business information. Specifically, this includes detecting inconsistent entries and formatting them into a standard format.

[0683] Step 3:

[0684] The server stores the prepared data in integrated storage. A new table is created using the database management system, and the cleaned data is imported. The input is the prepared data, and the output is the set of information stored in the database. Specifically, this involves connecting to the database and adding data.

[0685] Step 4:

[0686] The server analyzes the relationships between information using integrated storage. It uses generative AI models to discover patterns and relationships between data. The input is integrated data, and the output is insights into potential collaborations between departments. Specifically, its operation includes applying machine learning algorithms to quantify these relationships.

[0687] Step 5:

[0688] The server automatically generates business proposals based on the analysis results. It utilizes a generation AI model to create business proposals based on new collaborative relationships. The input is the analysis results, and the output is a business proposal document including feasibility. Specifically, prompts are set, and the AI ​​generation process begins.

[0689] Step 6:

[0690] The terminal delivers business proposals received from the server to the user. It displays the details of the proposal through the user interface. The input is the business proposal document, and the output is visual information for the user. Specifically, this involves the process of displaying the proposal document on the terminal screen.

[0691] Step 7:

[0692] Users report project progress based on business proposals using a terminal. The server receives data on project progress and develops improvement suggestions as needed. The input is project progress data, and the output is improvement suggestions. Specifically, report data is entered from the terminal, and the server performs analysis and generates suggestions.

[0693] (Application Example 1)

[0694] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0695] The knowledge assets and data held by each department within a group of companies are diverse, making it difficult to integrate and utilize this data to maximize interdepartmental collaboration. In particular, there are challenges in efficiently arranging and optimizing the operation of information processing equipment within factories. To solve this problem, it is necessary to integrate data from each department and realize more efficient and autonomous business processes.

[0696] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0697] In this invention, the server includes means for collecting knowledge asset data from multiple departments within a group of companies, means for cleaning up the collected data and converting it into an integrated database, means for analyzing relationships using the integrated database and identifying potential collaborative relationships, and means for optimizing the placement and operation schedule of information processing devices based on feasible business proposals. This enables the discovery of collaborative relationships between departments and the maximization of the placement and operation efficiency of information processing devices within a factory.

[0698] A "group of companies" refers to an organization in which multiple related companies or business divisions come together to conduct business as a unified entity.

[0699] "Knowledge asset data" is a general term for valuable data held by a company, such as customer information, business know-how, and management strategy information.

[0700] "Cleanup" refers to the data processing steps that remove duplicates and noise from collected data and organize it into a unified format.

[0701] An "integrated database" is a database that centralizes and stores cleaned-up data from various departments in an accessible format.

[0702] "Means for analyzing relationships" refers to devices or software that use data analysis techniques to find relationships between data within an integrated database.

[0703] "Potential collaboration" refers to operational efficiency improvements and new business opportunities that can be made possible through inter-departmental cooperation that is not yet apparent.

[0704] A "business proposal" is a plan for specific business improvements or new projects that is automatically generated based on analyzed data.

[0705] An "information processing device" refers to hardware and software equipment used in factories and businesses for inputting, processing, and outputting data.

[0706] "Means for optimizing placement and operation schedules" refer to techniques and methods for planning and adjusting the placement and operating time of information processing devices in order to use them effectively.

[0707] To implement this invention, a server for collecting data from each department within a group of companies, user terminals for displaying the data, and a network environment for them to work together are required. The server collects knowledge asset data from each department within the group of companies and cleans up this data. Specifically, it uses the Python Pandas library to remove duplicate data and convert it into a neat format.

[0708] Subsequently, this cleaned-up data is stored in an integrated database, and the server uses a generative AI model with TensorFlow to analyze the relationships between the data and discover potential collaborative relationships. Based on the discovered collaborative relationships, the server automatically generates business proposals and creates feasible plans. If necessary, the proposals can be further refined using machine learning models with Scikit-learn.

[0709] The user terminal distributes generated business proposals to employees, optimizing the placement and operation schedule of information processing devices. Users are expected to review the proposals on their terminals and implement them according to the instructions. This could improve efficiency within factories and companies, and potentially increase the success rate of new projects.

