system

Abstract

We provide the system. [Solution] Information input means and An artificial intelligence means for generating hypotheses based on the aforementioned information, A means for outputting the generated hypothesis, Means of collecting examples from others, The means for analyzing the aforementioned cases of others, Methods for simulating return on investment, A system including means for outputting the aforementioned simulation results.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of 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] Modern enterprises are increasingly in need of cost reduction, but many enterprises spend a great deal of time and resources in the process of considering cost reduction plans. Such a process has become a heavy burden on enterprises and an obstacle to realization in the face of the requirement for efficiency. In addition, there is a problem that the quality of decision-making may decrease due to insufficient collection of cases of other companies and accurate simulation of investment effects.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides a system equipped with information input means, artificial intelligence means, and hypothesis output means. This system reduces the burden on companies by efficiently generating hypotheses using artificial intelligence based on information from users and outputting those hypotheses. Furthermore, by providing means for collecting and analyzing other people's cases to provide highly relevant information in a timely manner, and by providing means for accurately simulating and outputting return on investment, the system supports corporate decision-making and enables effective cost reduction.

[0006] An "information input means" is a mechanism that collects information from the user and supplies it to the system for processing.

[0007] An "artificial intelligence tool" is a mechanism that utilizes AI technology to generate hypotheses based on input information and analyze that information.

[0008] A "provisional output means" is a mechanism for presenting the generated provisional to the user.

[0009] "Means of collecting examples from others" refers to a mechanism for collecting cost reduction examples from other companies that are relevant to the subject from external data sources.

[0010] "Means for analyzing other people's cases" refers to a mechanism for analyzing collected cases and extracting important information.

[0011] A "means for simulating return on investment" refers to a mechanism for predicting and simulating the return on investment after the implementation of a specific cost reduction plan.

[0012] A "system" is a comprehensive framework that combines the above methods to enable the consideration and implementation of efficient cost reductions. [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments 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, a 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, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a 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, and the like.

[0019] In the following embodiments, a numbered communication I / F (Interface) is an interface that includes a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[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] The present invention provides a platform for performing hypothesis generation and data analysis functions necessary for companies to effectively reduce costs. To implement the invention, users are required to input their company's basic information and cost reduction challenges into a terminal. The terminal transmits this information to a server. Upon receiving the information, the server analyzes the input data using its built-in artificial intelligence and generates optimal hypotheses.

[0035] The generated hypotheses are presented to the user through a hypothesis output mechanism. The user can select a cost reduction case study category of interest, and the selected information is transmitted to the server. The server acquires external data related to the specified category through means of collecting other people's case studies, analyzes that data, and provides the analysis results to the user. A distinctive feature of this system is its ability to accurately simulate return on investment using the collected data. When the user inputs a specific reduction plan, the server makes a prediction about that plan based on historical data and statistical models, and outputs the results to the user.

[0036] As a concrete example, consider a scenario where a user inputs information indicating they are "considering cost reduction through improved energy efficiency." In this case, the server collects past examples of successful energy efficiency improvements and analyzes that information. Simultaneously, it can perform predictive simulations to show the user the time to return on investment and the amount of cost reduction possible.

[0037] Thus, by using the system of the present invention, companies can quickly and effectively explore and implement cost reduction measures, thereby improving the quality of decision-making.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The user enters basic information and challenges related to cost reduction for their company into the terminal. The terminal then formats this information and prepares it to be sent to the server.

[0041] Step 2:

[0042] The terminal sends formatted information to the server. The server analyzes the received data, evaluates the input data using artificial intelligence, and generates hypotheses.

[0043] Step 3:

[0044] The server reconfirms the generated hypothesis and presents it to the user through a hypothesis output mechanism. The user can then conduct further investigation based on this hypothesis.

[0045] Step 4:

[0046] The user selects a category of industry case studies they are interested in using their device. The device transmits this information to the server, which then begins collecting case studies from other users.

[0047] Step 5:

[0048] The server collects other users' cases related to the specified category from external data sources. The collected data is analyzed, and important information is extracted.

[0049] Step 6:

[0050] The server provides the analysis results to the user. Based on the collected case studies, the user can evaluate the applicability to their own company.

[0051] Step 7:

[0052] The user enters detailed information about a specific cost-saving proposal into the terminal. The terminal formats this information and sends it to the server.

[0053] Step 8:

[0054] Based on the cost reduction proposals received by the server, the return on investment is simulated using artificial intelligence. This simulation includes predictions of initial investment and cost reduction effects.

[0055] Step 9:

[0056] The server provides the user with simulation results. Based on this, the user can make final decisions regarding cost reduction measures.

[0057] (Example 1)

[0058] 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."

[0059] Finding effective ways for companies to quickly reduce costs is challenging, especially when dealing with a large amount of information. Furthermore, it requires effectively utilizing industry-specific data and the success stories of others when generating hypotheses and simulating return on investment.

[0060] 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.

[0061] In this invention, the server includes artificial intelligence means for generating hypotheses based on information, means for collecting and analyzing other people's case studies, and means for simulating return on investment using past data and statistical models. This enables companies to quickly identify effective cost reduction measures and predict return on investment with high accuracy.

[0062] An "information input method" is a means for users to input basic information and data related to cost reduction into the system.

[0063] "Artificial intelligence means" refers to software technology executed by a computer to analyze input information and generate optimal hypotheses.

[0064] "Means for outputting hypotheses" refer to user interfaces and notification methods for presenting the generated hypotheses to the user.

[0065] "Means of collecting examples from others" refers to the processes and techniques for collecting success stories and useful data from external sources.

[0066] "Means of analyzing cases" refers to data processing techniques used to analyze collected cases from others and identify trends and patterns.

[0067] "Means of simulating return on investment" refers to methods or techniques for making predictions about a specific reduction plan using historical data and statistical models.

[0068] "Means for visualizing and outputting simulation results" refers to technologies for showing calculated simulation results to users in visual formats such as graphs and tables.

[0069] The embodiments for carrying out the present invention will be described below.

[0070] This system is designed to help businesses effectively reduce costs. Users use a terminal to input their company's basic information and cost-reduction challenges. Standard PCs and tablets can be used as terminals, and data entry is performed through a dedicated web browser application.

[0071] The input information is sent to the server via the internet. Upon receiving the information, the server analyzes the data using an artificial intelligence model. Here, Python machine learning libraries such as TENSORFLOW® and PyTorch are used, enabling rapid and highly accurate hypothesis generation.

[0072] The hypotheses generated by the artificial intelligence model are presented to the user through a user interface. Based on the displayed hypotheses, the user selects a category of cost reduction case study that interests them and sends the information back to the server. Based on this information, the server refers to external databases and publicly available information to collect and analyze relevant data.

[0073] The server uses the collected data to perform simulations of the return on investment for cost reduction proposals. The simulations utilize statistical tools such as R and MATLAB®, and also refer to historical data and existing models. The results are provided to the user in a visually easy-to-understand format. This allows companies to obtain information necessary for concrete return on investment periods and strategic decision-making.

[0074] For example, if a user inputs information stating that they are "considering cost reduction through improved energy efficiency," the server will collect past examples of successful energy efficiency improvements and analyze that information. It will also provide the user with prompts such as "Please tell me the details of successful examples and the expected return on investment," and based on that, it will use a generated AI model to predict the return on investment.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] Users input their company's basic information and cost reduction challenges into a terminal. Specifically, users enter company data and reduction targets into a form in a web browser and press the submit button. The input data is organized in JSON format and sent.

[0078] Step 2:

[0079] The terminal sends the entered information to the server. This transmission is performed using HTTPS, a secure communication protocol. The input data is converted into a format that is easily received by the server before being sent.

[0080] Step 3:

[0081] The server first stores the received data in a database for analysis. An artificial intelligence model using TensorFlow is employed for data analysis, classifying the input data and generating optimal hypotheses. The input data is also compared against historical database data.

[0082] Step 4:

[0083] The generated hypotheses are presented to the user via a user interface by the server. Specifically, the hypotheses are visualized in real time and displayed in the web browser. The user can review this information and select an option.

[0084] Step 5:

[0085] The user selects a cost reduction case study category of interest and sends that information back to the server from their device. The selected category information is then organized as new data and sent.

[0086] Step 6:

[0087] The server collects external data related to the specified category. It uses external databases and public APIs to retrieve the latest information. The collected data is sent to the server's analysis system.

[0088] Step 7:

[0089] The server analyzes the collected data and provides the results to the user. Libraries such as Numpy and Pandas are used for the analysis, and the resulting data is organized and visualized as statistical information.

[0090] Step 8:

[0091] To simulate the return on investment for a specific cost reduction plan, the server utilizes historical data and statistical models. The simulation results calculate the expected payback period and cost savings.

[0092] Step 9:

[0093] The server visualizes the simulation results and presents them to the user. The results are presented in graphs and tables, easily accessible to the user through a browser. This information is then used to assist the user in making decisions.

[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 modern industry, optimizing the energy consumption of machinery while effectively reducing operating costs is a critical challenge. In particular, to address these challenges, there is a need for a system that can efficiently collect and analyze operational data and propose optimal operating methods.

[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 information gathering means, knowledge processing means, and evaluation means. This enables the proposal of operational improvement methods based on usage information and consumption information of the operational machine, thereby reducing operating costs and improving energy efficiency.

[0099] "Information gathering means" refers to a function or device used to collect relevant data or information.

[0100] "Knowledge processing means" refers to artificial intelligence or data processing technology used to analyze collected information and generate hypotheses.

[0101] "Display means" refers to devices or functions that visually provide users with generated hypotheses or analysis results.

[0102] "Data processing means" refers to methods or devices used to analyze collected cases and data from others and to derive insights.

[0103] "Evaluation means" refers to a function or technology for simulating the results of input resources and evaluating their effectiveness.

[0104] "Presentation means" refers to methods or devices for displaying or communicating simulation results or analysis results to the user.

[0105] "Information input means" refers to methods or devices for users to input usage information and consumption information of operating machines.

[0106] The system of this invention begins with the user inputting information on the operation of the machine and energy consumption information from a smartphone or terminal via an information input means. The input information is transmitted to a cloud server via the internet. The server collects relevant data using an information collection means and analyzes it using a knowledge processing means. The knowledge processing means incorporates generative AI models such as TensorFlow and PyTorch.

