system

Abstract

We provide the system. [Solution] A receiving means that works in conjunction with a device for acquiring information and inputs basic information related to the organization's activities and cost reduction targets, A communication means for transmitting received information to a processing unit, A generation means that generates various hypotheses based on received information using a generation device within the processing device, A display means for notifying users of the generated hypothesis, A data analysis means that works in conjunction with the measuring device of the operating machine and performs analysis based on the collected data, A strategy generation means that generates operational improvement measures based on information from measuring devices, 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] Many companies are considering various measures to reduce costs, but there is a problem that this consideration activity itself also takes a lot of time, labor, and thus cost. Furthermore, since each company sets its own problems and conducts information collection and analysis, it is inefficient and not utilized as standardized know-how. Therefore, there is a need for a new system for companies to formulate and evaluate cost reduction plans quickly and effectively.

Means for Solving the Problems

[0005] This invention provides a system for companies to effectively formulate and evaluate cost reduction proposals. The system receives basic information about a company's operations and cost reduction objectives entered by the user, and a generating AI generates hypotheses based on this information. Furthermore, the generating AI collects information on successful case studies from other companies and available services, and presents this information to the user, thereby supporting efficient decision-making. In addition, for specific cost reduction proposals, it performs a return on investment simulation, helping the user determine whether a particular reduction proposal is feasible. In this way, the system streamlines a company's review process and ultimately contributes to cost reduction.

[0006] "Information input devices" refer to terminals or devices used by users to manually or automatically input business information or cost reduction data for a company.

[0007] A "receiving means" refers to a device or module that has the function of receiving information input from a user and converting it into a format that can be used within the system.

[0008] "Communication means" refers to an interface or protocol for transmitting received information to other modules within the system or to external processing units.

[0009] "Generation means" refers to a process or device that uses artificial intelligence technology to generate hypotheses or solutions based on input information.

[0010] "Display means" refers to devices such as screens and displays used to visually communicate generated hypotheses or solutions to users.

[0011] "Data collection means" refers to a process or device for collecting information on other companies' case studies and available services from the internet or other data sources and using it within a system.

[0012] A "simulation tool" is a process or function that performs calculations to predict the return on investment for a particular cost reduction plan. [Brief explanation of the drawing]

[0013] [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention presents an implementation of a system designed for companies to effectively formulate and evaluate cost reduction plans. The system consists of users, terminals, and a server, and operates as follows:

[0035] First, the user uses a terminal to input basic information about their company's operations and specific goals for cost reduction. This information includes industry, department, and current challenges. The terminal then sends this information to the server.

[0036] Next, the server uses generative AI to generate appropriate cost reduction hypotheses based on the received information. The generative AI creates hypotheses based on pre-programmed databases and learning models, while also considering success stories and best practices from other companies.

[0037] Based on the generated hypotheses, the terminal visually displays suggestions to the user. This display allows the user to understand specific cost reduction strategies and prepare to incorporate them into the company's strategy.

[0038] Furthermore, the server has the functionality to collect information on successful case studies from other companies, as well as available tools and services. This data collection process is performed automatically by a generating AI, and the results are displayed to the user via their device. Based on this, the user can consider effective measures.

[0039] Furthermore, for specific cost reduction proposals, the server uses AI to perform a return on investment simulation. This calculates startup costs and future cost reduction effects specifically, and displays them to the user on their terminal. Based on this evaluation, the user can decide whether or not to implement the reduction proposal.

[0040] One example of its use is when a manufacturing company utilizes this system to receive hypothetical proposals for revising its procurement process aimed at reducing material costs. In this case, the generating AI might analyze existing supply chain information and suggest more effective potential suppliers. Along with these proposals, the system provides simulation results of cost reduction effects from the server, enabling the company to make data-driven decisions.

[0041] Thus, in the embodiments of the present invention, by integrating the collection, analysis, and proposal of information, it is possible to streamline a company's cost reduction activities and increase their success rate.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] Users use a terminal to input basic information about the company's operations, as well as areas and specific goals for cost reduction. This includes industry, department name, and current challenges and resource status.

[0045] Step 2:

[0046] The terminal formats the input information, performs format conversion as necessary, and then sends the information to the server as a data packet.

[0047] Step 3:

[0048] The server analyzes the received information and invokes a generative AI. The generative AI generates hypotheses about cost reduction related to the input information, based on the database and past learning models.

[0049] Step 4:

[0050] The server converts the generated hypotheses into an internal data format, generating more detailed and usable information. This includes case study data from other companies and relevant market data.

[0051] Step 5:

[0052] The terminal receives hypotheses and accompanying information transmitted from the server and displays them visually on the user interface. The user reviews this and examines the elements that can be applied to their company's strategy.

[0053] Step 6:

[0054] Users select hypotheses and proposals that interest them and request detailed simulations. These selections are then sent back to the server via the terminal.

[0055] Step 7:

[0056] The server then uses the generated AI again to perform a return on investment simulation for the selected proposal. This process calculates the initial investment amount, estimated cost savings, implementation period, and other factors.

[0057] Step 8:

[0058] The server compiles the simulation results and sends this information to the terminal in the form of specific numerical data and graphs.

[0059] Step 9:

[0060] The terminal displays the simulation results on the user interface, allowing the user to consider the feasibility of implementing cost reduction proposals. The user then makes a decision based on this information.

[0061] Through the steps outlined above, this system enables an efficient planning and evaluation process for cost reduction within a company.

[0062] (Example 1)

[0063] 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."

[0064] In today's business environment, companies are required to improve operational efficiency while simultaneously reducing costs. Traditional methods require significant time and effort to develop improvement plans, and they often fail to utilize successful case studies from other companies or the latest tools. This creates a challenge in that optimal cost-reduction measures may be overlooked.

[0065] 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.

[0066] In this invention, the server includes an input means that works in conjunction with a device for inputting information to record basic business data and cost reduction targets, a communication means that transmits the input data to a central processing unit, and a generation means that uses an automatic generation device within the central processing unit to construct multiple hypotheses based on the input data. This enables companies to quickly formulate specific and data-driven cost reduction measures and to utilize successful case studies from other companies and the latest tools.

[0067] "Input means" refers to a device or interface for recording basic business data and cost reduction targets.

[0068] "Communication means" refers to the technologies that constitute protocols and devices for transmitting input data to a central processing unit.

[0069] "Generation means" refers to a function within the central processing unit that uses an automatic generation device to construct multiple hypotheses based on input data.

[0070] "Display means" refers to a device or software mechanism for visually presenting a constructed hypothesis to the user.

[0071] "Information gathering methods" refer to algorithms and systems for collecting information on other people's success stories and available tools.

[0072] "Analysis methods" refer to processes or models that use automated generation devices to predict the financial effects of specific cost reduction proposals.

[0073] The embodiments for carrying out the present invention are described below.

[0074] This invention is a system aimed at enabling companies to reduce costs while improving operational efficiency. The system mainly consists of a server, terminals, and users. The server functions as a central processing unit and is responsible for major data processing and the operation of the generation AI model. The terminals receive input from users and communicate with the server.

[0075] Specifically, users input basic business-related data and cost reduction targets into a terminal. This input data is transmitted via an input device such as a PC or tablet, and is implemented through a user interface. The terminal then transmits this data to a server. This communication is carried out using protocols that utilize the internet or the company's internal network.

[0076] The server automatically generates hypotheses using a generative AI model based on the received data. This generative AI model uses pre-trained databases and algorithms to construct hypotheses while considering successful case studies and the latest best practices from other companies. This process identifies a variety of cost-reduction proposals.

[0077] Furthermore, the server uses analytical tools to predict the financial effects of the generated hypotheses. Specific analyses include comparing startup costs with expected cost savings. This allows companies to obtain detailed data for evaluating feasibility.

[0078] The generated hypotheses and their analysis results are presented visually to the user via the device. This presentation utilizes visualization techniques such as charts and graphs to facilitate data interpretation.

[0079] For example, a manufacturing company might use this system to receive suggestions for improving its procurement process to reduce material costs. In this case, the generating AI can analyze existing supply chain data and suggest more effective suppliers. Furthermore, based on the cost reduction simulation results provided by the server, companies can make data-driven decisions.

[0080] An example of a prompt would be: "Please propose effective cost reduction measures to lower material costs in our manufacturing sector. Refer to successful case studies from other companies and also indicate the expected return on investment."

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] Users use a terminal to input basic data about their company's operations and cost reduction targets. This input is done through a dedicated application on the terminal or a web interface, and includes information such as industry, department, and current challenges. This input data is then transmitted directly from the terminal to the server.

[0084] Step 2:

[0085] The server analyzes the data received from the terminal. The received information is standardized through a parser that classifies each item and formatted as input data for the generated AI model. During this process, missing or outlier data is checked and corrected or removed as necessary.

[0086] Step 3:

[0087] The server activates a generative AI model and generates prompt messages. Based on the information received from the user, the server forms the optimal prompt message and passes it to the generative AI. This prompt message includes instructions for suggesting cost reduction measures, and the model generates a variety of hypotheses.

[0088] Step 4:

[0089] The server evaluates the hypotheses generated by the AI ​​model. The generated hypotheses are scored using predefined evaluation criteria, focusing on economic validity and feasibility. The optimal hypothesis is selected and formatted as data to be presented to the user.

[0090] Step 5:

[0091] The terminal visually presents the best hypothesis sent from the server to the user. Using visualization tools, the details of the hypothesis and the expected cost reduction effects are displayed in graphs and text format. Based on the visual information, the user considers specific cost reduction measures.

[0092] Step 6:

[0093] The server gathers additional information and updates its hypotheses. For example, it regularly searches online resources and other companies' databases to collect new success stories and industry best practices. This information is also used as material for hypothesis formation.

[0094] (Application Example 1)

[0095] 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."

[0096] In recent years, improving productivity and reducing costs within organizations have become crucial management decisions. However, traditional methods make it difficult to quickly and accurately identify operational inefficiencies and formulate optimal improvement measures. In particular, utilizing operational machine data to support real-time decision-making requires considerable effort and cost. Therefore, there is a need for technology that can easily and effectively analyze the performance of operational machines and obtain optimal improvement suggestions.

[0097] 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.

[0098] In this invention, the server includes a receiving means that cooperates with a device for acquiring information and inputs basic information related to the organization's activities and cost reduction targets; a communication means that transmits the received information to a processing unit; a generation means that uses a generation device within the processing unit to generate various hypotheses based on the received information; a data analysis means that works in conjunction with a measuring device of the operational machine to perform analysis based on the collected data; and a strategy generation means that generates operational improvement measures based on information from the measuring device. This makes it possible to formulate efficient and effective operational improvement measures that utilize real-time data from the operational machine.

[0099] "Receiving means" refers to a function that works in conjunction with devices for acquiring information to obtain basic information related to the organization's activities and cost reduction targets.

[0100] "Communication means" refers to a function for transmitting received information to a processing unit.

[0101] "Generation means" refers to a function that uses a generation device within the processing unit to generate various hypotheses based on received information.

[0102] "Display means" refers to a function for notifying users of the generated hypothesis.

[0103] A "data analysis means" is a function that works in conjunction with the measuring devices of the operating machine to perform analysis based on the collected data.

[0104] A "strategy generation tool" is a function that generates operational improvement measures based on information from measuring devices.

[0105] Embodiments of this invention include a system for efficiently formulating operational improvement measures. A server, in cooperation with a device for acquiring information, receives basic information and cost reduction targets related to the organization's activities. Information is then collected through the receiving means. The received information is transmitted to a processing unit using a communication means, and a generation means within the processing unit uses a generation AI model to generate various hypotheses based on the received information.

[0106] The generated hypotheses are notified to the user via a terminal. The display device fulfills this role, allowing the user to obtain information and receive support for decision-making. Furthermore, the server works in conjunction with the measuring devices of the operational machinery to analyze the data collected by the data analysis device. This highlights areas for improvement in operational efficiency at the site.

[0107] The strategy generation system generates operational improvement measures based on information from measurement devices. These generated improvement measures can be viewed by users via smart glasses or other devices, promoting operational efficiency. Simulation and effect prediction of the improvement measures utilize a generation AI model, and by providing concrete implementation examples, effective strategy planning becomes possible.

[0108] As a concrete example, there are cases where a large amount of sensor information is collected to identify line bottlenecks and propose rearrangement. For instance, by analyzing sensor information from a production line that frequently experiences stoppages, it might be proposed that rearrangement could improve efficiency by up to 30%. This proposal is visualized using the AR function of smart glasses, allowing line managers to understand it intuitively.

[0109] Examples of prompts for generative AI models:

[0110] We will provide the factory robot data below. Based on this data, please generate operational improvement proposals and present the simulation results of their return on investment.

[0111] Production line: Line A

[0112] Energy consumption: High

[0113] Operating hours: 24 hours

[0114] Summary: Propose ways to increase efficiency and reduce energy consumption.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] Users input basic information related to their organization's activities and cost reduction goals using a device designed to retrieve information. This input information is transmitted to the server via the terminal. The input data here concerns the current state and goals of operations. As output, this data is stored on the server.

[0118] Step 2:

[0119] The server generates various hypotheses using a generative AI model based on the received information. In this step, the received information is input into the generative AI model, and hypothesis ideas are output. Data processing involves generating hypotheses based on success stories and best practices from other companies. As output, a list of hypothesis ideas is obtained.