[0710] As a concrete example, one factory faces the challenge of coordinating different production lines. This system addresses this by analyzing production data from each department and proposing an optimal production line schedule, thereby resolving bottlenecks. An example of a prompt message used in this process is: "Based on the current production speed and assembly time, please propose a production schedule that maximizes the overall efficiency of the manufacturing line." This enables efficient production management.

[0711] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0712] Step 1:

[0713] The server collects knowledge asset data from each department within a group of companies. Inputs are departmental databases and CSV files, and output is a raw dataset. This dataset encompasses a wide range of information held by the companies. The server has the capability to automatically import this data using APIs and FTP.

[0714] Step 2:

[0715] The server cleans up the collected data. The input is the raw dataset collected in step 1, and the output is the cleaned, unified formatted dataset. It uses the Python Pandas library to remove duplicates and unify the formatting, including actions such as formatting dates and numerical units.

[0716] Step 3:

[0717] The server stores the cleaned dataset in a unified database. The input is a unified format dataset, and the output is storage in the database. This process uses an SQL database and also indexes the data. This provides a foundation for efficient subsequent processing.

[0718] Step 4:

[0719] The server performs data analysis using generative AI with an integrated database. The input is the integrated database, and the output is the results of the cooperative relationship analysis. TensorFlow is used to analyze the relationships between data and identify potential cooperative relationships. In this process, a model is built to detect data correlations and trends.

[0720] Step 5:

[0721] The server automatically generates business proposals and creates plans based on the analysis results. The input is the analysis results from step 4, and the output is the business proposal document. This process utilizes NLP technology to assemble insights obtained from the AI ​​model generated by Scikit-learn into natural language text.

[0722] Step 6:

[0723] The server distributes the generated business proposals to the terminals of the relevant departments. The input is the business proposal itself, and the output is the email or document distributed to the department. The server distributes information via a mail server or shared drive, and the terminals provide a user interface (UI) to facilitate document viewing.

[0724] Step 7:

[0725] The user terminal optimizes the placement and operation schedule of information processing equipment based on the proposal. Inputs are the proposal and on-site information, while output is the optimized schedule and layout plan. The user operates the terminal's UI and takes action to implement specific instructions.

[0726] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0727] This invention is a system that integrates and analyzes knowledge asset data collected from various departments within a group of companies, and combines an emotion engine with automatically generated business proposals. In this system, the server, terminals, and users work together to support the entire process from data collection to proposal generation, evaluation, and improvement.

[0728] First, the server collects knowledge asset data from each department within the group of companies, cleans it up, and aggregates it into an integrated database. Based on this data, the server performs analysis using generative AI to discover collaborative relationships between departments and new business opportunities. Subsequently, based on these analysis results, it automatically generates business proposals and detailed implementation plans.

[0729] Here, the newly integrated emotion engine recognizes the user's emotions and analyzes their response to the business proposal. Based on the results of the emotion engine, the server can dynamically adjust the proposal and plan. For example, if the user's response to the proposal is negative, the server re-evaluates the proposal and attempts to revise it to meet the user's expectations.

[0730] As a concrete example, in an evaluation meeting for a new business proposal, the server uses an emotion engine to grasp the participants' real-time emotions. The terminal visualizes the user's positive or negative emotions towards the proposal as graphs and recommendation lists, and the server adjusts the proposal based on this. This function aims to make proposals more acceptable to each department and project team.

[0731] As the project progresses, the server collects user feedback and continuously refines suggestions and plans as needed. The emotion engine monitors changes in user emotions, providing information to determine if the project is progressing properly. Throughout this entire process, the goal is to maximize synergies within the group of companies and improve operational efficiency.

[0732] The following describes the processing flow.

[0733] Step 1:

[0734] The server sends data collection requests to each department within the group of companies. Once knowledge asset data has been collected from each department, the server receives this data and begins processing it.

[0735] Step 2:

[0736] The server cleans up the received data. It removes duplicate data, converts inconsistent data to a standard format, and organizes it into a unified database.