[0107] The server generates hypotheses based on the analyzed data and simulates the resource input versus output using evaluation tools. In this process, the accuracy of the hypotheses is improved by referring to historical data and statistical models. The analysis and simulation results are visually presented on smartphones and other devices through display tools.

[0108] As a concrete example, if a factory is considering ways to improve the energy efficiency of its machinery, the server analyzes past similar cases and information from an external database using data processing tools to propose the optimal operating method. At this time, the generating AI model forms hypotheses using prompt statements such as, "Please tell me how to improve the energy efficiency of the factory robots we are using. Based on past data, please propose the most effective operating method." Through this method, the system of the present invention effectively improves the operational efficiency of the factory.

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] Users input information about the operation of their machinery and energy consumption into their smartphone's information input device. This information is organized in JSON format.

[0112] Step 2:

[0113] The device sends the entered information to the cloud server. The data is transmitted via a secure protocol and received by the server.

[0114] Step 3:

[0115] The server uses information gathering tools to collect relevant data from internal databases and external information sources. During this process, it obtains the necessary data through available APIs.

[0116] Step 4:

[0117] The server analyzes the data collected by the knowledge processing tools. Specifically, it uses a generative AI model (e.g., TensorFlow) to identify patterns in the input data and generate hypotheses based on the data. The prompt "Please tell me how to improve energy efficiency" is input to the model.

[0118] Step 5:

[0119] The server uses evaluation tools to simulate the resource input versus output based on the generated hypotheses. By comparing this with past data, it predicts the effectiveness of the proposed improvement measures.

[0120] Step 6:

[0121] The server compiles the analysis and simulation results and transmits them to the terminal via a display device. The terminal then visually presents these results to the user.

[0122] Step 7:

[0123] The user accepts and implements the proposed operational efficiency improvements. The feasibility of the proposals is reviewed, and adjustments are made as necessary.

[0124] 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.

[0125] This invention provides a system that offers advanced support to companies when they plan and implement cost reduction strategies, taking into account the emotional state of the user. The system comprises information input means, artificial intelligence means, hypothesis output means, means for collecting examples from others, means for analyzing examples, means for simulating return on investment, and an emotion engine.

[0126] The user inputs their company's challenges and desired outcomes into a terminal. After input, the terminal sends the information to a server. The server uses artificial intelligence to generate hypotheses based on the input information, industry databases, and past training data. The generated hypotheses are presented to the user through a hypothesis output device.

[0127] Furthermore, this system is equipped with an emotion engine that recognizes the user's emotions in real time. The emotion engine analyzes the user's emotions from their input data and behavior during operation, and dynamically adjusts the parameters of the hypothesis generation means based on the results. This function enables the system to propose optimal hypotheses according to the user's emotional state.

[0128] The method for collecting other people's case studies involves using external databases and publicly available information to collect relevant cases and analyze them. The emotion engine adjusts the order in which the analysis results are presented to the user based on their emotional state, providing information in a way that is most easily accepted by the user.

[0129] Furthermore, a precise simulation of the return on investment is performed for the reduction plan selected by the user. The results are then fed back to the user in an optimal format, taking into account their emotional state.

[0130] For example, consider a situation where a user is considering "cutting their marketing budget." If the system detects that the user is stressed, the emotion engine will generate a relaxing interface and prioritize presenting an easily understandable summary. This allows the user to efficiently receive information and make better decisions.

[0131] This system enables companies to develop more flexible and emotionally sensitive strategies, and to advance cost reduction processes more effectively.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The user enters their company's cost-reduction challenges and desired goals into the terminal. The terminal formats the user's input data and prepares to send it to the server.

[0135] Step 2:

[0136] The device sends formatted user information to the server. Upon receiving the information, the server uses an emotion engine to simultaneously analyze the user's emotional state.

[0137] Step 3:

[0138] The server uses artificial intelligence to generate optimal hypotheses by referencing data submitted by the user, industry databases, and past learning results. The parameters for hypothesis generation are adjusted based on the results of the emotion engine.

[0139] Step 4:

[0140] The server generates hypotheses and presents them to the user through an appropriate interface based on their emotional state. A hypothesis output mechanism is used here, and the information is displayed to the user.

[0141] Step 5:

[0142] The system selects other users' case studies based on the categories the user has shown interest in. The device sends this information to the server, which then activates a system for collecting other users' case studies to gather relevant examples.

[0143] Step 6:

[0144] The server collects other people's cases related to a specified category from external databases and publicly available information. The collected data is analyzed using methods for analyzing other people's cases.

[0145] Step 7:

[0146] The server effectively presents analysis results, taking into account the user's emotional state. The emotion engine adjusts the order in which information is presented, ensuring that the information is delivered in the format most easily accepted by the user.

[0147] Step 8:

[0148] The user selects and enters specific cost-reduction proposals on the terminal. The terminal sends the information to the server, which prepares to simulate the return on investment.

[0149] Step 9:

[0150] The server uses artificial intelligence to simulate the return on investment for the selected reduction plan. Based on the analysis results from the emotion engine, the optimal method for displaying the results is selected.

[0151] Step 10:

[0152] The simulation results are displayed on the terminal, allowing the user to make strategic decisions based on the results.

[0153] (Example 2)

[0154] 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".

[0155] When companies seek to reduce costs, they need to consider not only the effectiveness of their strategies but also the emotions of those involved. However, conventional systems often derive hypotheses without adequately considering the user's emotional state, which can lead to situations where users are reluctant to accept proposals. Furthermore, the resulting proposals and simulation results may be presented in a way that does not alleviate the user's stress or anxiety. Thus, the lack of systems that can reflect user emotions in strategic planning is a challenge.

[0156] 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.

[0157] In this invention, the server includes emotion analysis means for analyzing the user's emotional state in real time, means for adjusting the parameters of hypothesis generation means based on the emotional state, and means for dynamically adjusting the user interface according to the emotional state. This enables the generation of optimal hypotheses that take the user's emotional state into consideration and the presentation of information in an easily acceptable format.

[0158] "Information input means" refers to a device or method for users to input information regarding a company's challenges and expected outcomes.

[0159] "Artificial intelligence means" refers to a system that uses machine learning algorithms and database lookups to generate hypotheses based on input information.

[0160] "Means for outputting a hypothesis" refers to a device or method for presenting the generated hypothesis to the user.

[0161] "Means for collecting examples from others" refers to devices or methods for collecting relevant examples from external databases or publicly available information.

[0162] "Means of analyzing the cases of others" refers to a device or method that analyzes collected cases and uses the results to aid in strategic planning.

[0163] "Means for simulating return on investment" refers to a device or method for precisely evaluating the cost-effectiveness of a strategic plan selected by the user.

[0164] "Emotional analysis means" refers to a device or method that analyzes a user's emotional state in real time based on the user's input or operations.

[0165] "Means for adjusting parameters" refers to a device or method for dynamically changing settings in the hypothesis generation process based on the results of sentiment analysis.

[0166] "Means for dynamically adjusting the user interface" refers to a device or method that adjusts the display and operation of the user interface according to the emotional state.

[0167] This invention is a system for generating effective proposals while taking into account the emotional state of users when companies formulate strategies. The system mainly consists of the following elements:

[0168] Users input information about their company's challenges and expected outcomes into a terminal and send it to a server. The terminal can use a touchscreen or keyboard as a means of inputting information. The server uses artificial intelligence to generate efficient hypotheses based on the input information. The AI ​​model used here is called a generative AI model, which derives the optimal hypothesis by referring to industry databases and past training data.

[0169] Furthermore, the server uses emotion analysis tools to analyze the user's emotional state in real time from their input and actions. This makes it possible to consider emotions when generating hypotheses and adjusting the user interface. Emotion analysis is performed using natural language processing technology.

[0170] The generated hypotheses are presented to the user through a means of outputting those hypotheses. The user interface is dynamically adjusted according to the user's emotional state, and information is provided in an easily digestible format. This allows the user to receive information efficiently without experiencing stress.

[0171] A concrete example would be a user considering "reducing their marketing budget." If the server recognizes the user's stress level through emotion analysis, it will automatically generate a relaxing interface and prioritize presenting easily understandable content.

[0172] The following is an example of a prompt message to input into the generating AI model.

[0173] "Analyze the emotional state of the user, determine which data should be prioritized, and generate appropriate hypotheses."

[0174] In this way, the system can more effectively support companies in reducing costs and developing strategies.

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

[0176] Step 1:

[0177] Users input information about their company's challenges and expected outcomes into a terminal. The terminal receives the data entered using a touchscreen or keyboard. The entered information is then transmitted to a server as digital data.

[0178] Step 2:

[0179] The server generates hypotheses using artificial intelligence based on the received user data. Here, the server uses a generation AI model, referencing industry databases and historical training data. Data processing involves extracting relevant information from the input data and creating new hypotheses through machine learning algorithms. The generated hypotheses are then presented to the user in the next stage.

[0180] Step 3:

[0181] The server analyzes the user's emotional state in real time from their input data and behavior during operation using emotion analysis tools. Natural language processing techniques are used to analyze the input data's text and speech to determine the user's emotions. The results of the emotion analysis are used to adjust parameters in hypothesis generation.

[0182] Step 4:

[0183] The server dynamically adjusts the parameters for hypothesis generation based on the results obtained from sentiment analysis. This ensures that the generated hypotheses are appropriate to the user's emotional state. The adjusted hypotheses are then presented in a way that is more acceptable and easier for the user to understand.

[0184] Step 5:

[0185] The terminal displays generated hypotheses sent from the server as suggestions in the user interface. The interface design is dynamically adjusted according to the user's emotional state; for example, relaxing colors and fonts are adopted. This reduces stress and improves receptivity.

[0186] Step 6:

[0187] If necessary, the server activates methods for collecting other users' case data, gathering relevant cases from external databases and publicly available information. This case data is analyzed and presented to the user in visual or text format. Based on the sentiment analysis results, the presentation order and format are also dynamically adjusted.