[0120] Step 3:

[0121] The generated hypothetical ideas are notified to the user via the terminal's display device. The user reviews the hypothesis based on this display and makes revisions or provides feedback as needed. The input is the hypothetical idea, and the output is the user's evaluation and feedback.

[0122] Step 4:

[0123] The server works in conjunction with the measuring devices of the operational machinery to collect and analyze actual operational data. The data analysis method integrates the collected sensor data to identify operational efficiency issues. The input is actual measurement data, and the output provides points for operational improvement.

[0124] Step 5:

[0125] The server generates operational improvement measures using a strategy generation mechanism based on measurement data. In this step, it performs the data calculations necessary to generate improvement measures and outputs specific improvement measures. The input is the operational challenges, and the output is specific improvement proposals.

[0126] Step 6:

[0127] Users visually review improvement measures via their devices or smart glasses and decide whether or not to implement them. In this step, the simulation results of the generated improvement measures are displayed, providing information for decision-making. The input is the improvement measures, and the user's decision is output.

[0128] 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.

[0129] This invention presents an embodiment of a system that offers effective cost-reduction proposals and provides feedback that takes user emotions into consideration. The system mainly consists of a user, a terminal, a server, and an emotion engine.

[0130] First, the user uses a terminal to input basic company information and cost reduction objectives. This information input specifically includes details such as industry, department, challenges, and expected results. The terminal then converts this information into a format and sends it to the server.

[0131] Next, the server analyzes the received information and requests a generative AI to generate appropriate hypotheses. This generative AI utilizes existing databases and inference models, taking into account past success stories and market trends. The hypotheses generated here propose cost reduction measures that are considered effective for the user.

[0132] Next, the emotion engine collects user emotion data through the device. This is done by acquiring and analyzing information such as the user's voice, facial expressions, and input speed while they are operating the device. Based on the acquired data, the emotion engine evaluates the user's emotional state.

[0133] Subsequently, the server adjusts how hypotheses are presented based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, it provides information tailored to their emotions, such as adding more relaxing feedback. This allows suggestions and information to be presented in a way that is appropriate to the user's emotional state, improving the user experience.

[0134] The terminal receives feedback from the server and displays it to the user visually and audibly. This display includes not only detailed information on cost-saving proposals, but also emotionally responsive advice and recommendations for the next steps.

[0135] As a concrete example, consider a scenario where a product manufacturing company uses the system. If the user is aiming to optimize the selling price to customers, the system will suggest a revision of the discount algorithm. If the user is feeling anxious at this time, the emotion engine will sense this and display feedback on the terminal to help them feel more at ease with the suggestion.

[0136] Thus, this invention not only supports companies' cost reduction activities but also enables interactive and flexible information delivery that takes user emotions into consideration.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] Users use a terminal to input basic information about the company's operations and specific cost reduction objectives. This includes details such as industry, department, current challenges, and reduction targets.

[0140] Step 2:

[0141] The terminal converts the information entered by the user into digital data and sends it to the server. The transmitted data is formatted in a way that is necessary for analysis on the server.

[0142] Step 3:

[0143] The server activates a generation AI based on the received business information, and generates appropriate cost reduction hypotheses based on the input information. The generation AI takes historical data and market trends into consideration and extracts multiple hypotheses.

[0144] Step 4:

[0145] The server further organizes the generated hypotheses and prepares to send them to the terminal as a concrete action plan, including detailed information and relevant case studies.

[0146] Step 5:

[0147] The device presents the received information to the user, but at the same time, it activates an emotion engine to monitor the user's reaction. Emotional data is collected through voice input and facial recognition.

[0148] Step 6:

[0149] The emotion engine analyzes the user's emotional data to determine whether they are stressed, at ease, or interested. This information is sent to the server.

[0150] Step 7:

[0151] The server receives data from the emotion engine and generates hypothetical feedback appropriate to the user's emotional state. For example, if the user is feeling stressed, it adds softer language and reassuring information to help them relax.

[0152] Step 8:

[0153] The device redisplays feedback sent from the server to the user. This display includes visuals and audio to help the user make decisions in a relaxed environment.

[0154] Step 9:

[0155] Based on the presented cost reduction hypotheses and related information, users select appropriate actions and proceed to the next step.

[0156] The above outlines the specific processing flow of a system that integrates an emotion engine. This process allows users to make data-driven decisions while receiving emotional considerations.

[0157] (Example 2)

[0158] 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".

[0159] Traditional cost reduction systems were limited to making suggestions based on company data and were unable to provide adaptive feedback tailored to the user's emotions and circumstances. As a result, problems arose such as users experiencing stress or the suggestions not being effectively communicated.

[0160] 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.

[0161] In this invention, the server is linked to a terminal for inputting information about work content and goals, and includes an input means for inputting basic information and objectives, a generation means for analyzing the input information and generating hypotheses using a generation AI model, and an emotion adaptation means for adjusting and presenting suggestions based on the user's emotional information in conjunction with the generated hypotheses. This makes it possible to provide feedback that is appropriate to the user's emotions and to ensure that the suggested content is communicated to the user more effectively.

[0162] A "terminal" refers to a device used by users to input information and plays a role in sending and receiving data in conjunction with a system.

[0163] An "input method" is a means for users to input business information and objectives into a terminal, and it is equipped with the function to appropriately transfer that information into the system.

[0164] A "generative AI model" is an artificial intelligence model that generates hypotheses and proposals based on received information, and is an algorithm that performs inference based on a large amount of data.

[0165] A "generative means" is a means that has the function of generating hypotheses from input data using a generative AI model.

[0166] "Emotional adaptation means" refers to functions and methods for analyzing a user's emotional information, adjusting the suggested content based on the results, and presenting it in the most optimal form.

[0167] A "visualization tool" is a means of visually displaying feedback information adapted to generated hypotheses and emotions to the user, and is a device that has the function of conveying information in an easy-to-understand manner through a user interface.

[0168] This invention is an embodiment of a system that effectively proposes cost reductions for companies and provides feedback that takes user emotions into consideration.

[0169] Specifically, users first input company business information using a terminal. The terminal is a computer device equipped with a dedicated interface for inputting information such as industry, department, tasks, and expected results. User input is converted into data format in real time and sent to the server.

[0170] Next, the server analyzes the received data. Here, a generative AI model is used to create prompt statements and generate the optimal hypothesis while referring to the database and inference algorithms. This generative AI model refers to an algorithm that runs in a software environment such as Python or TENSORFLOW®.

[0171] Subsequently, the emotion engine collects user emotion data through the device. This involves analyzing facial expressions, voice tone, and input speed during operation using cameras, microphones, sensors, etc. This includes a means of quantifying the user's emotional state from this information.

[0172] Finally, the server adaptively adjusts the presentation method of the generated hypotheses based on emotional information. As the central device of the system, the server generates feedback that corresponds to the user's emotions and sends it to the terminal. The terminal displays this feedback to the user using visualization means.

[0173] A concrete example of this system could be a product manufacturing company. When a user aims to optimize the selling price to their customers, the system may suggest a revision of the discount algorithm. At the same time, if the emotion engine detects that the user is feeling stressed, feedback to promote a sense of security will be displayed on the screen.

[0174] An example of a prompt message provided to the generating AI might be: "Please propose an effective discount strategy for optimizing customer pricing in product manufacturing. Also, please consider methods for providing feedback that respond to user emotions."

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] Users input business information and cost reduction objectives using a terminal. Specifically, they enter their industry, department, challenges, and expected results into a dedicated input form. The entered data is structured within the terminal and formatted for subsequent processing. A formatted data object is generated as the output of the input.

[0178] Step 2:

[0179] The terminal sends the formatted data to the server. The communication module within the terminal packets the data and sends it to the server using a secure communication protocol. The server re-analyzes the received data and stores it in an internal data structure for analysis. Based on the data received as input, a dataset for analysis is output.

[0180] Step 3:

[0181] The server generates hypotheses using a generative AI model. It creates prompt statements as input and sends them to the generative AI. Here, the inference algorithm runs using libraries such as Python and TensorFlow. Based on historical data and marketing trends, the model outputs new cost reduction proposals. The generated hypotheses are output as hypothesis data.

[0182] Step 4:

[0183] The device collects emotional data based on the user's actions. Specifically, it uses a camera and microphone to record facial expressions and voice, and sensors to measure input speed and pressure. The obtained data is analyzed in real time by an emotion engine and output as a numerical value indicating the user's emotional state.

[0184] Step 5:

[0185] The server receives evaluation results from the emotion engine and adjusts how hypotheses are presented. It receives emotion evaluation scores as input and adjusts the wording of prompts and output hypotheses. If necessary, it uses the regenerative AI model to generate new feedback and outputs suggestions in an adaptive and optimal format.

[0186] Step 6:

[0187] The device displays tailored feedback to the user. In addition to presenting visual information on the display, it guides the user through suggestions via audio output. The user can confirm information visually and aurally, and receive guidance to select the next action. The output includes visually and audibly generated feedback.

[0188] (Application Example 2)

[0189] 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".

[0190] When companies seek to reduce costs, they need not only to propose various hypotheses but also to respond flexibly, taking into account the emotional state of users, in order to make effective proposals. Similarly, in physical stores, providing information based on the customer's emotional state is necessary to make effective sales proposals that meet customer needs. Conventional systems lack the ability to optimize proposals using this kind of emotional data.

[0191] 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.

[0192] In this invention, the server includes input means linked to electronic devices for supplying information, information transmission means for transmitting information to data processing equipment, generation means for generating various hypotheses using a hypothesis generation device, emotion evaluation means for acquiring emotion data, and adjustment means for adjusting the method of presenting hypotheses. This enables flexible and effective cost reduction and sales proposals that respond to the user's emotions.

[0193] "Electronic devices for supplying information" refers to devices used by users to input basic information about a company's business and to achieve cost reduction objectives.

[0194] An "input method" is a device that allows users to supply information via electronic devices and incorporate it into the system.

[0195] The "information transmission means" refers to the part responsible for transmitting the input information to a data processing device.

[0196] "Data processing equipment" refers to the primary equipment used to generate hypotheses based on supplied information and to perform various processing tasks.

[0197] A "hypothesis generation device" is a device used within a data processing device to generate various hypotheses based on supplied information.

[0198] "Generative means" refers to the function of constructing diverse hypotheses using a hypothesis generation device.

[0199] "Visualization means" refers to a function that provides users with a visual representation of the generated hypotheses.

[0200] "Emotional evaluation means" refers to a function that acquires user emotional data and analyzes that state.

[0201] "Adjustment mechanisms" refer to functions for optimizing the method and content of hypothesis presentation based on acquired emotional data.

[0202] In this embodiment of the invention, the system primarily uses an "electronic device for supplying information," a "data processing device," and a "sentiment evaluation means." First, the user inputs basic company information and cost reduction objectives using the electronic device for supplying information. This activates the input means, and the input information is transmitted to the data processing device via the information transmission means.

[0203] Next, the data processing equipment uses a hypothesis generation device to generate various hypotheses based on the supplied information. The hypothesis generation device constructs hypotheses by utilizing prompts to existing databases and generation AI models. In this process, the generation means handles the process, and the generated hypotheses are visually presented to the user through a visualization means.

[0204] Furthermore, an emotion assessment system is activated to acquire and analyze emotional data from the user's voice and facial expressions, thereby evaluating the user's emotional state. This emotional data influences the way hypotheses are presented through adjustment mechanisms. For example, if the user is experiencing stress, the presentation method is flexibly adjusted to provide feedback that enhances relaxation.

[0205] As a concrete example, a product manufacturing company might use the system to optimize its sales strategy to customers. The user inputs a pricing strategy for a specific product, and a hypothesis generator suggests a revised discount algorithm. In this process, an emotion evaluation system senses the user's reaction, and an adjustment system selects a more relaxed suggestion method.

[0206] An example of a prompt to a generative AI model is: "This customer is looking for a new washing machine with a budget of approximately 50,000 yen. Please present options that offer the best cost performance under those conditions." This invention enables the presentation of appropriate information that takes user sentiment into account, as well as more reliable cost-saving proposals.

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] Users input basic company information and cost reduction objectives using electronic devices to supply information. The entered data includes information such as business areas, departments, challenges, and expected outcomes. This data is collected by the input means and transmitted to data processing equipment via the information transmission means.

[0210] Step 2:

[0211] The server acts as a data processing device, analyzing received information using a hypothesis generation device. Based on the information input, it generates prompt sentences using a generative AI model and queries the generative AI model. The hypothesis generation device considers past successes and market trends to generate a variety of hypotheses. As output, it provides a list of multiple possible hypotheses.

[0212] Step 3:

[0213] The server uses visualization tools to visually present the generated hypotheses to the user. The output data is displayed graphically on the user's electronic device, providing detailed information on the proposed cost reduction measures.

[0214] Step 4:

[0215] While the user operates the system through the terminal, the emotion evaluation system operates, acquiring emotion data based on the user's voice and facial expressions. The input data includes voice tone and emotion patterns obtained using facial recognition technology.

[0216] Step 5:

[0217] The server analyzes emotional data and modifies the generated hypothesis sharing method using adjustment mechanisms. This analysis prepares optimal feedback tailored to the user's emotional state. The output is the improved presentation method.