[0737] Step 3:

[0738] The server analyzes the integrated database. Using generative AI, it identifies relationships between data and pinpoints new collaborative relationships and business opportunities. Based on these results, it automatically generates business proposals.

[0739] Step 4:

[0740] The server activates the emotion engine and collects user emotion data in real time. Through the terminal, it recognizes emotions from the user's facial expressions and voice data and analyzes their response to the suggested content.

[0741] Step 5:

[0742] Based on the analysis of emotional data, the server dynamically adjusts business proposals. If the response to a proposal is negative, the plan is revised and changed to better align with the user's expectations.

[0743] Step 6:

[0744] The terminal presents the user with a revised business proposal and implementation plan. The user can review it and either approve the proposal or request additional revisions.

[0745] Step 7:

[0746] Users periodically record their progress and emotional responses using their devices during project implementation. This data is sent to a server and used to evaluate the project.

[0747] Step 8:

[0748] The server analyzes the received progress and sentiment data to evaluate the project. Based on the analysis, it generates suggestions for project improvement as needed and provides feedback to the project team.

[0749] Step 9:

[0750] The terminal receives feedback from the server and notifies the user. Based on the feedback, the user adjusts the project and takes action to achieve the best possible outcome.

[0751] (Example 2)

[0752] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0753] Conventional business proposal systems have problems in that they cannot adequately reflect users' feelings and opinions during the analysis of data collected from each department and in the proposal creation process. Furthermore, the generated proposals do not always meet the expectations of each user and may not be well-received. In addition, progress management during project execution and flexible revision of proposals are difficult.

[0754] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0755] In this invention, the server includes means for collecting information assets from multiple departments within a group of companies, means for formatting the collected information and converting it into integrated data storage, means for automatically generating business proposals and creating actionable plans based on identified collaborative relationships using a generative AI model, and means for analyzing the user's emotions towards the proposals using an emotion analysis engine and dynamically adjusting the proposal content. This enables the provision of business proposals that are easily accepted by each department and project team, as well as flexible project management that reflects the user's emotions in real time.

[0756] "Information assets" refer to the collective knowledge, data, and information accumulated within a group of companies. These are documents and digital content that are managed integrally and utilized to create value.

[0757] "Integrated data storage" refers to a database or data warehouse for organizing and integrating information assets collected from multiple departments, providing a foundation for consistent and efficient data analysis.

[0758] A "generative AI model" refers to artificial intelligence technology used to derive patterns and insights from data and generate new business proposals and solutions. These models utilize natural language processing and machine learning algorithms.

[0759] An "emotion analysis engine" is a technology that analyzes emotions and intentions from a user's text or voice, and adjusts the suggested content based on the results. It is an important tool for reflecting user feedback in real time.

[0760] A "business proposal" is a document that outlines plans and strategies for companies and departments to efficiently and effectively carry out their operations, based on the results of analysis by a generative AI model.

[0761] A description of embodiments for carrying out the present invention will be provided.

[0762] The server collects information assets from various departments within the corporate group. This information includes business reports, project progress data, and customer feedback. Remote access technologies and APIs are used for information collection. The collected data is formatted using data cleansing software (e.g., data cleansing tools), unnecessary information is removed, and then it is stored in integrated data storage.

[0763] Based on integrated data storage, the server performs data analysis using a generative AI model. This analysis uncovers potential collaborations between departments and new business opportunities. Specifically, it uses algorithms with natural language processing technology (e.g., the GPT-4 model) as the generative AI model to extract useful patterns from vast amounts of data. Based on the analysis results, the server automatically generates business proposals and actionable plans.

[0764] On the other hand, when a user receives a business proposal, the terminal uses an emotion analysis engine to analyze the user's emotions in real time. This emotion analysis engine (e.g., an emotion analysis tool) identifies emotions from the user's text and voice, and adjusts the proposal content based on the results. The server receives emotional feedback from the user, dynamically improves the proposal content, and creates a more acceptable proposal.

[0765] As a concrete example, when proposing a new marketing strategy, the generative AI model analyzes past success stories and uses the factors that contributed to those successes to construct a new strategy. Furthermore, it uses an emotion analysis engine to analyze the emotions users have towards the strategy and corrects any parts that do not meet expectations.