[0188] Step 7:

[0189] The server performs a return on investment (ROI) simulation for the hypotheses and strategies selected by the user. Economic data analysis algorithms are used for the simulation data calculations, and the derived results are fed back to the user visually or as text via the terminal.

[0190] (Application Example 2)

[0191] 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".

[0192] In modern cities, efficiently providing public services and increasing citizen satisfaction are crucial challenges. However, conventional systems struggle to generate flexible proposals and provide information that take into account citizens' emotional states. Therefore, it is necessary to support optimized decision-making in citizen-proposed reservations and usage plans for public facilities.

[0193] 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.

[0194] In this invention, the server includes information acquisition means, machine learning means, display means, information collection means, analysis means, evaluation means, sentiment analysis means, and adaptation means. This makes it possible to analyze the emotional state of citizens in real time and customize suggestions based on the results, thereby supporting the provision of optimal public services.

[0195] "Information acquisition means" refers to a device or process for collecting user input information and using it as basic data for processing.

[0196] "Machine learning methods" refer to algorithms or techniques used to automatically generate hypotheses based on collected information.

[0197] A "display means" is an interface for visually presenting the results of analysis or simulation to the user.

[0198] "Information gathering means" refers to the process or device for collecting necessary data from external information management systems or publicly available information.

[0199] "Analysis methods" refer to techniques or processes for analyzing collected data and extracting specific insights or patterns.

[0200] "Evaluation means" refers to a device or process for simulating return on investment and other performance indicators, and for evaluating the results.

[0201] "Emotional analysis means" refers to technology or devices for recognizing and analyzing a user's emotional state from their facial expressions, voice, etc.

[0202] "Adaptive measures" refer to technologies or processes that dynamically adjust system parameters in response to emotion analysis results to provide the user with the optimal outcome.

[0203] To realize this invention, the server executes a series of programs. Information acquisition means collects suggested information related to public services from user terminals. Machine learning means generates hypotheses based on the collected information. In this process, advanced suggestions become possible by referring to the data aggregation system and past learning results.

[0204] The server analyzes emotions in real time from collected user facial expressions and voice using emotion analysis tools. The analysis results are used to dynamically adjust the parameters of the hypothesis generation tool through an adaptation tool. Specifically, it is expected that an emotion engine (e.g., Microsoft® Azure® Emotion API) will be used.

[0205] The display means visually presents hypotheses and analysis results to the user. Here, the user is supported in making appropriate decisions based on information customized according to their emotions.

[0206] The information gathering means collects relevant data using external information management systems and publicly available information, and this data is analyzed by the analysis means. The evaluation means simulates and outputs the return on investment of the proposed hypothesis.

[0207] As a concrete example, when suggesting the efficient use of public facilities, users can respond to the suggestions, and the system will customize the suggestions based on their feedback. An example of a prompt message might be, "When formulating plans for the use of public facilities proposed by citizens, please consider citizens' feelings and customize the suggestions to reduce stress."

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The terminal collects suggested information and related requests entered by the user using information acquisition means. The entered information is sent to the server and stored as basic data for hypothesis generation.

[0211] Step 2:

[0212] The server generates hypotheses using machine learning methods based on the received information. It references user input, data aggregation systems, and past learning results, and uses a generative AI model to output hypotheses suitable for the proposal.

[0213] Step 3:

[0214] The device collects the user's facial expressions and voice information and analyzes it using emotion analysis tools. The facial expressions and voice, as input data, are processed to identify the emotional state, and the result is output as the emotional state.

[0215] Step 4:

[0216] Based on the results of the emotion analysis, the server dynamically adjusts the parameters of the hypothesis generation mechanism using adaptive means. This regenerates the optimal hypothesis according to the user's emotions, and the adjusted hypothesis is output.

[0217] Step 5:

[0218] The server uses information gathering tools to collect supplementary data from external information management systems. The collected data is analyzed by analytical tools and output as insights to refine the proposed content.

[0219] Step 6:

[0220] The server simulates the return on investment of hypotheses generated using evaluation tools. Based on the generated hypotheses and supplementary data as input data, evaluation calculations are performed and the simulation results are output.

[0221] Step 7:

[0222] The terminal visually and dynamically presents the final proposal and simulation results to the user through a display device. The results are customized and displayed in a format that is easy for the user to understand.

[0223] 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.

[0224] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0225] 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.

[0226] [Second Embodiment]

[0227] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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".

[0239] The present invention provides a platform for performing hypothesis generation and data analysis functions necessary for companies to effectively reduce costs. To implement the invention, users are required to input their company's basic information and cost reduction challenges into a terminal. The terminal transmits this information to a server. Upon receiving the information, the server analyzes the input data using its built-in artificial intelligence and generates optimal hypotheses.

[0240] The generated hypotheses are presented to the user through a hypothesis output mechanism. The user can select a cost reduction case study category of interest, and the selected information is transmitted to the server. The server acquires external data related to the specified category through means of collecting other people's case studies, analyzes that data, and provides the analysis results to the user. A distinctive feature of this system is its ability to accurately simulate return on investment using the collected data. When the user inputs a specific reduction plan, the server makes a prediction about that plan based on historical data and statistical models, and outputs the results to the user.

[0241] As a concrete example, consider a scenario where a user inputs information indicating they are "considering cost reduction through improved energy efficiency." In this case, the server collects past examples of successful energy efficiency improvements and analyzes that information. Simultaneously, it can perform predictive simulations to show the user the time to return on investment and the amount of cost reduction possible.

[0242] Thus, by using the system of the present invention, companies can quickly and effectively explore and implement cost reduction measures, thereby improving the quality of decision-making.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The user enters basic information and challenges related to cost reduction for their company into the terminal. The terminal then formats this information and prepares it to be sent to the server.

[0246] Step 2:

[0247] The terminal sends formatted information to the server. The server analyzes the received data, evaluates the input data using artificial intelligence, and generates hypotheses.

[0248] Step 3:

[0249] The server reconfirms the generated hypothesis and presents it to the user through a hypothesis output mechanism. The user can then conduct further investigation based on this hypothesis.

[0250] Step 4:

[0251] The user selects a category of industry case studies they are interested in using their device. The device transmits this information to the server, which then begins collecting case studies from other users.

[0252] Step 5:

[0253] The server collects other users' cases related to the specified category from external data sources. The collected data is analyzed, and important information is extracted.

[0254] Step 6:

[0255] The server provides the analysis results to the user. Based on the collected case studies, the user can evaluate the applicability to their own company.

[0256] Step 7:

[0257] The user enters detailed information about a specific cost-saving proposal into the terminal. The terminal formats this information and sends it to the server.

[0258] Step 8:

[0259] Based on the cost reduction proposals received by the server, the return on investment is simulated using artificial intelligence. This simulation includes predictions of initial investment and cost reduction effects.

[0260] Step 9:

[0261] The server provides the user with simulation results. Based on this, the user can make final decisions regarding cost reduction measures.

[0262] (Example 1)

[0263] 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."

[0264] Finding effective ways for companies to quickly reduce costs is challenging, especially when dealing with a large amount of information. Furthermore, it requires effectively utilizing industry-specific data and the success stories of others when generating hypotheses and simulating return on investment.

[0265] 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.

[0266] In this invention, the server includes artificial intelligence means for generating hypotheses based on information, means for collecting and analyzing other people's case studies, and means for simulating return on investment using past data and statistical models. This enables companies to quickly identify effective cost reduction measures and predict return on investment with high accuracy.

[0267] An "information input method" is a means for users to input basic information and data related to cost reduction into the system.

[0268] "Artificial intelligence means" refers to software technology executed by a computer to analyze input information and generate optimal hypotheses.

[0269] "Means for outputting hypotheses" refer to user interfaces and notification methods for presenting the generated hypotheses to the user.

[0270] "Means of collecting examples from others" refers to the processes and techniques for collecting success stories and useful data from external sources.

[0271] "Means of analyzing cases" refers to data processing techniques used to analyze collected cases from others and identify trends and patterns.

[0272] "Means of simulating return on investment" refers to methods or techniques for making predictions about a specific reduction plan using historical data and statistical models.

[0273] "Means for visualizing and outputting simulation results" refers to technologies for showing calculated simulation results to users in visual formats such as graphs and tables.

[0274] The embodiments for carrying out the present invention will be described below.

[0275] This system is designed to help businesses effectively reduce costs. Users use a terminal to input their company's basic information and cost-reduction challenges. Standard PCs and tablets can be used as terminals, and data entry is performed through a dedicated web browser application.

[0276] The input information is sent to the server via the internet. Upon receiving the information, the server analyzes the data using an artificial intelligence model. Here, Python machine learning libraries such as TensorFlow and PyTorch are used, enabling rapid and highly accurate hypothesis generation.

[0277] The hypotheses generated by the artificial intelligence model are presented to the user through a user interface. Based on the displayed hypotheses, the user selects a category of cost reduction case study that interests them and sends the information back to the server. Based on this information, the server refers to external databases and publicly available information to collect and analyze relevant data.

[0278] The server uses the collected data to perform a simulation of the investment return on cost reduction plans. Statistical tools such as R language and Matlab are used in the simulation, and past data and existing models are also referenced. The results are provided to the user in a visually understandable format. This enables the enterprise to obtain information necessary for specific payback periods and strategic decision-making.

[0279] As a specific example, when the user inputs information stating that they "are considering cost reduction through energy efficiency improvement", the server collects past successful cases of energy efficiency improvement and analyzes that information. Additionally, a prompt sentence such as "Please tell me the details of the investment return assumed for the successful case" is provided to the user, and based on this, a prediction of the investment return is made using a generative AI model.

[0280] The flow of the specific process in Example 1 will be described using FIG. 11.

[0281] Step 1:

[0282] The user inputs their company's basic information and issues related to cost reduction into the terminal. As a specific operation, the user enters company data and reduction targets into the form of a web browser and presses the send button. The input data is organized in JSON format and sent.

[0283] Step 2:

[0284] The terminal sends the input information to the server. This transmission is performed using HTTPS, a secure communication protocol. The input data is converted into a format that is easy for the server to receive and then sent.

[0285] Step 3:

[0286] The server first saves the received data in a database in order to analyze it. For data analysis, an artificial intelligence model using TensorFlow is used to classify the input data and generate an optimal hypothesis. The input data is also compared with the past database.