[0218] Step 6:

[0219] The device visually and audibly presents the final, tailored suggestions to the user. The tailored information is delivered in a way that is appropriate to the user's situation, ensuring an effective experience.

[0220] 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.

[0221] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), 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.

[0222] 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.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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".

[0236] This invention presents an implementation of a system designed for companies to effectively formulate and evaluate cost reduction plans. The system consists of users, terminals, and a server, and operates as follows:

[0237] First, the user uses a terminal to input basic information about their company's operations and specific goals for cost reduction. This information includes industry, department, and current challenges. The terminal then sends this information to the server.

[0238] Next, the server uses generative AI to generate appropriate cost reduction hypotheses based on the received information. The generative AI creates hypotheses based on pre-programmed databases and learning models, while also considering success stories and best practices from other companies.

[0239] Based on the generated hypotheses, the terminal visually displays suggestions to the user. This display allows the user to understand specific cost reduction strategies and prepare to incorporate them into the company's strategy.

[0240] Furthermore, the server has the functionality to collect information on successful case studies from other companies, as well as available tools and services. This data collection process is performed automatically by a generating AI, and the results are displayed to the user via their device. Based on this, the user can consider effective measures.

[0241] Furthermore, for specific cost reduction proposals, the server uses AI to perform a return on investment simulation. This calculates startup costs and future cost reduction effects specifically, and displays them to the user on their terminal. Based on this evaluation, the user can decide whether or not to implement the reduction proposal.

[0242] One example of its use is when a manufacturing company utilizes this system to receive hypothetical proposals for revising its procurement process aimed at reducing material costs. In this case, the generating AI might analyze existing supply chain information and suggest more effective potential suppliers. Along with these proposals, the system provides simulation results of cost reduction effects from the server, enabling the company to make data-driven decisions.

[0243] Thus, in the embodiments of the present invention, by integrating the collection, analysis, and proposal of information, it is possible to streamline a company's cost reduction activities and increase their success rate.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] Users use a terminal to input basic information about the company's operations, as well as areas and specific goals for cost reduction. This includes industry, department name, and current challenges and resource status.

[0247] Step 2:

[0248] The terminal formats the input information, performs format conversion as necessary, and then sends the information to the server as a data packet.

[0249] Step 3:

[0250] The server analyzes the received information and invokes a generative AI. The generative AI generates hypotheses about cost reduction related to the input information, based on the database and past learning models.

[0251] Step 4:

[0252] The server converts the generated hypotheses into an internal data format, generating more detailed and usable information. This includes case study data from other companies and relevant market data.

[0253] Step 5:

[0254] The terminal receives hypotheses and accompanying information transmitted from the server and displays them visually on the user interface. The user reviews this and examines the elements that can be applied to their company's strategy.

[0255] Step 6:

[0256] Users select hypotheses and proposals that interest them and request detailed simulations. These selections are then sent back to the server via the terminal.

[0257] Step 7:

[0258] The server then uses the generated AI again to perform a return on investment simulation for the selected proposal. This process calculates the initial investment amount, estimated cost savings, implementation period, and other factors.

[0259] Step 8:

[0260] The server compiles the simulation results and sends this information to the terminal in the form of specific numerical data and graphs.

[0261] Step 9:

[0262] The terminal displays the simulation results on the user interface, allowing the user to consider the feasibility of implementing cost reduction proposals. The user then makes a decision based on this information.

[0263] Through the steps outlined above, this system enables an efficient planning and evaluation process for cost reduction within a company.

[0264] (Example 1)

[0265] 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."

[0266] In today's business environment, companies are required to improve operational efficiency while simultaneously reducing costs. Traditional methods require significant time and effort to develop improvement plans, and they often fail to utilize successful case studies from other companies or the latest tools. This creates a challenge in that optimal cost-reduction measures may be overlooked.

[0267] 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.

[0268] In this invention, the server includes an input means that works in conjunction with a device for inputting information to record basic business data and cost reduction targets, a communication means that transmits the input data to a central processing unit, and a generation means that uses an automatic generation device within the central processing unit to construct multiple hypotheses based on the input data. This enables companies to quickly formulate specific and data-driven cost reduction measures and to utilize successful case studies from other companies and the latest tools.

[0269] "Input means" refers to a device or interface for recording basic business data and cost reduction targets.

[0270] "Communication means" refers to the technologies that constitute protocols and devices for transmitting input data to a central processing unit.

[0271] "Generation means" refers to a function within the central processing unit that uses an automatic generation device to construct multiple hypotheses based on input data.

[0272] "Display means" refers to a device or software mechanism for visually presenting a constructed hypothesis to the user.

[0273] "Information gathering methods" refer to algorithms and systems for collecting information on other people's success stories and available tools.

[0274] "Analysis methods" refer to processes or models that use automated generation devices to predict the financial effects of specific cost reduction proposals.

[0275] The embodiments for carrying out the present invention are described below.

[0276] This invention is a system aimed at enabling companies to reduce costs while improving operational efficiency. The system mainly consists of a server, terminals, and users. The server functions as a central processing unit and is responsible for major data processing and the operation of the generation AI model. The terminals receive input from users and communicate with the server.

[0277] Specifically, users input basic business-related data and cost reduction targets into a terminal. This input data is transmitted via an input device such as a PC or tablet, and is implemented through a user interface. The terminal then transmits this data to a server. This communication is carried out using protocols that utilize the internet or the company's internal network.

[0278] The server automatically generates hypotheses using a generative AI model based on the received data. This generative AI model uses pre-trained databases and algorithms to construct hypotheses while considering successful case studies and the latest best practices from other companies. This process identifies a variety of cost-reduction proposals.

[0279] Furthermore, the server uses analytical tools to predict the financial effects of the generated hypotheses. Specific analyses include comparing startup costs with expected cost savings. This allows companies to obtain detailed data for evaluating feasibility.

[0280] The generated hypotheses and their analysis results are presented visually to the user via the device. This presentation utilizes visualization techniques such as charts and graphs to facilitate data interpretation.

[0281] For example, a manufacturing company might use this system to receive suggestions for improving its procurement process to reduce material costs. In this case, the generating AI can analyze existing supply chain data and suggest more effective suppliers. Furthermore, based on the cost reduction simulation results provided by the server, companies can make data-driven decisions.

[0282] An example of a prompt would be: "Please propose effective cost reduction measures to lower material costs in our manufacturing sector. Refer to successful case studies from other companies and also indicate the expected return on investment."

[0283] The flow of the specific process in Example 1 will be described with reference to FIG. 11.

[0284] Step 1:

[0285] The user uses the terminal to input the basic data related to the company's business and the goal of cost reduction. The input is performed through the dedicated application or web interface of the terminal and includes information such as industry type, department, and current issues. This input data is directly transmitted from the terminal to the server.

[0286] Step 2:

[0287] The server analyzes the data received from the terminal. The received information is standardized through a parser that classifies each item and formatted as input data for the generated AI model. In this process, data deficiencies and outliers are checked and corrected or removed as necessary.

[0288] Step 3:

[0289] The server activates the generated AI model and creates a prompt sentence. Based on the information received from the user, the server forms an optimal prompt sentence and passes it to the generated AI. This prompt sentence includes instructions for presenting cost reduction measures, and various hypotheses are generated by the model.

[0290] Step 4:

[0291] The server evaluates the hypotheses obtained from the generated AI model. The generated hypotheses are scored from the perspectives of economic validity and feasibility using pre-defined evaluation criteria. The optimal hypothesis is selected and formatted as data for presentation to the user.

[0292] Step 5:

[0293] The terminal visually presents the best hypothesis sent from the server to the user. Using visualization tools, the details of the hypothesis and the expected cost reduction effects are displayed in graphs and text format. Based on the visual information, the user considers specific cost reduction measures.

[0294] Step 6:

[0295] The server gathers additional information and updates its hypotheses. For example, it regularly searches online resources and other companies' databases to collect new success stories and industry best practices. This information is also used as material for hypothesis formation.

[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] In recent years, improving productivity and reducing costs within organizations have become crucial management decisions. However, traditional methods make it difficult to quickly and accurately identify operational inefficiencies and formulate optimal improvement measures. In particular, utilizing operational machine data to support real-time decision-making requires considerable effort and cost. Therefore, there is a need for technology that can easily and effectively analyze the performance of operational machines and obtain optimal improvement suggestions.

[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 cooperates with a device for acquiring information, and includes a receiving means for receiving basic information related to the activities of an organization and cost reduction targets, a communication means for transmitting the received information to a processing device, a generating means for generating various hypotheses based on the received information by using a generating device in the processing device, a data analysis means for performing analysis based on data collected in conjunction with a measuring device of an operating machine, and a strategy generating means for generating operation improvement measures based on information from the measuring device. Thereby, it becomes possible to formulate efficient and effective operation improvement measures utilizing the real-time data of the operating machine.

[0301] The "receiving means" is a function that cooperates with a device for acquiring information and acquires basic information related to the activities of an organization and cost reduction targets.

[0302] The "communication means" is a function for transmitting the received information to a processing device.

[0303] The "generating means" is a function for generating various hypotheses based on the received information by using a generating device in the processing device.

[0304] The "display means" is a function for notifying a user of the generated hypothesis.

[0305] The "data analysis means" is a function for performing analysis based on data collected in conjunction with a measuring device of an operating machine.

[0306] The "strategy generating means" is a function for generating operation improvement measures based on information from the measuring device.

[0307] In an embodiment of this invention, a system for efficiently formulating operation improvement measures is included. The server cooperates with a device for acquiring information and receives basic information related to the activities of an organization and cost reduction targets. Thereby, information is collected through the receiving means. The received information is transmitted to a processing device by using the communication means, and the generating means in the processing device uses a generating AI model to generate various hypotheses based on the received information.

[0308] The generated hypotheses are notified to the user via a terminal. The display device fulfills this role, allowing the user to obtain information and receive support for decision-making. Furthermore, the server works in conjunction with the measuring devices of the operational machinery to analyze the data collected by the data analysis device. This highlights areas for improvement in operational efficiency at the site.

[0309] The strategy generation system generates operational improvement measures based on information from measurement devices. These generated improvement measures can be viewed by users via smart glasses or other devices, promoting operational efficiency. Simulation and effect prediction of the improvement measures utilize a generation AI model, and by providing concrete implementation examples, effective strategy planning becomes possible.

[0310] As a concrete example, there are cases where a large amount of sensor information is collected to identify line bottlenecks and propose rearrangement. For instance, by analyzing sensor information from a production line that frequently experiences stoppages, it might be proposed that rearrangement could improve efficiency by up to 30%. This proposal is visualized using the AR function of smart glasses, allowing line managers to understand it intuitively.

[0311] Examples of prompts for generative AI models:

[0312] We will provide the factory robot data below. Based on this data, please generate operational improvement proposals and present the simulation results of their return on investment.

[0313] Production line: Line A

[0314] Energy consumption: High

[0315] Operating hours: 24 hours

[0316] Summary: Propose ways to increase efficiency and reduce energy consumption.

[0317] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0318] Step 1:

[0319] Users input basic information related to their organization's activities and cost reduction goals using a device designed to retrieve information. This input information is transmitted to the server via the terminal. The input data here concerns the current state and goals of operations. As output, this data is stored on the server.

[0320] Step 2:

[0321] The server generates various hypotheses using a generative AI model based on the received information. In this step, the received information is input into the generative AI model, and hypothesis ideas are output. Data processing involves generating hypotheses based on success stories and best practices from other companies. As output, a list of hypothesis ideas is obtained.

[0322] Step 3:

[0323] The generated hypothetical ideas are notified to the user via the terminal's display device. The user reviews the hypothesis based on this display and makes revisions or provides feedback as needed. The input is the hypothetical idea, and the output is the user's evaluation and feedback.

[0324] Step 4:

[0325] The server works in conjunction with the measuring devices of the operational machinery to collect and analyze actual operational data. The data analysis method integrates the collected sensor data to identify operational efficiency issues. The input is actual measurement data, and the output provides points for operational improvement.

[0326] Step 5:

[0327] The server generates operational improvement measures using a strategy generation mechanism based on measurement data. In this step, it performs the data calculations necessary to generate improvement measures and outputs specific improvement measures. The input is the operational challenges, and the output is specific improvement proposals.

[0328] Step 6:

[0329] Users visually review improvement measures via their devices or smart glasses and decide whether or not to implement them. In this step, the simulation results of the generated improvement measures are displayed, providing information for decision-making. The input is the improvement measures, and the user's decision is output.

[0330] 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.

[0331] This invention presents an embodiment of a system that offers effective cost-reduction proposals and provides feedback that takes user emotions into consideration. The system mainly consists of a user, a terminal, a server, and an emotion engine.

[0332] First, the user uses a terminal to input basic company information and cost reduction objectives. This information input specifically includes details such as industry, department, challenges, and expected results. The terminal then converts this information into a format and sends it to the server.

[0333] Next, the server analyzes the received information and requests a generative AI to generate appropriate hypotheses. This generative AI utilizes existing databases and inference models, taking into account past success stories and market trends. The hypotheses generated here propose cost reduction measures that are considered effective for the user.