[0766] As an example of a prompt, you would input something like, "Please tell me how to use a generative AI model to analyze past success stories and discover new business opportunities in order to propose a new marketing strategy," and give instructions to the generative AI.

[0767] Through this series of processes, it is possible to realize a system that maximizes the use of information assets within a group of companies, enabling improved operational efficiency and the creation of new business opportunities.

[0768] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0769] Step 1:

[0770] The server collects information assets from various departments within the corporate group. Inputs include business reports and project progress data, which are received via APIs. The server analyzes this data, formats it using data cleansing tools to remove inconsistencies and duplicates, and stores it in integrated data storage. The output is a clean and consistent dataset.

[0771] Step 2:

[0772] The server analyzes data stored in integrated data storage using a generative AI model. The input is an organized dataset. The server sends prompts to the generative AI model (e.g., GPT-4) to discover data relationships and patterns. This data analysis reveals potential inter-departmental collaborations and business opportunities. The output is a list of discovered patterns and insights.

[0773] Step 3:

[0774] The server automatically generates business proposals and actionable plans based on the analysis results. The input for this stage is the patterns and insights obtained in Step 2. The server uses the generated AI model to concretize the proposals and formalize them as feasible strategies. The output consists of a business proposal document and an action plan document.

[0775] Step 4:

[0776] The terminal collects user responses to generated business proposals. Input includes user voice and text, which are fed into an emotion analysis engine. The terminal analyzes the user's text and voice input and sends the emotion data to the server. The output is the user's emotional state.

[0777] Step 5:

[0778] The server dynamically adjusts the business proposal based on the sentiment analysis results. Using the sentiment data from Step 4 as input, it analyzes which parts were received favorably or negatively by the user. The server re-examines the proposal and modifies it as needed. The output is a business proposal optimized for the user.

[0779] Step 6:

[0780] Users evaluate the final proposal and provide feedback via their terminal. They receive the refined business proposal as input and send their opinions and expectations as feedback to the server. The server receives this feedback and uses it to further improve the project progress and the proposal. The output includes user evaluations and suggestions for improvement to the proposal.

[0781] (Application Example 2)

[0782] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0783] In a corporate environment, a key challenge is effectively utilizing large amounts of knowledge data obtained from multiple departments to efficiently and quickly generate business proposals. Furthermore, dynamic adjustments to these proposals, taking user sentiment into account, are necessary to ensure they are readily accepted by relevant departments and customers. Ultimately, this is required to optimize corporate resources and improve operational efficiency.

[0784] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0785] In this invention, the server includes means for collecting knowledge asset data from multiple departments within a group of companies, means for cleaning up the collected data and converting it into an integrated database, means for analyzing relationships using the integrated database and identifying potential collaborative relationships, means for automatically generating business proposals and creating feasible plans based on the identified collaborative relationships, means for recognizing users' emotions towards the proposals and dynamically adjusting the proposal content based on those emotions, and means for distributing the adjusted proposals to relevant departments, tracking project progress, and improving the proposals based on feedback. This maximizes knowledge sharing and synergy effects among departments and enables business proposals tailored to individual user needs.

[0786] A "group of companies" is a group of companies that collaborate as an organization, sharing their resources and information to carry out their activities.

[0787] "Knowledge asset data" refers to a collection of data with intellectual value, such as documents, information, and know-how, generated within a company.

[0788] "Cleanup" is the process of removing noise and redundant information from collected data and preparing it in a format that can be analyzed.

[0789] An "integrated database" is a database that centrally manages information collected from multiple data sources and is built to allow easy access and analysis.

[0790] "Relationship analysis" is the process of finding relationships and patterns between data and revealing potential meanings and dependencies.

[0791] A "business proposal" is a proposal that presents the optimal solution or action plan for a specific business challenge.

[0792] "Emotion recognition" is a technology that determines a user's emotional state from their facial expressions, voice, and actions, and extracts that information.

[0793] "Dynamic adjustment" refers to the process of continuously modifying and optimizing pre-determined plans and proposals based on real-time situations and new information.