[0287] Step 4:

[0288] The generated hypothesis is presented to the user by the server through the user interface. Specifically, the hypothesis is visualized in real time and displayed on the web browser. The user can check this information and select options.

[0289] Step 5:

[0290] The user selects the cost reduction case category of interest and resends the information from the terminal to the server. The selected category information is newly organized as data and sent.

[0291] Step 6:

[0292] The server collects external data related to the specified category. Use external databases and public APIs to obtain the latest information. The collected data is sent to the analysis system within the server.

[0293] Step 7:

[0294] The server analyzes the collected data and provides the results to the user. Libraries such as Numpy and Pandas are used for analysis, and the resulting data is organized and visualized as statistical information.

[0295] Step 8:

[0296] To simulate the investment-to-effectiveness of a specific reduction plan, the server utilizes past data and statistical models. The simulation results calculate the predicted investment payback period and cost reduction amount.

[0297] Step 9:

[0298] The server visualizes the simulation results and presents them to the user. The results are presented in graphs and tables, easily accessible to the user through a browser. This information is then used to assist the user in making decisions.

[0299] (Application Example 1)

[0300] 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."

[0301] In modern industry, optimizing the energy consumption of machinery while effectively reducing operating costs is a critical challenge. In particular, to address these challenges, there is a need for a system that can efficiently collect and analyze operational data and propose optimal operating methods.

[0302] 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.

[0303] In this invention, the server includes information gathering means, knowledge processing means, and evaluation means. This enables the proposal of operational improvement methods based on usage information and consumption information of the operational machine, thereby reducing operating costs and improving energy efficiency.

[0304] "Information gathering means" refers to a function or device used to collect relevant data or information.

[0305] "Knowledge processing means" refers to artificial intelligence or data processing technology used to analyze collected information and generate hypotheses.

[0306] "Display means" refers to devices or functions that visually provide users with generated hypotheses or analysis results.

[0307] "Data processing means" refers to a method or device used to analyze the collected cases and data of others and draw insights.

[0308] "Evaluation means" refers to a function or technology for simulating the results of input resources and evaluating their effects.

[0309] "Presentation means" refers to a method or device for displaying or transmitting the simulation results and analysis results to the user.

[0310] "Information input means" refers to a method or device for the user to input the usage information and consumption information of the operating machine.

[0311] The system of the present invention starts with the user inputting the usage information and energy consumption information of the operating machine from a smartphone or terminal through the information input means. The input information is transmitted to the cloud server via the Internet. The server collects relevant data using the information collection means and analyzes this using the knowledge processing means. The knowledge processing means incorporates generative AI models such as TensorFlow and PyTorch.

[0312] The server generates a hypothesis based on the analyzed data and simulates the input resources vs. results using the evaluation means. In this process, the accuracy of the hypothesis is enhanced by referring to past data and statistical models. The analysis results and simulation results are visually presented to the smartphone or terminal through the display means.

[0313] As a concrete example, if a factory is considering ways to improve the energy efficiency of its machinery, the server analyzes past similar cases and information from an external database using data processing tools to propose the optimal operating method. At this time, the generating AI model forms hypotheses using prompt statements such as, "Please tell me how to improve the energy efficiency of the factory robots we are using. Based on past data, please propose the most effective operating method." Through this method, the system of the present invention effectively improves the operational efficiency of the factory.

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

[0315] Step 1:

[0316] Users input information about the operation of their machinery and energy consumption into their smartphone's information input device. This information is organized in JSON format.

[0317] Step 2:

[0318] The device sends the entered information to the cloud server. The data is transmitted via a secure protocol and received by the server.

[0319] Step 3:

[0320] The server uses information gathering tools to collect relevant data from internal databases and external information sources. During this process, it obtains the necessary data through available APIs.

[0321] Step 4:

[0322] The server analyzes the data collected by the knowledge processing tools. Specifically, it uses a generative AI model (e.g., TensorFlow) to identify patterns in the input data and generate hypotheses based on the data. The prompt "Please tell me how to improve energy efficiency" is input to the model.

[0323] Step 5:

[0324] The server uses evaluation tools to simulate the resource input versus output based on the generated hypotheses. By comparing this with past data, it predicts the effectiveness of the proposed improvement measures.

[0325] Step 6:

[0326] The server compiles the analysis and simulation results and transmits them to the terminal via a display device. The terminal then visually presents these results to the user.

[0327] Step 7:

[0328] The user accepts and implements the proposed operational efficiency improvements. The feasibility of the proposals is reviewed, and adjustments are made as necessary.

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

[0330] This invention provides a system that offers advanced support to companies when they plan and implement cost reduction strategies, taking into account the emotional state of the user. The system comprises information input means, artificial intelligence means, hypothesis output means, means for collecting examples from others, means for analyzing examples, means for simulating return on investment, and an emotion engine.

[0331] The user inputs their company's challenges and desired outcomes into a terminal. After input, the terminal sends the information to a server. The server uses artificial intelligence to generate hypotheses based on the input information, industry databases, and past training data. The generated hypotheses are presented to the user through a hypothesis output device.

[0332] Furthermore, this system is equipped with an emotion engine that recognizes the user's emotions in real time. The emotion engine analyzes the user's emotions from their input data and behavior during operation, and dynamically adjusts the parameters of the hypothesis generation means based on the results. This function enables the system to propose optimal hypotheses according to the user's emotional state.

[0333] The method for collecting other people's case studies involves using external databases and publicly available information to collect relevant cases and analyze them. The emotion engine adjusts the order in which the analysis results are presented to the user based on their emotional state, providing information in a way that is most easily accepted by the user.

[0334] Furthermore, a precise simulation of the return on investment is performed for the reduction plan selected by the user. The results are then fed back to the user in an optimal format, taking into account their emotional state.

[0335] For example, consider a situation where a user is considering "cutting their marketing budget." If the system detects that the user is stressed, the emotion engine will generate a relaxing interface and prioritize presenting an easily understandable summary. This allows the user to efficiently receive information and make better decisions.

[0336] This system enables companies to develop more flexible and emotionally sensitive strategies, and to advance cost reduction processes more effectively.

[0337] The following describes the processing flow.

[0338] Step 1:

[0339] The user enters their company's cost-reduction challenges and desired goals into the terminal. The terminal formats the user's input data and prepares to send it to the server.

[0340] Step 2:

[0341] The device sends formatted user information to the server. Upon receiving the information, the server uses an emotion engine to simultaneously analyze the user's emotional state.

[0342] Step 3:

[0343] The server uses artificial intelligence to generate optimal hypotheses by referencing data submitted by the user, industry databases, and past learning results. The parameters for hypothesis generation are adjusted based on the results of the emotion engine.

[0344] Step 4:

[0345] The server generates hypotheses and presents them to the user through an appropriate interface based on their emotional state. A hypothesis output mechanism is used here, and the information is displayed to the user.

[0346] Step 5:

[0347] The system selects other users' case studies based on the categories the user has shown interest in. The device sends this information to the server, which then activates a system for collecting other users' case studies to gather relevant examples.

[0348] Step 6:

[0349] The server collects other people's cases related to a specified category from external databases and publicly available information. The collected data is analyzed using methods for analyzing other people's cases.

[0350] Step 7:

[0351] The server effectively presents analysis results, taking into account the user's emotional state. The emotion engine adjusts the order in which information is presented, ensuring that the information is delivered in the format most easily accepted by the user.

[0352] Step 8:

[0353] The user selects and enters specific cost-reduction proposals on the terminal. The terminal sends the information to the server, which prepares to simulate the return on investment.

[0354] Step 9:

[0355] The server uses artificial intelligence to simulate the return on investment for the selected reduction plan. Based on the analysis results from the emotion engine, the optimal method for displaying the results is selected.

[0356] Step 10:

[0357] The simulation results are displayed on the terminal, allowing the user to make strategic decisions based on the results.

[0358] (Example 2)

[0359] 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".

[0360] When companies seek to reduce costs, they need to consider not only the effectiveness of their strategies but also the emotions of those involved. However, conventional systems often derive hypotheses without adequately considering the user's emotional state, which can lead to situations where users are reluctant to accept proposals. Furthermore, the resulting proposals and simulation results may be presented in a way that does not alleviate the user's stress or anxiety. Thus, the lack of systems that can reflect user emotions in strategic planning is a challenge.

[0361] 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.

[0362] In this invention, the server includes emotion analysis means for analyzing the user's emotional state in real time, means for adjusting the parameters of hypothesis generation means based on the emotional state, and means for dynamically adjusting the user interface according to the emotional state. This enables the generation of optimal hypotheses that take the user's emotional state into consideration and the presentation of information in an easily acceptable format.

[0363] "Information input means" refers to a device or method for users to input information regarding a company's challenges and expected outcomes.

[0364] "Artificial intelligence means" refers to a system that uses machine learning algorithms and database lookups to generate hypotheses based on input information.

[0365] "Means for outputting a hypothesis" refers to a device or method for presenting the generated hypothesis to the user.

[0366] "Means for collecting examples from others" refers to devices or methods for collecting relevant examples from external databases or publicly available information.

[0367] "Means of analyzing the cases of others" refers to a device or method that analyzes collected cases and uses the results to aid in strategic planning.

[0368] "Means for simulating return on investment" refers to a device or method for precisely evaluating the cost-effectiveness of a strategic plan selected by the user.

[0369] "Emotional analysis means" refers to a device or method that analyzes a user's emotional state in real time based on the user's input or operations.

[0370] "Means for adjusting parameters" refers to a device or method for dynamically changing settings in the hypothesis generation process based on the results of sentiment analysis.

[0371] "Means for dynamically adjusting the user interface" refers to a device or method that adjusts the display and operation of the user interface according to the emotional state.

[0372] This invention is a system for generating effective proposals while taking into account the emotional state of users when companies formulate strategies. The system mainly consists of the following elements:

[0373] Users input information about their company's challenges and expected outcomes into a terminal and send it to a server. The terminal can use a touchscreen or keyboard as a means of inputting information. The server uses artificial intelligence to generate efficient hypotheses based on the input information. The AI ​​model used here is called a generative AI model, which derives the optimal hypothesis by referring to industry databases and past training data.