[0334] Next, the emotion engine collects user emotion data through the device. This is done by acquiring and analyzing information such as the user's voice, facial expressions, and input speed while they are operating the device. Based on the acquired data, the emotion engine evaluates the user's emotional state.

[0335] Subsequently, the server adjusts how hypotheses are presented based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, it provides information tailored to their emotions, such as adding more relaxing feedback. This allows suggestions and information to be presented in a way that is appropriate to the user's emotional state, improving the user experience.

[0336] The terminal receives feedback from the server and displays it to the user visually and audibly. This display includes not only detailed information on cost-saving proposals, but also emotionally responsive advice and recommendations for the next steps.

[0337] As a concrete example, consider a scenario where a product manufacturing company uses the system. If the user is aiming to optimize the selling price to customers, the system will suggest a revision of the discount algorithm. If the user is feeling anxious at this time, the emotion engine will sense this and display feedback on the terminal to help them feel more at ease with the suggestion.

[0338] Thus, this invention not only supports companies' cost reduction activities but also enables interactive and flexible information delivery that takes user emotions into consideration.

[0339] The following describes the processing flow.

[0340] Step 1:

[0341] Users use a terminal to input basic information about the company's operations and specific cost reduction objectives. This includes details such as industry, department, current challenges, and reduction targets.

[0342] Step 2:

[0343] The terminal converts the information entered by the user into digital data and sends it to the server. The transmitted data is formatted in a way that is necessary for analysis on the server.

[0344] Step 3:

[0345] The server activates a generation AI based on the received business information, and generates appropriate cost reduction hypotheses based on the input information. The generation AI takes historical data and market trends into consideration and extracts multiple hypotheses.

[0346] Step 4:

[0347] The server further organizes the generated hypotheses and prepares to send them to the terminal as a concrete action plan, including detailed information and relevant case studies.

[0348] Step 5:

[0349] The device presents the received information to the user, but at the same time, it activates an emotion engine to monitor the user's reaction. Emotional data is collected through voice input and facial recognition.

[0350] Step 6:

[0351] The emotion engine analyzes the user's emotional data to determine whether they are stressed, at ease, or interested. This information is sent to the server.

[0352] Step 7:

[0353] The server receives data from the emotion engine and generates hypothetical feedback appropriate to the user's emotional state. For example, if the user is feeling stressed, it adds softer language and reassuring information to help them relax.

[0354] Step 8:

[0355] The device redisplays feedback sent from the server to the user. This display includes visuals and audio to help the user make decisions in a relaxed environment.

[0356] Step 9:

[0357] Based on the presented cost reduction hypotheses and related information, users select appropriate actions and proceed to the next step.

[0358] The above outlines the specific processing flow of a system that integrates an emotion engine. This process allows users to make data-driven decisions while receiving emotional considerations.

[0359] (Example 2)

[0360] 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".

[0361] Traditional cost reduction systems were limited to making suggestions based on company data and were unable to provide adaptive feedback tailored to the user's emotions and circumstances. As a result, problems arose such as users experiencing stress or the suggestions not being effectively communicated.

[0362] 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.

[0363] In this invention, the server is linked to a terminal for inputting information about work content and goals, and includes an input means for inputting basic information and objectives, a generation means for analyzing the input information and generating hypotheses using a generation AI model, and an emotion adaptation means for adjusting and presenting suggestions based on the user's emotional information in conjunction with the generated hypotheses. This makes it possible to provide feedback that is appropriate to the user's emotions and to ensure that the suggested content is communicated to the user more effectively.

[0364] A "terminal" refers to a device used by users to input information and plays a role in sending and receiving data in conjunction with a system.

[0365] An "input method" is a means for users to input business information and objectives into a terminal, and it is equipped with the function to appropriately transfer that information into the system.

[0366] A "generative AI model" is an artificial intelligence model that generates hypotheses and proposals based on received information, and is an algorithm that performs inference based on a large amount of data.

[0367] A "generative means" is a means that has the function of generating hypotheses from input data using a generative AI model.

[0368] "Emotional adaptation means" refers to functions and methods for analyzing a user's emotional information, adjusting the suggested content based on the results, and presenting it in the most optimal form.

[0369] A "visualization tool" is a means of visually displaying feedback information adapted to generated hypotheses and emotions to the user, and is a device that has the function of conveying information in an easy-to-understand manner through a user interface.

[0370] This invention is an embodiment of a system that effectively proposes cost reductions for companies and provides feedback that takes user emotions into consideration.

[0371] Specifically, users first input company business information using a terminal. The terminal is a computer device equipped with a dedicated interface for inputting information such as industry, department, tasks, and expected results. User input is converted into data format in real time and sent to the server.

[0372] Next, the server analyzes the received data. Here, a generative AI model is used to create prompt statements and generate the optimal hypothesis while referring to the database and inference algorithms. This generative AI model refers to an algorithm that runs in a software environment such as Python or TensorFlow.

[0373] Subsequently, the emotion engine collects user emotion data through the device. This involves analyzing facial expressions, voice tone, and input speed during operation using cameras, microphones, sensors, etc. This includes a means of quantifying the user's emotional state from this information.

[0374] Finally, the server adaptively adjusts the presentation method of the generated hypotheses based on emotional information. As the central device of the system, the server generates feedback that corresponds to the user's emotions and sends it to the terminal. The terminal displays this feedback to the user using visualization means.

[0375] A concrete example of this system could be a product manufacturing company. When a user aims to optimize the selling price to their customers, the system may suggest a revision of the discount algorithm. At the same time, if the emotion engine detects that the user is feeling stressed, feedback to promote a sense of security will be displayed on the screen.

[0376] An example of a prompt message provided to the generating AI might be: "Please propose an effective discount strategy for optimizing customer pricing in product manufacturing. Also, please consider methods for providing feedback that respond to user emotions."

[0377] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0378] Step 1:

[0379] Users input business information and cost reduction objectives using a terminal. Specifically, they enter their industry, department, challenges, and expected results into a dedicated input form. The entered data is structured within the terminal and formatted for subsequent processing. A formatted data object is generated as the output of the input.

[0380] Step 2:

[0381] The terminal sends the formatted data to the server. The communication module within the terminal packets the data and sends it to the server using a secure communication protocol. The server re-analyzes the received data and stores it in an internal data structure for analysis. Based on the data received as input, a dataset for analysis is output.

[0382] Step 3:

[0383] The server generates hypotheses using a generative AI model. It creates prompt statements as input and sends them to the generative AI. Here, the inference algorithm runs using libraries such as Python and TensorFlow. Based on historical data and marketing trends, the model outputs new cost reduction proposals. The generated hypotheses are output as hypothesis data.

[0384] Step 4:

[0385] The device collects emotional data based on the user's actions. Specifically, it uses a camera and microphone to record facial expressions and voice, and sensors to measure input speed and pressure. The obtained data is analyzed in real time by an emotion engine and output as a numerical value indicating the user's emotional state.

[0386] Step 5:

[0387] The server receives evaluation results from the emotion engine and adjusts how hypotheses are presented. It receives emotion evaluation scores as input and adjusts the wording of prompts and output hypotheses. If necessary, it uses the regenerative AI model to generate new feedback and outputs suggestions in an adaptive and optimal format.

[0388] Step 6:

[0389] The device displays tailored feedback to the user. In addition to presenting visual information on the display, it guides the user through suggestions via audio output. The user can confirm information visually and aurally, and receive guidance to select the next action. The output includes visually and audibly generated feedback.

[0390] (Application Example 2)

[0391] 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."

[0392] When companies seek to reduce costs, they need not only to propose various hypotheses but also to respond flexibly, taking into account the emotional state of users, in order to make effective proposals. Similarly, in physical stores, providing information based on the customer's emotional state is necessary to make effective sales proposals that meet customer needs. Conventional systems lack the ability to optimize proposals using this kind of emotional data.

[0393] 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.

[0394] In this invention, the server includes input means linked to electronic devices for supplying information, information transmission means for transmitting information to data processing equipment, generation means for generating various hypotheses using a hypothesis generation device, emotion evaluation means for acquiring emotion data, and adjustment means for adjusting the method of presenting hypotheses. This enables flexible and effective cost reduction and sales proposals that respond to the user's emotions.

[0395] "Electronic devices for supplying information" refers to devices used by users to input basic information about a company's business and to achieve cost reduction objectives.

[0396] An "input method" is a device that allows users to supply information via electronic devices and incorporate it into the system.

[0397] The "information transmission means" refers to the part responsible for transmitting the input information to a data processing device.

[0398] "Data processing equipment" refers to the primary equipment used to generate hypotheses based on supplied information and to perform various processing tasks.

[0399] A "hypothesis generation device" is a device used within a data processing device to generate various hypotheses based on supplied information.

[0400] "Generative means" refers to the function of constructing diverse hypotheses using a hypothesis generation device.

[0401] "Visualization means" refers to a function that provides users with a visual representation of the generated hypotheses.

[0402] "Emotional evaluation means" refers to a function that acquires user emotional data and analyzes that state.

[0403] "Adjustment mechanisms" refer to functions for optimizing the method and content of hypothesis presentation based on acquired emotional data.

[0404] In this embodiment of the invention, the system primarily uses an "electronic device for supplying information," a "data processing device," and a "sentiment evaluation means." First, the user inputs basic company information and cost reduction objectives using the electronic device for supplying information. This activates the input means, and the input information is transmitted to the data processing device via the information transmission means.

[0405] Next, the data processing equipment uses a hypothesis generation device to generate various hypotheses based on the supplied information. The hypothesis generation device constructs hypotheses by utilizing prompts to existing databases and generation AI models. In this process, the generation means handles the process, and the generated hypotheses are visually presented to the user through a visualization means.

[0406] Furthermore, an emotion assessment system is activated to acquire and analyze emotional data from the user's voice and facial expressions, thereby evaluating the user's emotional state. This emotional data influences the way hypotheses are presented through adjustment mechanisms. For example, if the user is experiencing stress, the presentation method is flexibly adjusted to provide feedback that enhances relaxation.

[0407] As a concrete example, a product manufacturing company might use the system to optimize its sales strategy to customers. The user inputs a pricing strategy for a specific product, and a hypothesis generator suggests a revised discount algorithm. In this process, an emotion evaluation system senses the user's reaction, and an adjustment system selects a more relaxed suggestion method.

[0408] An example of a prompt to a generative AI model is: "This customer is looking for a new washing machine with a budget of approximately 50,000 yen. Please present options that offer the best cost performance under those conditions." This invention enables the presentation of appropriate information that takes user sentiment into account, as well as more reliable cost-saving proposals.

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] Users input basic company information and cost reduction objectives using electronic devices to supply information. The entered data includes information such as business areas, departments, challenges, and expected outcomes. This data is collected by the input means and transmitted to data processing equipment via the information transmission means.

[0412] Step 2:

[0413] The server acts as a data processing device, analyzing received information using a hypothesis generation device. Based on the information input, it generates prompt sentences using a generative AI model and queries the generative AI model. The hypothesis generation device considers past successes and market trends to generate a variety of hypotheses. As output, it provides a list of multiple possible hypotheses.

[0414] Step 3:

[0415] The server uses visualization tools to visually present the generated hypotheses to the user. The output data is displayed graphically on the user's electronic device, providing detailed information on the proposed cost reduction measures.

[0416] Step 4:

[0417] While the user operates the system through the terminal, the emotion evaluation system operates, acquiring emotion data based on the user's voice and facial expressions. The input data includes voice tone and emotion patterns obtained using facial recognition technology.

[0418] Step 5:

[0419] The server analyzes emotional data and modifies the generated hypothesis sharing method using adjustment mechanisms. This analysis prepares optimal feedback tailored to the user's emotional state. The output is the improved presentation method.

[0420] Step 6:

[0421] The device visually and audibly presents the final, tailored suggestions to the user. The tailored information is delivered in a way that is appropriate to the user's situation, ensuring an effective experience.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] [Third Embodiment]

[0426] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0427] 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.

[0428] 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).

[0429] 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.

[0430] 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.

[0431] 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).

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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".

[0438] This invention presents an implementation of a system designed for companies to effectively formulate and evaluate cost reduction plans. The system consists of users, terminals, and a server, and operates as follows:

[0439] First, the user uses a terminal to input basic information about their company's operations and specific goals for cost reduction. This information includes industry, department, and current challenges. The terminal then sends this information to the server.

[0440] Next, the server uses generative AI to generate appropriate cost reduction hypotheses based on the received information. The generative AI creates hypotheses based on pre-programmed databases and learning models, while also considering success stories and best practices from other companies.

[0441] Based on the generated hypotheses, the terminal visually displays suggestions to the user. This display allows the user to understand specific cost reduction strategies and prepare to incorporate them into the company's strategy.

[0442] Furthermore, the server has the functionality to collect information on successful case studies from other companies, as well as available tools and services. This data collection process is performed automatically by a generating AI, and the results are displayed to the user via their device. Based on this, the user can consider effective measures.

[0443] Furthermore, for specific cost reduction proposals, the server uses AI to perform a return on investment simulation. This calculates startup costs and future cost reduction effects specifically, and displays them to the user on their terminal. Based on this evaluation, the user can decide whether or not to implement the reduction proposal.