[0794] "Improving based on feedback" refers to the act of improving the system's functions and suggestions by reflecting actual operational results and opinions from users.

[0795] In an embodiment of this invention, the server collects knowledge asset data from each department within a group of companies. The collected data undergoes a cleanup process and is converted into an integrated database. Using this database, the server utilizes a generative AI model to analyze the relationships between the data. The purpose of the analysis is to identify potential collaborative relationships and discover new business opportunities. Based on the results, business proposals are automatically generated and concrete implementation plans are formulated.

[0796] The server also utilizes data provided by the terminal to recognize the user's emotions towards the proposal. Emotion recognition uses an emotion engine that analyzes the user's voice and facial expressions. The emotion engine determines the emotional state in real time and provides feedback to the server. Based on this feedback, the server dynamically adjusts the proposal to create a better one. For example, during an evaluation meeting, the server analyzes participants' reactions through the emotion engine and immediately modifies the proposal if it is being received negatively.

[0797] The server distributes the revised proposal to terminals, allowing relevant departments to approve or revise it on their own devices. This process is expected to improve the acceptability of proposals and promote more synergistic progress in projects within the group of companies.

[0798] As a concrete example, let's consider generating suggestions when a customer is relaxing. The generating AI model can use prompts like the following: "Please suggest products that are suitable for a customer who is relaxing. You can purchase the latest relaxation products at a 10% discount."

[0799] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0800] Step 1:

[0801] The server collects knowledge asset data from each department within a group of companies. The input is raw data provided by each department, and the output is a collection of the collected data. This data includes documents, numerical data, project reports, etc. The server stores this data in a database and prepares it for the next step.

[0802] Step 2:

[0803] The server cleans up the collected data and builds an integrated database. The input is a collection of raw data, which includes unnecessary and duplicate data. The server uses cleansing tools to remove noise and processes the data to ensure data integrity. The output is an integrated dataset suitable for analysis.

[0804] Step 3:

[0805] The server analyzes relationships using an integrated database. The input is a cleaned-up dataset, and the output is the potential collaborations and business opportunities discovered. The server utilizes generative AI models to perform pattern recognition and relationship analysis to explore new business possibilities.

[0806] Step 4:

[0807] The server automatically generates business proposals based on the analysis results. The input is the discovered collaborative relationships and business opportunities, and the output is the automatically generated business proposals and implementation plans. The server inputs prompt messages into the AI ​​model to create a detailed proposal document and execution plan.

[0808] Step 5:

[0809] The server interacts with the terminal to recognize the user's emotions in response to a suggestion. Input is the user's voice and facial expressions, and output is analyzed emotion data. The terminal uses an emotion engine to analyze emotions in real time and sends the results to the server.

[0810] Step 6:

[0811] The server dynamically adjusts the proposal based on sentiment data. The input is sentiment data, and the output is an adjusted proposal. The server reviews the proposal, makes improvements to meet user expectations, and enhances its acceptability.

[0812] Step 7:

[0813] The server delivers the revised proposal to the terminal. The input is the revised proposal document, and the output is the delivery status to the relevant department head. The department head can then review the proposal on their terminal and use the interface to approve or revise it as needed.

[0814] 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.

[0815] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0816] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0817] 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.

[0818] Figure 9 shows an 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.

[0819] 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.

[0820] 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.

[0821] 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, motorcycles, etc., 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, for example, based 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.

[0822] 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."

[0823] 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.

[0824] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0825] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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 the like 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.

[0834] 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.

[0835] The following is further disclosed regarding the embodiments described above.

[0836] (Claim 1)

[0837] A means of collecting knowledge asset data from multiple departments within a group of companies,

[0838] A means of cleaning up the collected data and converting it into an integrated database,

[0839] A means of analyzing relationships using an integrated database and identifying potential collaborative relationships,

[0840] A means of automatically generating business proposals based on identified collaborative relationships and creating feasible plans,

[0841] A means of distributing proposals to relevant departments and tracking project progress,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, which evaluates the progress of a project and makes suggestions for project improvements based on the evaluation results.