[0374] Furthermore, the server uses emotion analysis tools to analyze the user's emotional state in real time from their input and actions. This makes it possible to consider emotions when generating hypotheses and adjusting the user interface. Emotion analysis is performed using natural language processing technology.

[0375] The generated hypotheses are presented to the user through a means of outputting those hypotheses. The user interface is dynamically adjusted according to the user's emotional state, and information is provided in an easily digestible format. This allows the user to receive information efficiently without experiencing stress.

[0376] A concrete example would be a user considering "reducing their marketing budget." If the server recognizes the user's stress level through emotion analysis, it will automatically generate a relaxing interface and prioritize presenting easily understandable content.

[0377] The following is an example of a prompt message to input into the generating AI model.

[0378] "Analyze the emotional state of the user, determine which data should be prioritized, and generate appropriate hypotheses."

[0379] In this way, the system can more effectively support companies in reducing costs and developing strategies.

[0380] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0381] Step 1:

[0382] Users input information about their company's challenges and expected outcomes into a terminal. The terminal receives the data entered using a touchscreen or keyboard. The entered information is then transmitted to a server as digital data.

[0383] Step 2:

[0384] The server generates hypotheses using artificial intelligence based on the received user data. Here, the server uses a generation AI model, referencing industry databases and historical training data. Data processing involves extracting relevant information from the input data and creating new hypotheses through machine learning algorithms. The generated hypotheses are then presented to the user in the next stage.

[0385] Step 3:

[0386] The server analyzes the user's emotional state in real time from their input data and behavior during operation using emotion analysis tools. Natural language processing techniques are used to analyze the input data's text and speech to determine the user's emotions. The results of the emotion analysis are used to adjust parameters in hypothesis generation.

[0387] Step 4:

[0388] The server dynamically adjusts the parameters for hypothesis generation based on the results obtained from sentiment analysis. This ensures that the generated hypotheses are appropriate to the user's emotional state. The adjusted hypotheses are then presented in a way that is more acceptable and easier for the user to understand.

[0389] Step 5:

[0390] The terminal displays generated hypotheses sent from the server as suggestions in the user interface. The interface design is dynamically adjusted according to the user's emotional state; for example, relaxing colors and fonts are adopted. This reduces stress and improves receptivity.

[0391] Step 6:

[0392] If necessary, the server activates methods for collecting other users' case data, gathering relevant cases from external databases and publicly available information. This case data is analyzed and presented to the user in visual or text format. Based on the sentiment analysis results, the presentation order and format are also dynamically adjusted.

[0393] Step 7:

[0394] The server performs a return on investment (ROI) simulation for the hypotheses and strategies selected by the user. Economic data analysis algorithms are used for the simulation data calculations, and the derived results are fed back to the user visually or as text via the terminal.

[0395] (Application Example 2)

[0396] 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 as the "terminal".

[0397] In modern cities, efficiently providing public services and increasing citizen satisfaction are crucial challenges. However, conventional systems struggle to generate flexible proposals and provide information that take into account citizens' emotional states. Therefore, it is necessary to support optimized decision-making in citizen-proposed reservations and usage plans for public facilities.

[0398] 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.

[0399] In this invention, the server includes information acquisition means, machine learning means, display means, information collection means, analysis means, evaluation means, sentiment analysis means, and adaptation means. This makes it possible to analyze the emotional state of citizens in real time and customize suggestions based on the results, thereby supporting the provision of optimal public services.

[0400] "Information acquisition means" refers to a device or process for collecting user input information and using it as basic data for processing.

[0401] "Machine learning methods" refer to algorithms or techniques used to automatically generate hypotheses based on collected information.

[0402] A "display means" is an interface for visually presenting the results of analysis or simulation to the user.

[0403] "Information gathering means" refers to the process or device for collecting necessary data from external information management systems or publicly available information.

[0404] "Analysis methods" refer to techniques or processes for analyzing collected data and extracting specific insights or patterns.

[0405] "Evaluation means" refers to a device or process for simulating return on investment and other performance indicators, and for evaluating the results.

[0406] "Emotional analysis means" refers to technology or devices for recognizing and analyzing a user's emotional state from their facial expressions, voice, etc.

[0407] "Adaptive measures" refer to technologies or processes that dynamically adjust system parameters in response to emotion analysis results to provide the user with the optimal outcome.

[0408] To realize this invention, the server executes a series of programs. Information acquisition means collects suggested information related to public services from user terminals. Machine learning means generates hypotheses based on the collected information. In this process, advanced suggestions become possible by referring to the data aggregation system and past learning results.

[0409] The server analyzes user emotions in real time from collected facial expressions and voices using emotion analysis tools. The analysis results are used to dynamically adjust the parameters of the hypothesis generation tool through an adaptation tool. Specifically, it is expected that an emotion engine (e.g., Microsoft Azure's Emotion API) will be used.

[0410] The display means visually presents hypotheses and analysis results to the user. Here, the user is supported in making appropriate decisions based on information customized according to their emotions.

[0411] The information gathering means collects relevant data using external information management systems and publicly available information, and this data is analyzed by the analysis means. The evaluation means simulates and outputs the return on investment of the proposed hypothesis.

[0412] As a concrete example, when suggesting the efficient use of public facilities, users can respond to the suggestions, and the system will customize the suggestions based on their feedback. An example of a prompt message might be, "When formulating plans for the use of public facilities proposed by citizens, please consider citizens' feelings and customize the suggestions to reduce stress."

[0413] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0414] Step 1:

[0415] The terminal collects suggested information and related requests entered by the user using information acquisition means. The entered information is sent to the server and stored as basic data for hypothesis generation.

[0416] Step 2:

[0417] The server generates hypotheses using machine learning methods based on the received information. It references user input, data aggregation systems, and past learning results, and uses a generative AI model to output hypotheses suitable for the proposal.

[0418] Step 3:

[0419] The device collects the user's facial expressions and voice information and analyzes it using emotion analysis tools. The facial expressions and voice, as input data, are processed to identify the emotional state, and the result is output as the emotional state.

[0420] Step 4:

[0421] Based on the results of the emotion analysis, the server dynamically adjusts the parameters of the hypothesis generation mechanism using adaptive means. This regenerates the optimal hypothesis according to the user's emotions, and the adjusted hypothesis is output.

[0422] Step 5:

[0423] The server uses information gathering tools to collect supplementary data from external information management systems. The collected data is analyzed by analytical tools and output as insights to refine the proposed content.

[0424] Step 6:

[0425] The server simulates the return on investment of hypotheses generated using evaluation tools. Based on the generated hypotheses and supplementary data as input data, evaluation calculations are performed and the simulation results are output.

[0426] Step 7:

[0427] The terminal visually and dynamically presents the final proposal and simulation results to the user through a display device. The results are customized and displayed in a format that is easy for the user to understand.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] [Third Embodiment]

[0432] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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".

[0444] The present invention provides a platform for performing hypothesis generation and data analysis functions necessary for companies to effectively reduce costs. To implement the invention, users are required to input their company's basic information and cost reduction challenges into a terminal. The terminal transmits this information to a server. Upon receiving the information, the server analyzes the input data using its built-in artificial intelligence and generates optimal hypotheses.

[0445] The generated hypotheses are presented to the user through a hypothesis output mechanism. The user can select a cost reduction case study category of interest, and the selected information is transmitted to the server. The server acquires external data related to the specified category through means of collecting other people's case studies, analyzes that data, and provides the analysis results to the user. A distinctive feature of this system is its ability to accurately simulate return on investment using the collected data. When the user inputs a specific reduction plan, the server makes a prediction about that plan based on historical data and statistical models, and outputs the results to the user.

[0446] As a concrete example, consider a scenario where a user inputs information indicating they are "considering cost reduction through improved energy efficiency." In this case, the server collects past examples of successful energy efficiency improvements and analyzes that information. Simultaneously, it can perform predictive simulations to show the user the time to return on investment and the amount of cost reduction possible.

[0447] Thus, by using the system of the present invention, companies can quickly and effectively explore and implement cost reduction measures, thereby improving the quality of decision-making.

[0448] The following describes the processing flow.

[0449] Step 1:

[0450] The user enters basic information and challenges related to cost reduction for their company into the terminal. The terminal then formats this information and prepares it to be sent to the server.

[0451] Step 2:

[0452] The terminal sends formatted information to the server. The server analyzes the received data, evaluates the input data using artificial intelligence, and generates hypotheses.

[0453] Step 3:

[0454] The server reconfirms the generated hypothesis and presents it to the user through a hypothesis output mechanism. The user can then conduct further investigation based on this hypothesis.

[0455] Step 4:

[0456] The user selects a category of industry case studies they are interested in using their device. The device transmits this information to the server, which then begins collecting case studies from other users.

[0457] Step 5:

[0458] The server collects other users' cases related to the specified category from external data sources. The collected data is analyzed, and important information is extracted.

[0459] Step 6:

[0460] The server provides the analysis results to the user. Based on the collected case studies, the user can evaluate the applicability to their own company.

[0461] Step 7:

[0462] The user enters detailed information about a specific cost-saving proposal into the terminal. The terminal formats this information and sends it to the server.

[0463] Step 8:

[0464] Based on the cost reduction proposals received by the server, the return on investment is simulated using artificial intelligence. This simulation includes predictions of initial investment and cost reduction effects.

[0465] Step 9:

[0466] The server provides the user with simulation results. Based on this, the user can make final decisions regarding cost reduction measures.

[0467] (Example 1)

[0468] 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."

[0469] Finding effective ways for companies to quickly reduce costs is challenging, especially when dealing with a large amount of information. Furthermore, it requires effectively utilizing industry-specific data and the success stories of others when generating hypotheses and simulating return on investment.

[0470] 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.

[0471] In this invention, the server includes artificial intelligence means for generating hypotheses based on information, means for collecting and analyzing other people's case studies, and means for simulating return on investment using past data and statistical models. This enables companies to quickly identify effective cost reduction measures and predict return on investment with high accuracy.

[0472] An "information input method" is a means for users to input basic information and data related to cost reduction into the system.

[0473] "Artificial intelligence means" refers to software technology executed by a computer to analyze input information and generate optimal hypotheses.