[0444] One example of its use is when a manufacturing company utilizes this system to receive hypothetical proposals for revising its procurement process aimed at reducing material costs. In this case, the generating AI might analyze existing supply chain information and suggest more effective potential suppliers. Along with these proposals, the system provides simulation results of cost reduction effects from the server, enabling the company to make data-driven decisions.

[0445] Thus, in the embodiments of the present invention, by integrating the collection, analysis, and proposal of information, it is possible to streamline a company's cost reduction activities and increase their success rate.

[0446] The following describes the processing flow.

[0447] Step 1:

[0448] Users use a terminal to input basic information about the company's operations, as well as areas and specific goals for cost reduction. This includes industry, department name, and current challenges and resource status.

[0449] Step 2:

[0450] The terminal formats the input information, performs format conversion as necessary, and then sends the information to the server as a data packet.

[0451] Step 3:

[0452] The server analyzes the received information and invokes a generative AI. The generative AI generates hypotheses about cost reduction related to the input information, based on the database and past learning models.

[0453] Step 4:

[0454] The server converts the generated hypotheses into an internal data format, generating more detailed and usable information. This includes case study data from other companies and relevant market data.

[0455] Step 5:

[0456] The terminal receives hypotheses and accompanying information transmitted from the server and displays them visually on the user interface. The user reviews this and examines the elements that can be applied to their company's strategy.

[0457] Step 6:

[0458] Users select hypotheses and proposals that interest them and request detailed simulations. These selections are then sent back to the server via the terminal.

[0459] Step 7:

[0460] The server then uses the generated AI again to perform a return on investment simulation for the selected proposal. This process calculates the initial investment amount, estimated cost savings, implementation period, and other factors.

[0461] Step 8:

[0462] The server compiles the simulation results and sends this information to the terminal in the form of specific numerical data and graphs.

[0463] Step 9:

[0464] The terminal displays the simulation results on the user interface, allowing the user to consider the feasibility of implementing cost reduction proposals. The user then makes a decision based on this information.

[0465] Through the steps outlined above, this system enables an efficient planning and evaluation process for cost reduction within a company.

[0466] (Example 1)

[0467] 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."

[0468] In today's business environment, companies are required to improve operational efficiency while simultaneously reducing costs. Traditional methods require significant time and effort to develop improvement plans, and they often fail to utilize successful case studies from other companies or the latest tools. This creates a challenge in that optimal cost-reduction measures may be overlooked.

[0469] 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.

[0470] In this invention, the server includes an input means that works in conjunction with a device for inputting information to record basic business data and cost reduction targets, a communication means that transmits the input data to a central processing unit, and a generation means that uses an automatic generation device within the central processing unit to construct multiple hypotheses based on the input data. This enables companies to quickly formulate specific and data-driven cost reduction measures and to utilize successful case studies from other companies and the latest tools.

[0471] "Input means" refers to a device or interface for recording basic business data and cost reduction targets.

[0472] "Communication means" refers to the technologies that constitute protocols and devices for transmitting input data to a central processing unit.

[0473] "Generation means" refers to a function within the central processing unit that uses an automatic generation device to construct multiple hypotheses based on input data.

[0474] "Display means" refers to a device or software mechanism for visually presenting a constructed hypothesis to the user.

[0475] "Information gathering methods" refer to algorithms and systems for collecting information on other people's success stories and available tools.

[0476] "Analysis methods" refer to processes or models that use automated generation devices to predict the financial effects of specific cost reduction proposals.

[0477] The embodiments for carrying out the present invention are described below.

[0478] This invention is a system aimed at enabling companies to reduce costs while improving operational efficiency. The system mainly consists of a server, terminals, and users. The server functions as a central processing unit and is responsible for major data processing and the operation of the generation AI model. The terminals receive input from users and communicate with the server.

[0479] Specifically, users input basic business-related data and cost reduction targets into a terminal. This input data is transmitted via an input device such as a PC or tablet, and is implemented through a user interface. The terminal then transmits this data to a server. This communication is carried out using protocols that utilize the internet or the company's internal network.

[0480] The server automatically generates hypotheses using a generative AI model based on the received data. This generative AI model uses pre-trained databases and algorithms to construct hypotheses while considering successful case studies and the latest best practices from other companies. This process identifies a variety of cost-reduction proposals.

[0481] Furthermore, the server uses analytical tools to predict the financial effects of the generated hypotheses. Specific analyses include comparing startup costs with expected cost savings. This allows companies to obtain detailed data for evaluating feasibility.

[0482] The generated hypotheses and their analysis results are presented visually to the user via the device. This presentation utilizes visualization techniques such as charts and graphs to facilitate data interpretation.

[0483] For example, a manufacturing company might use this system to receive suggestions for improving its procurement process to reduce material costs. In this case, the generating AI can analyze existing supply chain data and suggest more effective suppliers. Furthermore, based on the cost reduction simulation results provided by the server, companies can make data-driven decisions.

[0484] An example of a prompt would be: "Please propose effective cost reduction measures to lower material costs in our manufacturing sector. Refer to successful case studies from other companies and also indicate the expected return on investment."

[0485] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0486] Step 1:

[0487] Users use a terminal to input basic data about their company's operations and cost reduction targets. This input is done through a dedicated application on the terminal or a web interface, and includes information such as industry, department, and current challenges. This input data is then transmitted directly from the terminal to the server.

[0488] Step 2:

[0489] The server analyzes the data received from the terminal. The received information is standardized through a parser that classifies each item and formatted as input data for the generated AI model. During this process, missing or outlier data is checked and corrected or removed as necessary.

[0490] Step 3:

[0491] The server activates a generative AI model and generates prompt messages. Based on the information received from the user, the server forms the optimal prompt message and passes it to the generative AI. This prompt message includes instructions for suggesting cost reduction measures, and the model generates a variety of hypotheses.

[0492] Step 4:

[0493] The server evaluates the hypotheses generated by the AI ​​model. The generated hypotheses are scored using predefined evaluation criteria, focusing on economic validity and feasibility. The optimal hypothesis is selected and formatted as data to be presented to the user.

[0494] Step 5:

[0495] The terminal visually presents the best hypothesis sent from the server to the user. Using visualization tools, the details of the hypothesis and the expected cost reduction effects are displayed in graphs and text format. Based on the visual information, the user considers specific cost reduction measures.

[0496] Step 6:

[0497] The server gathers additional information and updates its hypotheses. For example, it regularly searches online resources and other companies' databases to collect new success stories and industry best practices. This information is also used as material for hypothesis formation.

[0498] (Application Example 1)

[0499] 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."

[0500] In recent years, improving productivity and reducing costs within organizations have become crucial management decisions. However, traditional methods make it difficult to quickly and accurately identify operational inefficiencies and formulate optimal improvement measures. In particular, utilizing operational machine data to support real-time decision-making requires considerable effort and cost. Therefore, there is a need for technology that can easily and effectively analyze the performance of operational machines and obtain optimal improvement suggestions.

[0501] 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.

[0502] In this invention, the server includes a receiving means that cooperates with a device for acquiring information and inputs basic information related to the organization's activities and cost reduction targets; a communication means that transmits the received information to a processing unit; a generation means that uses a generation device within the processing unit to generate various hypotheses based on the received information; a data analysis means that works in conjunction with a measuring device of the operational machine to perform analysis based on the collected data; and a strategy generation means that generates operational improvement measures based on information from the measuring device. This makes it possible to formulate efficient and effective operational improvement measures that utilize real-time data from the operational machine.

[0503] "Receiving means" refers to a function that works in conjunction with devices for acquiring information to obtain basic information related to the organization's activities and cost reduction targets.

[0504] "Communication means" refers to a function for transmitting received information to a processing unit.

[0505] "Generation means" refers to a function that uses a generation device within the processing unit to generate various hypotheses based on received information.

[0506] "Display means" refers to a function for notifying users of the generated hypothesis.

[0507] A "data analysis means" is a function that works in conjunction with the measuring devices of the operating machine to perform analysis based on the collected data.

[0508] A "strategy generation tool" is a function that generates operational improvement measures based on information from measuring devices.

[0509] Embodiments of this invention include a system for efficiently formulating operational improvement measures. A server, in cooperation with a device for acquiring information, receives basic information and cost reduction targets related to the organization's activities. Information is then collected through the receiving means. The received information is transmitted to a processing unit using a communication means, and a generation means within the processing unit uses a generation AI model to generate various hypotheses based on the received information.

[0510] The generated hypotheses are notified to the user via a terminal. The display device fulfills this role, allowing the user to obtain information and receive support for decision-making. Furthermore, the server works in conjunction with the measuring devices of the operational machinery to analyze the data collected by the data analysis device. This highlights areas for improvement in operational efficiency at the site.

[0511] The strategy generation system generates operational improvement measures based on information from measurement devices. These generated improvement measures can be viewed by users via smart glasses or other devices, promoting operational efficiency. Simulation and effect prediction of the improvement measures utilize a generation AI model, and by providing concrete implementation examples, effective strategy planning becomes possible.

[0512] As a concrete example, there are cases where a large amount of sensor information is collected to identify line bottlenecks and propose rearrangement. For instance, by analyzing sensor information from a production line that frequently experiences stoppages, it might be proposed that rearrangement could improve efficiency by up to 30%. This proposal is visualized using the AR function of smart glasses, allowing line managers to understand it intuitively.

[0513] Examples of prompts for generative AI models:

[0514] We will provide the factory robot data below. Based on this data, please generate operational improvement proposals and present the simulation results of their return on investment.

[0515] Production line: Line A

[0516] Energy consumption: High

[0517] Operating hours: 24 hours

[0518] Summary: Propose ways to increase efficiency and reduce energy consumption.

[0519] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0520] Step 1:

[0521] Users input basic information related to their organization's activities and cost reduction goals using a device designed to retrieve information. This input information is transmitted to the server via the terminal. The input data here concerns the current state and goals of operations. As output, this data is stored on the server.

[0522] Step 2:

[0523] The server generates various hypotheses using a generative AI model based on the received information. In this step, the received information is input into the generative AI model, and hypothesis ideas are output. Data processing involves generating hypotheses based on success stories and best practices from other companies. As output, a list of hypothesis ideas is obtained.

[0524] Step 3:

[0525] The generated hypothetical ideas are notified to the user via the terminal's display device. The user reviews the hypothesis based on this display and makes revisions or provides feedback as needed. The input is the hypothetical idea, and the output is the user's evaluation and feedback.

[0526] Step 4:

[0527] The server works in conjunction with the measuring devices of the operational machinery to collect and analyze actual operational data. The data analysis method integrates the collected sensor data to identify operational efficiency issues. The input is actual measurement data, and the output provides points for operational improvement.

[0528] Step 5:

[0529] The server generates operational improvement measures using a strategy generation mechanism based on measurement data. In this step, it performs the data calculations necessary to generate improvement measures and outputs specific improvement measures. The input is the operational challenges, and the output is specific improvement proposals.

[0530] Step 6:

[0531] Users visually review improvement measures via their devices or smart glasses and decide whether or not to implement them. In this step, the simulation results of the generated improvement measures are displayed, providing information for decision-making. The input is the improvement measures, and the user's decision is output.

[0532] 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.

[0533] This invention presents an embodiment of a system that offers effective cost-reduction proposals and provides feedback that takes user emotions into consideration. The system mainly consists of a user, a terminal, a server, and an emotion engine.

[0534] First, the user uses a terminal to input basic company information and cost reduction objectives. This information input specifically includes details such as industry, department, challenges, and expected results. The terminal then converts this information into a format and sends it to the server.

[0535] Next, the server analyzes the received information and requests a generative AI to generate appropriate hypotheses. This generative AI utilizes existing databases and inference models, taking into account past success stories and market trends. The hypotheses generated here propose cost reduction measures that are considered effective for the user.

[0536] Next, the emotion engine collects user emotion data through the device. This is done by acquiring and analyzing information such as the user's voice, facial expressions, and input speed while they are operating the device. Based on the acquired data, the emotion engine evaluates the user's emotional state.

[0537] Subsequently, the server adjusts how hypotheses are presented based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, it provides information tailored to their emotions, such as adding more relaxing feedback. This allows suggestions and information to be presented in a way that is appropriate to the user's emotional state, improving the user experience.

[0538] The terminal receives feedback from the server and displays it to the user visually and audibly. This display includes not only detailed information on cost-saving proposals, but also emotionally responsive advice and recommendations for the next steps.

[0539] As a concrete example, consider a scenario where a product manufacturing company uses the system. If the user is aiming to optimize the selling price to customers, the system will suggest a revision of the discount algorithm. If the user is feeling anxious at this time, the emotion engine will sense this and display feedback on the terminal to help them feel more at ease with the suggestion.

[0540] Thus, this invention not only supports companies' cost reduction activities but also enables interactive and flexible information delivery that takes user emotions into consideration.

[0541] The following describes the processing flow.

[0542] Step 1:

[0543] Users use a terminal to input basic information about the company's operations and specific cost reduction objectives. This includes details such as industry, department, current challenges, and reduction targets.

[0544] Step 2:

[0545] The terminal converts the information entered by the user into digital data and sends it to the server. The transmitted data is formatted in a way that is necessary for analysis on the server.

[0546] Step 3:

[0547] The server activates a generation AI based on the received business information, and generates appropriate cost reduction hypotheses based on the input information. The generation AI takes historical data and market trends into consideration and extracts multiple hypotheses.