[0845] (Claim 3)

[0846] The system according to claim 1, which displays the generated proposal and provides an interface for each department head to approve or revise the proposal.

[0847] "Example 1"

[0848] (Claim 1)

[0849] Means of collecting business information from multiple departments,

[0850] A means for organizing the collected information and converting it into an integrated storage device,

[0851] A means of analyzing the relationships between information using an integrated storage device and identifying potential cooperative relationships,

[0852] A means of automatically generating business proposals based on identified collaborative relationships using a generative model, and creating feasible plans,

[0853] A means of distributing business proposals to relevant departments and tracking the progress of the project,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, which evaluates the progress of a project and makes suggestions for improving the project based on the evaluation results.

[0857] (Claim 3)

[0858] The system according to claim 1, which displays the generated plan and provides an operation screen for each department manager to approve or modify the proposal.

[0859] "Application Example 1"

[0860] (Claim 1)

[0861] A means of collecting knowledge asset data from multiple departments within a group of companies,

[0862] A means of cleaning up the collected data and converting it into an integrated database,

[0863] A means of analyzing relationships using an integrated database and identifying potential collaborative relationships,

[0864] A means of automatically generating business proposals based on identified collaborative relationships and creating feasible plans,

[0865] A means of distributing proposals to relevant departments and tracking project progress,

[0866] A means of optimizing the placement and operation schedule of information processing equipment based on feasible business proposals,

[0867] A system that includes this.

[0868] (Claim 2)

[0869] The system according to claim 1, which evaluates the progress of a project and makes suggestions for project improvements based on the evaluation results.

[0870] (Claim 3)

[0871] The system according to claim 1, which displays the generated proposal and provides an interface for each department head to approve or revise the proposal.

[0872] "Example 2 of combining an emotion engine"

[0873] (Claim 1)

[0874] Means for collecting information assets from multiple departments within a group of companies,

[0875] A means of formatting the collected information and converting it into integrated data storage,

[0876] A means of analyzing relationships using integrated data storage and identifying potential collaborative relationships,

[0877] A means for automatically generating business proposals and creating actionable plans based on collaborative relationships identified using a generative AI model,

[0878] A means of dynamically adjusting the content of a proposal by analyzing the user's emotions in response to the proposal using an emotion analysis engine,

[0879] A means of distributing proposals to relevant departments and tracking project progress,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, which evaluates the progress of a project and makes suggestions for project improvements based on the results of an emotion analysis engine.

[0883] (Claim 3)

[0884] The system according to claim 1, which displays the generated proposal, provides an interface for departmental personnel to approve or revise the proposal, and visualizes the emotions of the users.

[0885] "Application example 2 when combining with an emotional engine"

[0886] (Claim 1)

[0887] A means of collecting knowledge asset data from multiple departments within a group of companies,

[0888] A means of cleaning up the collected data and converting it into an integrated database,

[0889] A means of analyzing relationships using an integrated database and identifying potential collaborative relationships,

[0890] A means of automatically generating business proposals and creating feasible plans based on identified collaborative relationships,

[0891] A means of recognizing the user's emotions towards a proposal and dynamically adjusting the proposal content based on those emotions,

[0892] A means of distributing the adjusted proposal to the relevant departments, tracking project progress, and improving the proposal based on feedback,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, which evaluates the progress of a project and makes suggestions for project improvements based on the evaluation results.

[0896] (Claim 3)

[0897] The system according to claim 1, which displays generated proposals and provides an interface that allows departmental personnel to approve or modify proposals and to enable additional improvements based on sentiment information. [Explanation of Symbols]

[0898] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting knowledge asset data from multiple departments within a group of companies, A means of cleaning up the collected data and converting it into an integrated database, A means of analyzing relationships using an integrated database and identifying potential collaborative relationships, A means of automatically generating business proposals based on identified collaborative relationships and creating feasible plans, A means of distributing proposals to relevant departments and tracking project progress, A system that includes this.

2. The system according to claim 1, which evaluates the progress of a project and makes suggestions for project improvements based on the evaluation results.

3. The system according to claim 1, which displays the generated proposal and provides an interface for each department head to approve or revise the proposal.

Images