[0474] "Means for outputting hypotheses" refer to user interfaces and notification methods for presenting the generated hypotheses to the user.

[0475] "Means of collecting examples from others" refers to the processes and techniques for collecting success stories and useful data from external sources.

[0476] "Means of analyzing cases" refers to data processing techniques used to analyze collected cases from others and identify trends and patterns.

[0477] "Means of simulating return on investment" refers to methods or techniques for making predictions about a specific reduction plan using historical data and statistical models.

[0478] "Means for visualizing and outputting simulation results" refers to technologies for showing calculated simulation results to users in visual formats such as graphs and tables.

[0479] The embodiments for carrying out the present invention will be described below.

[0480] This system is designed to help businesses effectively reduce costs. Users use a terminal to input their company's basic information and cost-reduction challenges. Standard PCs and tablets can be used as terminals, and data entry is performed through a dedicated web browser application.

[0481] The input information is sent to the server via the internet. Upon receiving the information, the server analyzes the data using an artificial intelligence model. Here, Python machine learning libraries such as TensorFlow and PyTorch are used, enabling rapid and highly accurate hypothesis generation.

[0482] The hypotheses generated by the artificial intelligence model are presented to the user through a user interface. Based on the displayed hypotheses, the user selects a category of cost reduction case study that interests them and sends the information back to the server. Based on this information, the server refers to external databases and publicly available information to collect and analyze relevant data.

[0483] The server uses the collected data to perform simulations of the return on investment (ROI) for cost reduction proposals. Statistical tools such as R and Matlab are used in the simulations, referencing historical data and existing models. The results are provided to the user in a visually easy-to-understand format. This allows companies to obtain information necessary for concrete return on investment periods and strategic decision-making.

[0484] For example, if a user inputs information stating that they are "considering cost reduction through improved energy efficiency," the server will collect past examples of successful energy efficiency improvements and analyze that information. It will also provide the user with prompts such as "Please tell me the details of successful examples and the expected return on investment," and based on that, it will use a generated AI model to predict the return on investment.

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

[0486] Step 1:

[0487] Users input their company's basic information and cost reduction challenges into a terminal. Specifically, users enter company data and reduction targets into a form in a web browser and press the submit button. The input data is organized in JSON format and sent.

[0488] Step 2:

[0489] The terminal sends the entered information to the server. This transmission is performed using HTTPS, a secure communication protocol. The input data is converted into a format that is easily received by the server before being sent.

[0490] Step 3:

[0491] The server first stores the received data in a database for analysis. An artificial intelligence model using TensorFlow is employed for data analysis, classifying the input data and generating optimal hypotheses. The input data is also compared against historical database data.

[0492] Step 4:

[0493] The generated hypotheses are presented to the user via a user interface by the server. Specifically, the hypotheses are visualized in real time and displayed in the web browser. The user can review this information and select an option.

[0494] Step 5:

[0495] The user selects a cost reduction case study category of interest and sends that information back to the server from their device. The selected category information is then organized as new data and sent.

[0496] Step 6:

[0497] The server collects external data related to the specified category. It uses external databases and public APIs to retrieve the latest information. The collected data is sent to the server's analysis system.

[0498] Step 7:

[0499] The server analyzes the collected data and provides the results to the user. Libraries such as Numpy and Pandas are used for the analysis, and the resulting data is organized and visualized as statistical information.

[0500] Step 8:

[0501] To simulate the return on investment for a specific cost reduction plan, the server utilizes historical data and statistical models. The simulation results calculate the expected payback period and cost savings.

[0502] Step 9:

[0503] The server visualizes the simulation results and presents them to the user. The results are presented in graphs and tables, easily accessible to the user through a browser. This information is then used to assist the user in making decisions.

[0504] (Application Example 1)

[0505] 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."

[0506] In modern industry, optimizing the energy consumption of machinery while effectively reducing operating costs is a critical challenge. In particular, to address these challenges, there is a need for a system that can efficiently collect and analyze operational data and propose optimal operating methods.

[0507] 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.

[0508] In this invention, the server includes information gathering means, knowledge processing means, and evaluation means. This enables the proposal of operational improvement methods based on usage information and consumption information of the operational machine, thereby reducing operating costs and improving energy efficiency.

[0509] "Information gathering means" refers to a function or device used to collect relevant data or information.

[0510] "Knowledge processing means" refers to artificial intelligence or data processing technology used to analyze collected information and generate hypotheses.

[0511] "Display means" refers to devices or functions that visually provide users with generated hypotheses or analysis results.

[0512] "Data processing means" refers to methods or devices used to analyze collected cases and data from others and to derive insights.

[0513] "Evaluation means" refers to a function or technology for simulating the results of input resources and evaluating their effectiveness.

[0514] "Presentation means" refers to methods or devices for displaying or communicating simulation results or analysis results to the user.

[0515] "Information input means" refers to methods or devices for users to input usage information and consumption information of operating machines.

[0516] The system of this invention begins with the user inputting information on the operation of the machine and energy consumption information from a smartphone or terminal via an information input means. The input information is transmitted to a cloud server via the internet. The server collects relevant data using an information collection means and analyzes it using a knowledge processing means. The knowledge processing means incorporates generative AI models such as TensorFlow and PyTorch.

[0517] The server generates hypotheses based on the analyzed data and simulates the resource input versus output using evaluation tools. In this process, the accuracy of the hypotheses is improved by referring to historical data and statistical models. The analysis and simulation results are visually presented on smartphones and other devices through display tools.

[0518] As a concrete example, if a factory is considering ways to improve the energy efficiency of its machinery, the server analyzes past similar cases and information from an external database using data processing tools to propose the optimal operating method. At this time, the generating AI model forms hypotheses using prompt statements such as, "Please tell me how to improve the energy efficiency of the factory robots we are using. Based on past data, please propose the most effective operating method." Through this method, the system of the present invention effectively improves the operational efficiency of the factory.

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

[0520] Step 1:

[0521] Users input information about the operation of their machinery and energy consumption into their smartphone's information input device. This information is organized in JSON format.

[0522] Step 2:

[0523] The device sends the entered information to the cloud server. The data is transmitted via a secure protocol and received by the server.

[0524] Step 3:

[0525] The server uses information gathering tools to collect relevant data from internal databases and external information sources. During this process, it obtains the necessary data through available APIs.

[0526] Step 4:

[0527] The server analyzes the data collected by the knowledge processing tools. Specifically, it uses a generative AI model (e.g., TensorFlow) to identify patterns in the input data and generate hypotheses based on the data. The prompt "Please tell me how to improve energy efficiency" is input to the model.

[0528] Step 5:

[0529] The server uses evaluation tools to simulate the resource input versus output based on the generated hypotheses. By comparing this with past data, it predicts the effectiveness of the proposed improvement measures.

[0530] Step 6:

[0531] The server compiles the analysis and simulation results and transmits them to the terminal via a display device. The terminal then visually presents these results to the user.

[0532] Step 7:

[0533] The user accepts and implements the proposed operational efficiency improvements. The feasibility of the proposals is reviewed, and adjustments are made as necessary.

[0534] 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.

[0535] This invention provides a system that offers advanced support to companies when they plan and implement cost reduction strategies, taking into account the emotional state of the user. The system comprises information input means, artificial intelligence means, hypothesis output means, means for collecting examples from others, means for analyzing examples, means for simulating return on investment, and an emotion engine.

[0536] The user inputs their company's challenges and desired outcomes into a terminal. After input, the terminal sends the information to a server. The server uses artificial intelligence to generate hypotheses based on the input information, industry databases, and past training data. The generated hypotheses are presented to the user through a hypothesis output device.

[0537] Furthermore, this system is equipped with an emotion engine that recognizes the user's emotions in real time. The emotion engine analyzes the user's emotions from their input data and behavior during operation, and dynamically adjusts the parameters of the hypothesis generation means based on the results. This function enables the system to propose optimal hypotheses according to the user's emotional state.

[0538] The method for collecting other people's case studies involves using external databases and publicly available information to collect relevant cases and analyze them. The emotion engine adjusts the order in which the analysis results are presented to the user based on their emotional state, providing information in a way that is most easily accepted by the user.

[0539] Furthermore, a precise simulation of the return on investment is performed for the reduction plan selected by the user. The results are then fed back to the user in an optimal format, taking into account their emotional state.

[0540] For example, consider a situation where a user is considering "cutting their marketing budget." If the system detects that the user is stressed, the emotion engine will generate a relaxing interface and prioritize presenting an easily understandable summary. This allows the user to efficiently receive information and make better decisions.

[0541] This system enables companies to develop more flexible and emotionally sensitive strategies, and to advance cost reduction processes more effectively.

[0542] The following describes the processing flow.

[0543] Step 1:

[0544] The user enters their company's cost-reduction challenges and desired goals into the terminal. The terminal formats the user's input data and prepares to send it to the server.

[0545] Step 2:

[0546] The device sends formatted user information to the server. Upon receiving the information, the server uses an emotion engine to simultaneously analyze the user's emotional state.

[0547] Step 3:

[0548] The server uses artificial intelligence to generate optimal hypotheses by referencing data submitted by the user, industry databases, and past learning results. The parameters for hypothesis generation are adjusted based on the results of the emotion engine.

[0549] Step 4:

[0550] The server generates hypotheses and presents them to the user through an appropriate interface based on their emotional state. A hypothesis output mechanism is used here, and the information is displayed to the user.

[0551] Step 5:

[0552] The system selects other users' case studies based on the categories the user has shown interest in. The device sends this information to the server, which then activates a system for collecting other users' case studies to gather relevant examples.

[0553] Step 6:

[0554] The server collects other people's cases related to a specified category from external databases and publicly available information. The collected data is analyzed using methods for analyzing other people's cases.

[0555] Step 7:

[0556] The server effectively presents analysis results, taking into account the user's emotional state. The emotion engine adjusts the order in which information is presented, ensuring that the information is delivered in the format most easily accepted by the user.

[0557] Step 8:

[0558] The user selects and enters specific cost-reduction proposals on the terminal. The terminal sends the information to the server, which prepares to simulate the return on investment.

[0559] Step 9:

[0560] The server uses artificial intelligence to simulate the return on investment for the selected reduction plan. Based on the analysis results from the emotion engine, the optimal method for displaying the results is selected.