[0548] Step 4:

[0549] The server further organizes the generated hypotheses and prepares to send them to the terminal as a concrete action plan, including detailed information and relevant case studies.

[0550] Step 5:

[0551] The device presents the received information to the user, but at the same time, it activates an emotion engine to monitor the user's reaction. Emotional data is collected through voice input and facial recognition.

[0552] Step 6:

[0553] The emotion engine analyzes the user's emotional data to determine whether they are stressed, at ease, or interested. This information is sent to the server.

[0554] Step 7:

[0555] The server receives data from the emotion engine and generates hypothetical feedback appropriate to the user's emotional state. For example, if the user is feeling stressed, it adds softer language and reassuring information to help them relax.

[0556] Step 8:

[0557] The device redisplays feedback sent from the server to the user. This display includes visuals and audio to help the user make decisions in a relaxed environment.

[0558] Step 9:

[0559] Based on the presented cost reduction hypotheses and related information, users select appropriate actions and proceed to the next step.

[0560] The above outlines the specific processing flow of a system that integrates an emotion engine. This process allows users to make data-driven decisions while receiving emotional considerations.

[0561] (Example 2)

[0562] 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."

[0563] Traditional cost reduction systems were limited to making suggestions based on company data and were unable to provide adaptive feedback tailored to the user's emotions and circumstances. As a result, problems arose such as users experiencing stress or the suggestions not being effectively communicated.

[0564] 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.

[0565] In this invention, the server is linked to a terminal for inputting information about work content and goals, and includes an input means for inputting basic information and objectives, a generation means for analyzing the input information and generating hypotheses using a generation AI model, and an emotion adaptation means for adjusting and presenting suggestions based on the user's emotional information in conjunction with the generated hypotheses. This makes it possible to provide feedback that is appropriate to the user's emotions and to ensure that the suggested content is communicated to the user more effectively.

[0566] A "terminal" refers to a device used by users to input information and plays a role in sending and receiving data in conjunction with a system.

[0567] An "input method" is a means for users to input business information and objectives into a terminal, and it is equipped with the function to appropriately transfer that information into the system.

[0568] A "generative AI model" is an artificial intelligence model that generates hypotheses and proposals based on received information, and is an algorithm that performs inference based on a large amount of data.

[0569] A "generative means" is a means that has the function of generating hypotheses from input data using a generative AI model.

[0570] "Emotional adaptation means" refers to functions and methods for analyzing a user's emotional information, adjusting the suggested content based on the results, and presenting it in the most optimal form.

[0571] A "visualization tool" is a means of visually displaying feedback information adapted to generated hypotheses and emotions to the user, and is a device that has the function of conveying information in an easy-to-understand manner through a user interface.

[0572] This invention is an embodiment of a system that effectively proposes cost reductions for companies and provides feedback that takes user emotions into consideration.

[0573] Specifically, users first input company business information using a terminal. The terminal is a computer device equipped with a dedicated interface for inputting information such as industry, department, tasks, and expected results. User input is converted into data format in real time and sent to the server.

[0574] Next, the server analyzes the received data. Here, a generative AI model is used to create prompt statements and generate the optimal hypothesis while referring to the database and inference algorithms. This generative AI model refers to an algorithm that runs in a software environment such as Python or TensorFlow.

[0575] Subsequently, the emotion engine collects user emotion data through the device. This involves analyzing facial expressions, voice tone, and input speed during operation using cameras, microphones, sensors, etc. This includes a means of quantifying the user's emotional state from this information.

[0576] Finally, the server adaptively adjusts the presentation method of the generated hypotheses based on emotional information. As the central device of the system, the server generates feedback that corresponds to the user's emotions and sends it to the terminal. The terminal displays this feedback to the user using visualization means.

[0577] A concrete example of this system could be a product manufacturing company. When a user aims to optimize the selling price to their customers, the system may suggest a revision of the discount algorithm. At the same time, if the emotion engine detects that the user is feeling stressed, feedback to promote a sense of security will be displayed on the screen.

[0578] An example of a prompt message provided to the generating AI might be: "Please propose an effective discount strategy for optimizing customer pricing in product manufacturing. Also, please consider methods for providing feedback that respond to user emotions."

[0579] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0580] Step 1:

[0581] Users input business information and cost reduction objectives using a terminal. Specifically, they enter their industry, department, challenges, and expected results into a dedicated input form. The entered data is structured within the terminal and formatted for subsequent processing. A formatted data object is generated as the output of the input.

[0582] Step 2:

[0583] The terminal sends the formatted data to the server. The communication module within the terminal packets the data and sends it to the server using a secure communication protocol. The server re-analyzes the received data and stores it in an internal data structure for analysis. Based on the data received as input, a dataset for analysis is output.

[0584] Step 3:

[0585] The server generates hypotheses using a generative AI model. It creates prompt statements as input and sends them to the generative AI. Here, the inference algorithm runs using libraries such as Python and TensorFlow. Based on historical data and marketing trends, the model outputs new cost reduction proposals. The generated hypotheses are output as hypothesis data.

[0586] Step 4:

[0587] The device collects emotional data based on the user's actions. Specifically, it uses a camera and microphone to record facial expressions and voice, and sensors to measure input speed and pressure. The obtained data is analyzed in real time by an emotion engine and output as a numerical value indicating the user's emotional state.

[0588] Step 5:

[0589] The server receives evaluation results from the emotion engine and adjusts how hypotheses are presented. It receives emotion evaluation scores as input and adjusts the wording of prompts and output hypotheses. If necessary, it uses the regenerative AI model to generate new feedback and outputs suggestions in an adaptive and optimal format.

[0590] Step 6:

[0591] The device displays tailored feedback to the user. In addition to presenting visual information on the display, it guides the user through suggestions via audio output. The user can confirm information visually and aurally, and receive guidance to select the next action. The output includes visually and audibly generated feedback.

[0592] (Application Example 2)

[0593] 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."

[0594] When companies seek to reduce costs, they need not only to propose various hypotheses but also to respond flexibly, taking into account the emotional state of users, in order to make effective proposals. Similarly, in physical stores, providing information based on the customer's emotional state is necessary to make effective sales proposals that meet customer needs. Conventional systems lack the ability to optimize proposals using this kind of emotional data.

[0595] 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.

[0596] In this invention, the server includes input means linked to electronic devices for supplying information, information transmission means for transmitting information to data processing equipment, generation means for generating various hypotheses using a hypothesis generation device, emotion evaluation means for acquiring emotion data, and adjustment means for adjusting the method of presenting hypotheses. This enables flexible and effective cost reduction and sales proposals that respond to the user's emotions.

[0597] "Electronic devices for supplying information" refers to devices used by users to input basic information about a company's business and to achieve cost reduction objectives.

[0598] An "input method" is a device that allows users to supply information via electronic devices and incorporate it into the system.

[0599] The "information transmission means" refers to the part responsible for transmitting the input information to a data processing device.

[0600] "Data processing equipment" refers to the primary equipment used to generate hypotheses based on supplied information and to perform various processing tasks.

[0601] A "hypothesis generation device" is a device used within a data processing device to generate various hypotheses based on supplied information.

[0602] "Generative means" refers to the function of constructing diverse hypotheses using a hypothesis generation device.

[0603] "Visualization means" refers to a function that provides users with a visual representation of the generated hypotheses.

[0604] "Emotional evaluation means" refers to a function that acquires user emotional data and analyzes that state.

[0605] "Adjustment mechanisms" refer to functions for optimizing the method and content of hypothesis presentation based on acquired emotional data.

[0606] In this embodiment of the invention, the system primarily uses an "electronic device for supplying information," a "data processing device," and a "sentiment evaluation means." First, the user inputs basic company information and cost reduction objectives using the electronic device for supplying information. This activates the input means, and the input information is transmitted to the data processing device via the information transmission means.

[0607] Next, the data processing equipment uses a hypothesis generation device to generate various hypotheses based on the supplied information. The hypothesis generation device constructs hypotheses by utilizing prompts to existing databases and generation AI models. In this process, the generation means handles the process, and the generated hypotheses are visually presented to the user through a visualization means.

[0608] Furthermore, an emotion assessment system is activated to acquire and analyze emotional data from the user's voice and facial expressions, thereby evaluating the user's emotional state. This emotional data influences the way hypotheses are presented through adjustment mechanisms. For example, if the user is experiencing stress, the presentation method is flexibly adjusted to provide feedback that enhances relaxation.

[0609] As a concrete example, a product manufacturing company might use the system to optimize its sales strategy to customers. The user inputs a pricing strategy for a specific product, and a hypothesis generator suggests a revised discount algorithm. In this process, an emotion evaluation system senses the user's reaction, and an adjustment system selects a more relaxed suggestion method.

[0610] An example of a prompt to a generative AI model is: "This customer is looking for a new washing machine with a budget of approximately 50,000 yen. Please present options that offer the best cost performance under those conditions." This invention enables the presentation of appropriate information that takes user sentiment into account, as well as more reliable cost-saving proposals.

[0611] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0612] Step 1:

[0613] Users input basic company information and cost reduction objectives using electronic devices to supply information. The entered data includes information such as business areas, departments, challenges, and expected outcomes. This data is collected by the input means and transmitted to data processing equipment via the information transmission means.

[0614] Step 2:

[0615] The server acts as a data processing device, analyzing received information using a hypothesis generation device. Based on the information input, it generates prompt sentences using a generative AI model and queries the generative AI model. The hypothesis generation device considers past successes and market trends to generate a variety of hypotheses. As output, it provides a list of multiple possible hypotheses.

[0616] Step 3:

[0617] The server uses visualization tools to visually present the generated hypotheses to the user. The output data is displayed graphically on the user's electronic device, providing detailed information on the proposed cost reduction measures.

[0618] Step 4:

[0619] While the user operates the system through the terminal, the emotion evaluation system operates, acquiring emotion data based on the user's voice and facial expressions. The input data includes voice tone and emotion patterns obtained using facial recognition technology.

[0620] Step 5:

[0621] The server analyzes emotional data and modifies the generated hypothesis sharing method using adjustment mechanisms. This analysis prepares optimal feedback tailored to the user's emotional state. The output is the improved presentation method.

[0622] Step 6:

[0623] The device visually and audibly presents the final, tailored suggestions to the user. The tailored information is delivered in a way that is appropriate to the user's situation, ensuring an effective experience.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] [Fourth Embodiment]

[0628] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0629] 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.

[0630] 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).

[0631] 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.

[0632] 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.

[0633] 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).

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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".

[0641] This invention presents an implementation of a system designed for companies to effectively formulate and evaluate cost reduction plans. The system consists of users, terminals, and a server, and operates as follows:

[0642] First, the user uses a terminal to input basic information about their company's operations and specific goals for cost reduction. This information includes industry, department, and current challenges. The terminal then sends this information to the server.

[0643] Next, the server uses generative AI to generate appropriate cost reduction hypotheses based on the received information. The generative AI creates hypotheses based on pre-programmed databases and learning models, while also considering success stories and best practices from other companies.

[0644] Based on the generated hypotheses, the terminal visually displays suggestions to the user. This display allows the user to understand specific cost reduction strategies and prepare to incorporate them into the company's strategy.

[0645] Furthermore, the server has the functionality to collect information on successful case studies from other companies, as well as available tools and services. This data collection process is performed automatically by a generating AI, and the results are displayed to the user via their device. Based on this, the user can consider effective measures.

[0646] Furthermore, for specific cost reduction proposals, the server uses AI to perform a return on investment simulation. This calculates startup costs and future cost reduction effects specifically, and displays them to the user on their terminal. Based on this evaluation, the user can decide whether or not to implement the reduction proposal.

[0647] One example of its use is when a manufacturing company utilizes this system to receive hypothetical proposals for revising its procurement process aimed at reducing material costs. In this case, the generating AI might analyze existing supply chain information and suggest more effective potential suppliers. Along with these proposals, the system provides simulation results of cost reduction effects from the server, enabling the company to make data-driven decisions.

[0648] Thus, in the embodiments of the present invention, by integrating the collection, analysis, and proposal of information, it is possible to streamline a company's cost reduction activities and increase their success rate.

[0649] The following describes the processing flow.

[0650] Step 1:

[0651] Users use a terminal to input basic information about the company's operations, as well as areas and specific goals for cost reduction. This includes industry, department name, and current challenges and resource status.

[0652] Step 2:

[0653] The terminal formats the input information, performs format conversion as necessary, and then sends the information to the server as a data packet.

[0654] Step 3:

[0655] The server analyzes the received information and invokes a generative AI. The generative AI generates hypotheses about cost reduction related to the input information, based on the database and past learning models.

[0656] Step 4:

[0657] The server converts the generated hypotheses into an internal data format, generating more detailed and usable information. This includes case study data from other companies and relevant market data.

[0658] Step 5:

[0659] The terminal receives hypotheses and accompanying information transmitted from the server and displays them visually on the user interface. The user reviews this and examines the elements that can be applied to their company's strategy.

[0660] Step 6:

[0661] Users select hypotheses and proposals that interest them and request detailed simulations. These selections are then sent back to the server via the terminal.

[0662] Step 7:

[0663] The server then uses the generated AI again to perform a return on investment simulation for the selected proposal. This process calculates the initial investment amount, estimated cost savings, implementation period, and other factors.

[0664] Step 8:

[0665] The server compiles the simulation results and sends this information to the terminal in the form of specific numerical data and graphs.

[0666] Step 9:

[0667] The terminal displays the simulation results on the user interface, allowing the user to consider the feasibility of implementing cost reduction proposals. The user then makes a decision based on this information.

[0668] Through the steps outlined above, this system enables an efficient planning and evaluation process for cost reduction within a company.

[0669] (Example 1)

[0670] 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".

[0671] In today's business environment, companies are required to improve operational efficiency while simultaneously reducing costs. Traditional methods require significant time and effort to develop improvement plans, and they often fail to utilize successful case studies from other companies or the latest tools. This creates a challenge in that optimal cost-reduction measures may be overlooked.

[0672] 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.

[0673] In this invention, the server includes an input means that works in conjunction with a device for inputting information to record basic business data and cost reduction targets, a communication means that transmits the input data to a central processing unit, and a generation means that uses an automatic generation device within the central processing unit to construct multiple hypotheses based on the input data. This enables companies to quickly formulate specific and data-driven cost reduction measures and to utilize successful case studies from other companies and the latest tools.

[0674] "Input means" refers to a device or interface for recording basic business data and cost reduction targets.

[0675] "Communication means" refers to the technologies that constitute protocols and devices for transmitting input data to a central processing unit.

[0676] "Generation means" refers to a function within the central processing unit that uses an automatic generation device to construct multiple hypotheses based on input data.

[0677] "Display means" refers to a device or software mechanism for visually presenting a constructed hypothesis to the user.

[0678] "Information gathering methods" refer to algorithms and systems for collecting information on other people's success stories and available tools.

[0679] "Analysis methods" refer to processes or models that use automated generation devices to predict the financial effects of specific cost reduction proposals.

[0680] The embodiments for carrying out the present invention are described below.

[0681] This invention is a system aimed at enabling companies to reduce costs while improving operational efficiency. The system mainly consists of a server, terminals, and users. The server functions as a central processing unit and is responsible for major data processing and the operation of the generation AI model. The terminals receive input from users and communicate with the server.

[0682] Specifically, users input basic business-related data and cost reduction targets into a terminal. This input data is transmitted via an input device such as a PC or tablet, and is implemented through a user interface. The terminal then transmits this data to a server. This communication is carried out using protocols that utilize the internet or the company's internal network.

[0683] The server automatically generates hypotheses using a generative AI model based on the received data. This generative AI model uses pre-trained databases and algorithms to construct hypotheses while considering successful case studies and the latest best practices from other companies. This process identifies a variety of cost-reduction proposals.

[0684] Furthermore, the server uses analytical tools to predict the financial effects of the generated hypotheses. Specific analyses include comparing startup costs with expected cost savings. This allows companies to obtain detailed data for evaluating feasibility.

[0685] The generated hypotheses and their analysis results are presented visually to the user via the device. This presentation utilizes visualization techniques such as charts and graphs to facilitate data interpretation.

[0686] For example, a manufacturing company might use this system to receive suggestions for improving its procurement process to reduce material costs. In this case, the generating AI can analyze existing supply chain data and suggest more effective suppliers. Furthermore, based on the cost reduction simulation results provided by the server, companies can make data-driven decisions.

[0687] An example of a prompt would be: "Please propose effective cost reduction measures to lower material costs in our manufacturing sector. Refer to successful case studies from other companies and also indicate the expected return on investment."

[0688] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0689] Step 1:

[0690] Users use a terminal to input basic data about their company's operations and cost reduction targets. This input is done through a dedicated application on the terminal or a web interface, and includes information such as industry, department, and current challenges. This input data is then transmitted directly from the terminal to the server.

[0691] Step 2:

[0692] The server analyzes the data received from the terminal. The received information is standardized through a parser that classifies each item and formatted as input data for the generated AI model. During this process, missing or outlier data is checked and corrected or removed as necessary.

[0693] Step 3:

[0694] The server activates a generative AI model and generates prompt messages. Based on the information received from the user, the server forms the optimal prompt message and passes it to the generative AI. This prompt message includes instructions for suggesting cost reduction measures, and the model generates a variety of hypotheses.

[0695] Step 4:

[0696] The server evaluates the hypotheses generated by the AI ​​model. The generated hypotheses are scored using predefined evaluation criteria, focusing on economic validity and feasibility. The optimal hypothesis is selected and formatted as data to be presented to the user.

[0697] Step 5:

[0698] The terminal visually presents the best hypothesis sent from the server to the user. Using visualization tools, the details of the hypothesis and the expected cost reduction effects are displayed in graphs and text format. Based on the visual information, the user considers specific cost reduction measures.

[0699] Step 6:

[0700] The server gathers additional information and updates its hypotheses. For example, it regularly searches online resources and other companies' databases to collect new success stories and industry best practices. This information is also used as material for hypothesis formation.

[0701] (Application Example 1)

[0702] 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".

[0703] In recent years, improving productivity and reducing costs within organizations have become crucial management decisions. However, traditional methods make it difficult to quickly and accurately identify operational inefficiencies and formulate optimal improvement measures. In particular, utilizing operational machine data to support real-time decision-making requires considerable effort and cost. Therefore, there is a need for technology that can easily and effectively analyze the performance of operational machines and obtain optimal improvement suggestions.

[0704] 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.

[0705] In this invention, the server includes a receiving means that cooperates with a device for acquiring information and inputs basic information related to the organization's activities and cost reduction targets; a communication means that transmits the received information to a processing unit; a generation means that uses a generation device within the processing unit to generate various hypotheses based on the received information; a data analysis means that works in conjunction with a measuring device of the operational machine to perform analysis based on the collected data; and a strategy generation means that generates operational improvement measures based on information from the measuring device. This makes it possible to formulate efficient and effective operational improvement measures that utilize real-time data from the operational machine.

[0706] "Receiving means" refers to a function that works in conjunction with devices for acquiring information to obtain basic information related to the organization's activities and cost reduction targets.

[0707] "Communication means" refers to a function for transmitting received information to a processing unit.

[0708] "Generation means" refers to a function that uses a generation device within the processing unit to generate various hypotheses based on received information.

[0709] "Display means" refers to a function for notifying users of the generated hypothesis.

[0710] A "data analysis means" is a function that works in conjunction with the measuring devices of the operating machine to perform analysis based on the collected data.

[0711] A "strategy generation tool" is a function that generates operational improvement measures based on information from measuring devices.

[0712] Embodiments of this invention include a system for efficiently formulating operational improvement measures. A server, in cooperation with a device for acquiring information, receives basic information and cost reduction targets related to the organization's activities. Information is then collected through the receiving means. The received information is transmitted to a processing unit using a communication means, and a generation means within the processing unit uses a generation AI model to generate various hypotheses based on the received information.

[0713] The generated hypotheses are notified to the user via a terminal. The display device fulfills this role, allowing the user to obtain information and receive support for decision-making. Furthermore, the server works in conjunction with the measuring devices of the operational machinery to analyze the data collected by the data analysis device. This highlights areas for improvement in operational efficiency at the site.

[0714] The strategy generation system generates operational improvement measures based on information from measurement devices. These generated improvement measures can be viewed by users via smart glasses or other devices, promoting operational efficiency. Simulation and effect prediction of the improvement measures utilize a generation AI model, and by providing concrete implementation examples, effective strategy planning becomes possible.

[0715] As a concrete example, there are cases where a large amount of sensor information is collected to identify line bottlenecks and propose rearrangement. For instance, by analyzing sensor information from a production line that frequently experiences stoppages, it might be proposed that rearrangement could improve efficiency by up to 30%. This proposal is visualized using the AR function of smart glasses, allowing line managers to understand it intuitively.

[0716] Examples of prompts for generative AI models:

[0717] We will provide the factory robot data below. Based on this data, please generate operational improvement proposals and present the simulation results of their return on investment.

[0718] Production line: Line A

[0719] Energy consumption: High

[0720] Operating hours: 24 hours

[0721] Summary: Propose ways to increase efficiency and reduce energy consumption.

[0722] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0723] Step 1:

[0724] Users input basic information related to their organization's activities and cost reduction goals using a device designed to retrieve information. This input information is transmitted to the server via the terminal. The input data here concerns the current state and goals of operations. As output, this data is stored on the server.

[0725] Step 2:

[0726] The server generates various hypotheses using a generative AI model based on the received information. In this step, the received information is input into the generative AI model, and hypothesis ideas are output. Data processing involves generating hypotheses based on success stories and best practices from other companies. As output, a list of hypothesis ideas is obtained.

[0727] Step 3:

[0728] The generated hypothetical ideas are notified to the user via the terminal's display device. The user reviews the hypothesis based on this display and makes revisions or provides feedback as needed. The input is the hypothetical idea, and the output is the user's evaluation and feedback.

[0729] Step 4:

[0730] The server works in conjunction with the measuring devices of the operational machinery to collect and analyze actual operational data. The data analysis method integrates the collected sensor data to identify operational efficiency issues. The input is actual measurement data, and the output provides points for operational improvement.

[0731] Step 5:

[0732] The server generates operational improvement measures using a strategy generation mechanism based on measurement data. In this step, it performs the data calculations necessary to generate improvement measures and outputs specific improvement measures. The input is the operational challenges, and the output is specific improvement proposals.

[0733] Step 6:

[0734] Users visually review improvement measures via their devices or smart glasses and decide whether or not to implement them. In this step, the simulation results of the generated improvement measures are displayed, providing information for decision-making. The input is the improvement measures, and the user's decision is output.

[0735] 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.

[0736] This invention presents an embodiment of a system that offers effective cost-reduction proposals and provides feedback that takes user emotions into consideration. The system mainly consists of a user, a terminal, a server, and an emotion engine.

[0737] First, the user uses a terminal to input basic company information and cost reduction objectives. This information input specifically includes details such as industry, department, challenges, and expected results. The terminal then converts this information into a format and sends it to the server.

[0738] Next, the server analyzes the received information and requests a generative AI to generate appropriate hypotheses. This generative AI utilizes existing databases and inference models, taking into account past success stories and market trends. The hypotheses generated here propose cost reduction measures that are considered effective for the user.

[0739] Next, the emotion engine collects user emotion data through the device. This is done by acquiring and analyzing information such as the user's voice, facial expressions, and input speed while they are operating the device. Based on the acquired data, the emotion engine evaluates the user's emotional state.

[0740] Subsequently, the server adjusts how hypotheses are presented based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, it provides information tailored to their emotions, such as adding more relaxing feedback. This allows suggestions and information to be presented in a way that is appropriate to the user's emotional state, improving the user experience.

[0741] The terminal receives feedback from the server and displays it to the user visually and audibly. This display includes not only detailed information on cost-saving proposals, but also emotionally responsive advice and recommendations for the next steps.

[0742] As a concrete example, consider a scenario where a product manufacturing company uses the system. If the user is aiming to optimize the selling price to customers, the system will suggest a revision of the discount algorithm. If the user is feeling anxious at this time, the emotion engine will sense this and display feedback on the terminal to help them feel more at ease with the suggestion.

[0743] Thus, this invention not only supports companies' cost reduction activities but also enables interactive and flexible information delivery that takes user emotions into consideration.

[0744] The following describes the processing flow.

[0745] Step 1:

[0746] Users use a terminal to input basic information about the company's operations and specific cost reduction objectives. This includes details such as industry, department, current challenges, and reduction targets.

[0747] Step 2:

[0748] The terminal converts the information entered by the user into digital data and sends it to the server. The transmitted data is formatted in a way that is necessary for analysis on the server.

[0749] Step 3:

[0750] The server activates a generation AI based on the received business information, and generates appropriate cost reduction hypotheses based on the input information. The generation AI takes historical data and market trends into consideration and extracts multiple hypotheses.

[0751] Step 4:

[0752] The server further organizes the generated hypotheses and prepares to send them to the terminal as a concrete action plan, including detailed information and relevant case studies.

[0753] Step 5:

[0754] The device presents the received information to the user, but at the same time, it activates an emotion engine to monitor the user's reaction. Emotional data is collected through voice input and facial recognition.

[0755] Step 6:

[0756] The emotion engine analyzes the user's emotional data to determine whether they are stressed, at ease, or interested. This information is sent to the server.

[0757] Step 7:

[0758] The server receives data from the emotion engine and generates hypothetical feedback appropriate to the user's emotional state. For example, if the user is feeling stressed, it adds softer language and reassuring information to help them relax.

[0759] Step 8:

[0760] The device redisplays feedback sent from the server to the user. This display includes visuals and audio to help the user make decisions in a relaxed environment.

[0761] Step 9:

[0762] Based on the presented cost reduction hypotheses and related information, users select appropriate actions and proceed to the next step.

[0763] The above outlines the specific processing flow of a system that integrates an emotion engine. This process allows users to make data-driven decisions while receiving emotional considerations.

[0764] (Example 2)

[0765] 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".

[0766] Traditional cost reduction systems were limited to making suggestions based on company data and were unable to provide adaptive feedback tailored to the user's emotions and circumstances. As a result, problems arose such as users experiencing stress or the suggestions not being effectively communicated.

[0767] 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.