[0561] Step 10:

[0562] The simulation results are displayed on the terminal, allowing the user to make strategic decisions based on the results.

[0563] (Example 2)

[0564] 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."

[0565] When companies seek to reduce costs, they need to consider not only the effectiveness of their strategies but also the emotions of those involved. However, conventional systems often derive hypotheses without adequately considering the user's emotional state, which can lead to situations where users are reluctant to accept proposals. Furthermore, the resulting proposals and simulation results may be presented in a way that does not alleviate the user's stress or anxiety. Thus, the lack of systems that can reflect user emotions in strategic planning is a challenge.

[0566] 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.

[0567] In this invention, the server includes emotion analysis means for analyzing the user's emotional state in real time, means for adjusting the parameters of hypothesis generation means based on the emotional state, and means for dynamically adjusting the user interface according to the emotional state. This enables the generation of optimal hypotheses that take the user's emotional state into consideration and the presentation of information in an easily acceptable format.

[0568] "Information input means" refers to a device or method for users to input information regarding a company's challenges and expected outcomes.

[0569] "Artificial intelligence means" refers to a system that uses machine learning algorithms and database lookups to generate hypotheses based on input information.

[0570] "Means for outputting a hypothesis" refers to a device or method for presenting the generated hypothesis to the user.

[0571] "Means for collecting examples from others" refers to devices or methods for collecting relevant examples from external databases or publicly available information.

[0572] "Means of analyzing the cases of others" refers to a device or method that analyzes collected cases and uses the results to aid in strategic planning.

[0573] "Means for simulating return on investment" refers to a device or method for precisely evaluating the cost-effectiveness of a strategic plan selected by the user.

[0574] "Emotional analysis means" refers to a device or method that analyzes a user's emotional state in real time based on the user's input or operations.

[0575] "Means for adjusting parameters" refers to a device or method for dynamically changing settings in the hypothesis generation process based on the results of sentiment analysis.

[0576] "Means for dynamically adjusting the user interface" refers to a device or method that adjusts the display and operation of the user interface according to the emotional state.

[0577] This invention is a system for generating effective proposals while taking into account the emotional state of users when companies formulate strategies. The system mainly consists of the following elements:

[0578] Users input information about their company's challenges and expected outcomes into a terminal and send it to a server. The terminal can use a touchscreen or keyboard as a means of inputting information. The server uses artificial intelligence to generate efficient hypotheses based on the input information. The AI ​​model used here is called a generative AI model, which derives the optimal hypothesis by referring to industry databases and past training data.

[0579] Furthermore, the server uses emotion analysis tools to analyze the user's emotional state in real time from their input and actions. This makes it possible to consider emotions when generating hypotheses and adjusting the user interface. Emotion analysis is performed using natural language processing technology.

[0580] The generated hypotheses are presented to the user through a means of outputting those hypotheses. The user interface is dynamically adjusted according to the user's emotional state, and information is provided in an easily digestible format. This allows the user to receive information efficiently without experiencing stress.

[0581] A concrete example would be a user considering "reducing their marketing budget." If the server recognizes the user's stress level through emotion analysis, it will automatically generate a relaxing interface and prioritize presenting easily understandable content.

[0582] The following is an example of a prompt message to input into the generating AI model.

[0583] "Analyze the emotional state of the user, determine which data should be prioritized, and generate appropriate hypotheses."

[0584] In this way, the system can more effectively support companies in reducing costs and developing strategies.

[0585] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0586] Step 1:

[0587] Users input information about their company's challenges and expected outcomes into a terminal. The terminal receives the data entered using a touchscreen or keyboard. The entered information is then transmitted to a server as digital data.

[0588] Step 2:

[0589] The server generates hypotheses using artificial intelligence based on the received user data. Here, the server uses a generation AI model, referencing industry databases and historical training data. Data processing involves extracting relevant information from the input data and creating new hypotheses through machine learning algorithms. The generated hypotheses are then presented to the user in the next stage.

[0590] Step 3:

[0591] The server analyzes the user's emotional state in real time from their input data and behavior during operation using emotion analysis tools. Natural language processing techniques are used to analyze the input data's text and speech to determine the user's emotions. The results of the emotion analysis are used to adjust parameters in hypothesis generation.

[0592] Step 4:

[0593] The server dynamically adjusts the parameters for hypothesis generation based on the results obtained from sentiment analysis. This ensures that the generated hypotheses are appropriate to the user's emotional state. The adjusted hypotheses are then presented in a way that is more acceptable and easier for the user to understand.

[0594] Step 5:

[0595] The terminal displays generated hypotheses sent from the server as suggestions in the user interface. The interface design is dynamically adjusted according to the user's emotional state; for example, relaxing colors and fonts are adopted. This reduces stress and improves receptivity.

[0596] Step 6:

[0597] If necessary, the server activates methods for collecting other users' case data, gathering relevant cases from external databases and publicly available information. This case data is analyzed and presented to the user in visual or text format. Based on the sentiment analysis results, the presentation order and format are also dynamically adjusted.

[0598] Step 7:

[0599] The server performs a return on investment (ROI) simulation for the hypotheses and strategies selected by the user. Economic data analysis algorithms are used for the simulation data calculations, and the derived results are fed back to the user visually or as text via the terminal.

[0600] (Application Example 2)

[0601] 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."

[0602] In modern cities, efficiently providing public services and increasing citizen satisfaction are crucial challenges. However, conventional systems struggle to generate flexible proposals and provide information that take into account citizens' emotional states. Therefore, it is necessary to support optimized decision-making in citizen-proposed reservations and usage plans for public facilities.

[0603] 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.

[0604] In this invention, the server includes information acquisition means, machine learning means, display means, information collection means, analysis means, evaluation means, sentiment analysis means, and adaptation means. This makes it possible to analyze the emotional state of citizens in real time and customize suggestions based on the results, thereby supporting the provision of optimal public services.

[0605] "Information acquisition means" refers to a device or process for collecting user input information and using it as basic data for processing.

[0606] "Machine learning methods" refer to algorithms or techniques used to automatically generate hypotheses based on collected information.

[0607] A "display means" is an interface for visually presenting the results of analysis or simulation to the user.

[0608] "Information gathering means" refers to the process or device for collecting necessary data from external information management systems or publicly available information.

[0609] "Analysis methods" refer to techniques or processes for analyzing collected data and extracting specific insights or patterns.

[0610] "Evaluation means" refers to a device or process for simulating return on investment and other performance indicators, and for evaluating the results.

[0611] "Emotional analysis means" refers to technology or devices for recognizing and analyzing a user's emotional state from their facial expressions, voice, etc.

[0612] "Adaptive measures" refer to technologies or processes that dynamically adjust system parameters in response to emotion analysis results to provide the user with the optimal outcome.

[0613] To realize this invention, the server executes a series of programs. Information acquisition means collects suggested information related to public services from user terminals. Machine learning means generates hypotheses based on the collected information. In this process, advanced suggestions become possible by referring to the data aggregation system and past learning results.

[0614] The server analyzes user emotions in real time from collected facial expressions and voices using emotion analysis tools. The analysis results are used to dynamically adjust the parameters of the hypothesis generation tool through an adaptation tool. Specifically, it is expected that an emotion engine (e.g., Microsoft Azure's Emotion API) will be used.

[0615] The display means visually presents hypotheses and analysis results to the user. Here, the user is supported in making appropriate decisions based on information customized according to their emotions.

[0616] The information gathering means collects relevant data using external information management systems and publicly available information, and this data is analyzed by the analysis means. The evaluation means simulates and outputs the return on investment of the proposed hypothesis.

[0617] As a concrete example, when suggesting the efficient use of public facilities, users can respond to the suggestions, and the system will customize the suggestions based on their feedback. An example of a prompt message might be, "When formulating plans for the use of public facilities proposed by citizens, please consider citizens' feelings and customize the suggestions to reduce stress."

[0618] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0619] Step 1:

[0620] The terminal collects suggested information and related requests entered by the user using information acquisition means. The entered information is sent to the server and stored as basic data for hypothesis generation.

[0621] Step 2:

[0622] The server generates hypotheses using machine learning methods based on the received information. It references user input, data aggregation systems, and past learning results, and uses a generative AI model to output hypotheses suitable for the proposal.

[0623] Step 3:

[0624] The device collects the user's facial expressions and voice information and analyzes it using emotion analysis tools. The facial expressions and voice, as input data, are processed to identify the emotional state, and the result is output as the emotional state.

[0625] Step 4:

[0626] Based on the results of the emotion analysis, the server dynamically adjusts the parameters of the hypothesis generation mechanism using adaptive means. This regenerates the optimal hypothesis according to the user's emotions, and the adjusted hypothesis is output.

[0627] Step 5:

[0628] The server uses information gathering tools to collect supplementary data from external information management systems. The collected data is analyzed by analytical tools and output as insights to refine the proposed content.

[0629] Step 6:

[0630] The server simulates the return on investment of hypotheses generated using evaluation tools. Based on the generated hypotheses and supplementary data as input data, evaluation calculations are performed and the simulation results are output.

[0631] Step 7:

[0632] The terminal visually and dynamically presents the final proposal and simulation results to the user through a display device. The results are customized and displayed in a format that is easy for the user to understand.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] [Fourth Embodiment]

[0637] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0638] 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.

[0639] 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).

[0640] 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.

[0641] 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.

[0642] 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).

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] 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.

[0648] 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.

[0649] 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".

[0650] The present invention provides a platform for performing hypothesis generation and data analysis functions necessary for companies to effectively reduce costs. To implement the invention, users are required to input their company's basic information and cost reduction challenges into a terminal. The terminal transmits this information to a server. Upon receiving the information, the server analyzes the input data using its built-in artificial intelligence and generates optimal hypotheses.

[0651] The generated hypotheses are presented to the user through a hypothesis output mechanism. The user can select a cost reduction case study category of interest, and the selected information is transmitted to the server. The server acquires external data related to the specified category through means of collecting other people's case studies, analyzes that data, and provides the analysis results to the user. A distinctive feature of this system is its ability to accurately simulate return on investment using the collected data. When the user inputs a specific reduction plan, the server makes a prediction about that plan based on historical data and statistical models, and outputs the results to the user.