[0768] In this invention, the server is linked to a terminal for inputting information about work content and goals, and includes an input means for inputting basic information and objectives, a generation means for analyzing the input information and generating hypotheses using a generation AI model, and an emotion adaptation means for adjusting and presenting suggestions based on the user's emotional information in conjunction with the generated hypotheses. This makes it possible to provide feedback that is appropriate to the user's emotions and to ensure that the suggested content is communicated to the user more effectively.

[0769] A "terminal" refers to a device used by users to input information and plays a role in sending and receiving data in conjunction with a system.

[0770] An "input method" is a means for users to input business information and objectives into a terminal, and it is equipped with the function to appropriately transfer that information into the system.

[0771] A "generative AI model" is an artificial intelligence model that generates hypotheses and proposals based on received information, and is an algorithm that performs inference based on a large amount of data.

[0772] A "generative means" is a means that has the function of generating hypotheses from input data using a generative AI model.

[0773] "Emotional adaptation means" refers to functions and methods for analyzing a user's emotional information, adjusting the suggested content based on the results, and presenting it in the most optimal form.

[0774] A "visualization tool" is a means of visually displaying feedback information adapted to generated hypotheses and emotions to the user, and is a device that has the function of conveying information in an easy-to-understand manner through a user interface.

[0775] This invention is an embodiment of a system that effectively proposes cost reductions for companies and provides feedback that takes user emotions into consideration.

[0776] Specifically, users first input company business information using a terminal. The terminal is a computer device equipped with a dedicated interface for inputting information such as industry, department, tasks, and expected results. User input is converted into data format in real time and sent to the server.

[0777] Next, the server analyzes the received data. Here, a generative AI model is used to create prompt statements and generate the optimal hypothesis while referring to the database and inference algorithms. This generative AI model refers to an algorithm that runs in a software environment such as Python or TensorFlow.

[0778] Subsequently, the emotion engine collects user emotion data through the device. This involves analyzing facial expressions, voice tone, and input speed during operation using cameras, microphones, sensors, etc. This includes a means of quantifying the user's emotional state from this information.

[0779] Finally, the server adaptively adjusts the presentation method of the generated hypotheses based on emotional information. As the central device of the system, the server generates feedback that corresponds to the user's emotions and sends it to the terminal. The terminal displays this feedback to the user using visualization means.

[0780] A concrete example of this system could be a product manufacturing company. When a user aims to optimize the selling price to their customers, the system may suggest a revision of the discount algorithm. At the same time, if the emotion engine detects that the user is feeling stressed, feedback to promote a sense of security will be displayed on the screen.

[0781] An example of a prompt message provided to the generating AI might be: "Please propose an effective discount strategy for optimizing customer pricing in product manufacturing. Also, please consider methods for providing feedback that respond to user emotions."

[0782] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0783] Step 1:

[0784] Users input business information and cost reduction objectives using a terminal. Specifically, they enter their industry, department, challenges, and expected results into a dedicated input form. The entered data is structured within the terminal and formatted for subsequent processing. A formatted data object is generated as the output of the input.

[0785] Step 2:

[0786] The terminal sends the formatted data to the server. The communication module within the terminal packets the data and sends it to the server using a secure communication protocol. The server re-analyzes the received data and stores it in an internal data structure for analysis. Based on the data received as input, a dataset for analysis is output.

[0787] Step 3:

[0788] The server generates hypotheses using a generative AI model. It creates prompt statements as input and sends them to the generative AI. Here, the inference algorithm runs using libraries such as Python and TensorFlow. Based on historical data and marketing trends, the model outputs new cost reduction proposals. The generated hypotheses are output as hypothesis data.

[0789] Step 4:

[0790] The device collects emotional data based on the user's actions. Specifically, it uses a camera and microphone to record facial expressions and voice, and sensors to measure input speed and pressure. The obtained data is analyzed in real time by an emotion engine and output as a numerical value indicating the user's emotional state.

[0791] Step 5:

[0792] The server receives evaluation results from the emotion engine and adjusts how hypotheses are presented. It receives emotion evaluation scores as input and adjusts the wording of prompts and output hypotheses. If necessary, it uses the regenerative AI model to generate new feedback and outputs suggestions in an adaptive and optimal format.

[0793] Step 6:

[0794] The device displays tailored feedback to the user. In addition to presenting visual information on the display, it guides the user through suggestions via audio output. The user can confirm information visually and aurally, and receive guidance to select the next action. The output includes visually and audibly generated feedback.

[0795] (Application Example 2)

[0796] 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".

[0797] When companies seek to reduce costs, they need not only to propose various hypotheses but also to respond flexibly, taking into account the emotional state of users, in order to make effective proposals. Similarly, in physical stores, providing information based on the customer's emotional state is necessary to make effective sales proposals that meet customer needs. Conventional systems lack the ability to optimize proposals using this kind of emotional data.

[0798] 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.

[0799] In this invention, the server includes input means linked to electronic devices for supplying information, information transmission means for transmitting information to data processing equipment, generation means for generating various hypotheses using a hypothesis generation device, emotion evaluation means for acquiring emotion data, and adjustment means for adjusting the method of presenting hypotheses. This enables flexible and effective cost reduction and sales proposals that respond to the user's emotions.

[0800] "Electronic devices for supplying information" refers to devices used by users to input basic information about a company's business and to achieve cost reduction objectives.

[0801] An "input method" is a device that allows users to supply information via electronic devices and incorporate it into the system.

[0802] The "information transmission means" refers to the part responsible for transmitting the input information to a data processing device.

[0803] "Data processing equipment" refers to the primary equipment used to generate hypotheses based on supplied information and to perform various processing tasks.

[0804] A "hypothesis generation device" is a device used within a data processing device to generate various hypotheses based on supplied information.

[0805] "Generative means" refers to the function of constructing diverse hypotheses using a hypothesis generation device.

[0806] "Visualization means" refers to a function that provides users with a visual representation of the generated hypotheses.

[0807] "Emotional evaluation means" refers to a function that acquires user emotional data and analyzes that state.

[0808] "Adjustment mechanisms" refer to functions for optimizing the method and content of hypothesis presentation based on acquired emotional data.

[0809] In this embodiment of the invention, the system primarily uses an "electronic device for supplying information," a "data processing device," and a "sentiment evaluation means." First, the user inputs basic company information and cost reduction objectives using the electronic device for supplying information. This activates the input means, and the input information is transmitted to the data processing device via the information transmission means.

[0810] Next, the data processing equipment uses a hypothesis generation device to generate various hypotheses based on the supplied information. The hypothesis generation device constructs hypotheses by utilizing prompts to existing databases and generation AI models. In this process, the generation means handles the process, and the generated hypotheses are visually presented to the user through a visualization means.

[0811] Furthermore, an emotion assessment system is activated to acquire and analyze emotional data from the user's voice and facial expressions, thereby evaluating the user's emotional state. This emotional data influences the way hypotheses are presented through adjustment mechanisms. For example, if the user is experiencing stress, the presentation method is flexibly adjusted to provide feedback that enhances relaxation.

[0812] As a concrete example, a product manufacturing company might use the system to optimize its sales strategy to customers. The user inputs a pricing strategy for a specific product, and a hypothesis generator suggests a revised discount algorithm. In this process, an emotion evaluation system senses the user's reaction, and an adjustment system selects a more relaxed suggestion method.

[0813] An example of a prompt to a generative AI model is: "This customer is looking for a new washing machine with a budget of approximately 50,000 yen. Please present options that offer the best cost performance under those conditions." This invention enables the presentation of appropriate information that takes user sentiment into account, as well as more reliable cost-saving proposals.

[0814] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0815] Step 1:

[0816] Users input basic company information and cost reduction objectives using electronic devices to supply information. The entered data includes information such as business areas, departments, challenges, and expected outcomes. This data is collected by the input means and transmitted to data processing equipment via the information transmission means.

[0817] Step 2:

[0818] The server acts as a data processing device, analyzing received information using a hypothesis generation device. Based on the information input, it generates prompt sentences using a generative AI model and queries the generative AI model. The hypothesis generation device considers past successes and market trends to generate a variety of hypotheses. As output, it provides a list of multiple possible hypotheses.

[0819] Step 3:

[0820] The server uses visualization tools to visually present the generated hypotheses to the user. The output data is displayed graphically on the user's electronic device, providing detailed information on the proposed cost reduction measures.

[0821] Step 4:

[0822] While the user operates the system through the terminal, the emotion evaluation system operates, acquiring emotion data based on the user's voice and facial expressions. The input data includes voice tone and emotion patterns obtained using facial recognition technology.

[0823] Step 5:

[0824] The server analyzes emotional data and modifies the generated hypothesis sharing method using adjustment mechanisms. This analysis prepares optimal feedback tailored to the user's emotional state. The output is the improved presentation method.

[0825] Step 6:

[0826] The device visually and audibly presents the final, tailored suggestions to the user. The tailored information is delivered in a way that is appropriate to the user's situation, ensuring an effective experience.

[0827] 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.

[0828] 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.

[0829] 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 robot 414.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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."

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] The following is further disclosed regarding the embodiments described above.

[0849] (Claim 1)

[0850] A receiving means that connects with a device for inputting information and inputs basic information related to a company's operations and the objectives of cost reduction,

[0851] A communication means for transmitting received information to a processing unit,

[0852] A generation means that generates various hypotheses based on received information using a generation device within the processing device,

[0853] A display means for notifying users of the generated hypothesis,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, further comprising data collection means for collecting information on other companies' practices and available services via communication means.

[0857] (Claim 3)

[0858] The system according to claim 1, further comprising a simulation means for simulating the return on investment of a specific cost reduction plan using a generation device.

[0859] "Example 1"

[0860] (Claim 1)

[0861] An input means that works in conjunction with a device for inputting information to record basic business data and cost reduction targets,

[0862] A communication means for transmitting input data to a central processing unit,

[0863] A generation means that uses an automated generation device in the central processing unit to construct multiple hypothesis structures based on input data,

[0864] A display means for visually presenting the constructed temporary structure to the user,

[0865] A system that includes this.

[0866] (Claim 2)

[0867] The system according to claim 1, further comprising an information gathering means for collecting information on other people's success stories and available tools via communication means.

[0868] (Claim 3)

[0869] The system according to claim 1, further comprising an analytical means for predicting the financial effects of a specific cost reduction plan using an automated generation device.

[0870] "Application Example 1"

[0871] (Claim 1)

[0872] A receiving means that works in conjunction with a device for acquiring information and inputs basic information related to the organization's activities and cost reduction targets,

[0873] A communication means for transmitting received information to a processing unit,

[0874] A generation means that generates various hypotheses based on received information using a generation device within the processing device,

[0875] A display means for notifying users of the generated hypothesis,

[0876] A data analysis means that works in conjunction with the measuring device of the operating machine and performs analysis based on the collected data,

[0877] A strategy generation means that generates operational improvement measures based on information from measuring devices,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, further comprising data collection means for collecting information on the cases and available services of other organizations via means of communication.

[0881] (Claim 3)

[0882] The system according to claim 1, further comprising a simulation means for simulating the return on investment of a specific cost reduction plan using a generation device.

[0883] "Example 2 of combining an emotion engine"

[0884] (Claim 1)

[0885] It connects with a terminal for inputting information about work content and goals, and provides an input method for entering basic information and objectives.

[0886] A generation method that analyzes input information and generates hypotheses using a generation AI model,

[0887] An emotional adaptation mechanism that adjusts and presents suggestions based on user emotional information in conjunction with the generated hypothesis,

[0888] A visualization means for displaying the presented hypotheses and proposals to the user,

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, further comprising means for evaluating the user's emotional state using an emotion engine and adjusting the presented content.

[0892] (Claim 3)

[0893] The system according to claim 1, further comprising a simulation means for simulating the return on investment of a submitted hypothesis using a generative AI model and visually presenting the results.

[0894] "Application example 2 when combining with an emotional engine"

[0895] (Claim 1)

[0896] An input device that connects with electronic devices for supplying information, and inputs basic information about a company's business and the objectives of cost reduction,

[0897] Information transmission means for transmitting input information to a data processing device,

[0898] A generation means that generates various hypotheses based on input information using a hypothesis generation device within a data processing device,

[0899] A visualization method for notifying users of the generated hypotheses,

[0900] A means of sentiment evaluation that acquires user sentiment data,

[0901] A means of adjusting the method of presenting hypotheses based on emotional data,

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, further comprising means for acquiring information to collect information on other companies' case studies and usable functions via a network.

[0905] (Claim 3)

[0906] The system according to claim 1, further comprising an evaluation means for simulating the efficiency of a specific cost reduction plan using a hypothesis generation device. [Explanation of Symbols]

[0907] 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 receiving means that works in conjunction with a device for acquiring information and inputs basic information related to the organization's activities and cost reduction targets, A communication means for transmitting received information to a processing unit, A generation means that generates various hypotheses based on received information using a generation device within the processing device, A display means for notifying users of the generated hypothesis, A data analysis means that works in conjunction with the measuring device of the operating machine and performs analysis based on the collected data, A strategy generation means that generates operational improvement measures based on information from measuring devices, A system that includes this.

2. The system according to claim 1, further comprising data collection means for collecting information on the cases and available services of other organizations via communication means.

3. The system according to claim 1, further comprising a simulation means for simulating the return on investment of a specific cost reduction plan using a generation device.

Images