[0652] As a concrete example, consider a scenario where a user inputs information indicating they are "considering cost reduction through improved energy efficiency." In this case, the server collects past examples of successful energy efficiency improvements and analyzes that information. Simultaneously, it can perform predictive simulations to show the user the time to return on investment and the amount of cost reduction possible.

[0653] Thus, by using the system of the present invention, companies can quickly and effectively explore and implement cost reduction measures, thereby improving the quality of decision-making.

[0654] The following describes the processing flow.

[0655] Step 1:

[0656] The user enters basic information and challenges related to cost reduction for their company into the terminal. The terminal then formats this information and prepares it to be sent to the server.

[0657] Step 2:

[0658] The terminal sends formatted information to the server. The server analyzes the received data, evaluates the input data using artificial intelligence, and generates hypotheses.

[0659] Step 3:

[0660] The server reconfirms the generated hypothesis and presents it to the user through a hypothesis output mechanism. The user can then conduct further investigation based on this hypothesis.

[0661] Step 4:

[0662] The user selects a category of industry case studies they are interested in using their device. The device transmits this information to the server, which then begins collecting case studies from other users.

[0663] Step 5:

[0664] The server collects other users' cases related to the specified category from external data sources. The collected data is analyzed, and important information is extracted.

[0665] Step 6:

[0666] The server provides the analysis results to the user. Based on the collected case studies, the user can evaluate the applicability to their own company.

[0667] Step 7:

[0668] The user enters detailed information about a specific cost-saving proposal into the terminal. The terminal formats this information and sends it to the server.

[0669] Step 8:

[0670] Based on the cost reduction proposals received by the server, the return on investment is simulated using artificial intelligence. This simulation includes predictions of initial investment and cost reduction effects.

[0671] Step 9:

[0672] The server provides the user with simulation results. Based on this, the user can make final decisions regarding cost reduction measures.

[0673] (Example 1)

[0674] 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".

[0675] Finding effective ways for companies to quickly reduce costs is challenging, especially when dealing with a large amount of information. Furthermore, it requires effectively utilizing industry-specific data and the success stories of others when generating hypotheses and simulating return on investment.

[0676] 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.

[0677] In this invention, the server includes artificial intelligence means for generating hypotheses based on information, means for collecting and analyzing other people's case studies, and means for simulating return on investment using past data and statistical models. This enables companies to quickly identify effective cost reduction measures and predict return on investment with high accuracy.

[0678] An "information input method" is a means for users to input basic information and data related to cost reduction into the system.

[0679] "Artificial intelligence means" refers to software technology executed by a computer to analyze input information and generate optimal hypotheses.

[0680] "Means for outputting hypotheses" refer to user interfaces and notification methods for presenting the generated hypotheses to the user.

[0681] "Means of collecting examples from others" refers to the processes and techniques for collecting success stories and useful data from external sources.

[0682] "Means of analyzing cases" refers to data processing techniques used to analyze collected cases from others and identify trends and patterns.

[0683] "Means of simulating return on investment" refers to methods or techniques for making predictions about a specific reduction plan using historical data and statistical models.

[0684] "Means for visualizing and outputting simulation results" refers to technologies for showing calculated simulation results to users in visual formats such as graphs and tables.

[0685] The embodiments for carrying out the present invention will be described below.

[0686] This system is designed to help businesses effectively reduce costs. Users use a terminal to input their company's basic information and cost-reduction challenges. Standard PCs and tablets can be used as terminals, and data entry is performed through a dedicated web browser application.

[0687] The input information is sent to the server via the internet. Upon receiving the information, the server analyzes the data using an artificial intelligence model. Here, Python machine learning libraries such as TensorFlow and PyTorch are used, enabling rapid and highly accurate hypothesis generation.

[0688] The hypotheses generated by the artificial intelligence model are presented to the user through a user interface. Based on the displayed hypotheses, the user selects a category of cost reduction case study that interests them and sends the information back to the server. Based on this information, the server refers to external databases and publicly available information to collect and analyze relevant data.

[0689] The server uses the collected data to perform simulations of the return on investment (ROI) for cost reduction proposals. Statistical tools such as R and Matlab are used in the simulations, referencing historical data and existing models. The results are provided to the user in a visually easy-to-understand format. This allows companies to obtain information necessary for concrete return on investment periods and strategic decision-making.

[0690] For example, if a user inputs information stating that they are "considering cost reduction through improved energy efficiency," the server will collect past examples of successful energy efficiency improvements and analyze that information. It will also provide the user with prompts such as "Please tell me the details of successful examples and the expected return on investment," and based on that, it will use a generated AI model to predict the return on investment.

[0691] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0692] Step 1:

[0693] Users input their company's basic information and cost reduction challenges into a terminal. Specifically, users enter company data and reduction targets into a form in a web browser and press the submit button. The input data is organized in JSON format and sent.

[0694] Step 2:

[0695] The terminal sends the entered information to the server. This transmission is performed using HTTPS, a secure communication protocol. The input data is converted into a format that is easily received by the server before being sent.

[0696] Step 3:

[0697] The server first stores the received data in a database for analysis. An artificial intelligence model using TensorFlow is employed for data analysis, classifying the input data and generating optimal hypotheses. The input data is also compared against historical database data.

[0698] Step 4:

[0699] The generated hypotheses are presented to the user via a user interface by the server. Specifically, the hypotheses are visualized in real time and displayed in the web browser. The user can review this information and select an option.

[0700] Step 5:

[0701] The user selects a cost reduction case study category of interest and sends that information back to the server from their device. The selected category information is then organized as new data and sent.

[0702] Step 6:

[0703] The server collects external data related to the specified category. It uses external databases and public APIs to retrieve the latest information. The collected data is sent to the server's analysis system.

[0704] Step 7:

[0705] The server analyzes the collected data and provides the results to the user. Libraries such as Numpy and Pandas are used for the analysis, and the resulting data is organized and visualized as statistical information.

[0706] Step 8:

[0707] To simulate the return on investment for a specific cost reduction plan, the server utilizes historical data and statistical models. The simulation results calculate the expected payback period and cost savings.

[0708] Step 9:

[0709] The server visualizes the simulation results and presents them to the user. The results are presented in graphs and tables, easily accessible to the user through a browser. This information is then used to assist the user in making decisions.

[0710] (Application Example 1)

[0711] 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".

[0712] In modern industry, optimizing the energy consumption of machinery while effectively reducing operating costs is a critical challenge. In particular, to address these challenges, there is a need for a system that can efficiently collect and analyze operational data and propose optimal operating methods.

[0713] 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.

[0714] In this invention, the server includes information gathering means, knowledge processing means, and evaluation means. This enables the proposal of operational improvement methods based on usage information and consumption information of the operational machine, thereby reducing operating costs and improving energy efficiency.

[0715] "Information gathering means" refers to a function or device used to collect relevant data or information.

[0716] "Knowledge processing means" refers to artificial intelligence or data processing technology used to analyze collected information and generate hypotheses.

[0717] "Display means" refers to devices or functions that visually provide users with generated hypotheses or analysis results.

[0718] "Data processing means" refers to methods or devices used to analyze collected cases and data from others and to derive insights.

[0719] "Evaluation means" refers to a function or technology for simulating the results of input resources and evaluating their effectiveness.

[0720] "Presentation means" refers to methods or devices for displaying or communicating simulation results or analysis results to the user.

[0721] "Information input means" refers to methods or devices for users to input usage information and consumption information of operating machines.

[0722] The system of this invention begins with the user inputting information on the operation of the machine and energy consumption information from a smartphone or terminal via an information input means. The input information is transmitted to a cloud server via the internet. The server collects relevant data using an information collection means and analyzes it using a knowledge processing means. The knowledge processing means incorporates generative AI models such as TensorFlow and PyTorch.

[0723] The server generates hypotheses based on the analyzed data and simulates the resource input versus output using evaluation tools. In this process, the accuracy of the hypotheses is improved by referring to historical data and statistical models. The analysis and simulation results are visually presented on smartphones and other devices through display tools.

[0724] As a concrete example, if a factory is considering ways to improve the energy efficiency of its machinery, the server analyzes past similar cases and information from an external database using data processing tools to propose the optimal operating method. At this time, the generating AI model forms hypotheses using prompt statements such as, "Please tell me how to improve the energy efficiency of the factory robots we are using. Based on past data, please propose the most effective operating method." Through this method, the system of the present invention effectively improves the operational efficiency of the factory.

[0725] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0726] Step 1:

[0727] Users input information about the operation of their machinery and energy consumption into their smartphone's information input device. This information is organized in JSON format.

[0728] Step 2:

[0729] The device sends the entered information to the cloud server. The data is transmitted via a secure protocol and received by the server.

[0730] Step 3:

[0731] The server uses information gathering tools to collect relevant data from internal databases and external information sources. During this process, it obtains the necessary data through available APIs.

[0732] Step 4:

[0733] The server analyzes the data collected by the knowledge processing tools. Specifically, it uses a generative AI model (e.g., TensorFlow) to identify patterns in the input data and generate hypotheses based on the data. The prompt "Please tell me how to improve energy efficiency" is input to the model.

[0734] Step 5:

[0735] The server uses evaluation tools to simulate the resource input versus output based on the generated hypotheses. By comparing this with past data, it predicts the effectiveness of the proposed improvement measures.

[0736] Step 6:

[0737] The server compiles the analysis and simulation results and transmits them to the terminal via a display device. The terminal then visually presents these results to the user.

[0738] Step 7:

[0739] The user accepts and implements the proposed operational efficiency improvements. The feasibility of the proposals is reviewed, and adjustments are made as necessary.

[0740] 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.

[0741] This invention provides a system that offers advanced support to companies when they plan and implement cost reduction strategies, taking into account the emotional state of the user. The system comprises information input means, artificial intelligence means, hypothesis output means, means for collecting examples from others, means for analyzing examples, means for simulating return on investment, and an emotion engine.

[0742] The user inputs their company's challenges and desired outcomes into a terminal. After input, the terminal sends the information to a server. The server uses artificial intelligence to generate hypotheses based on the input information, industry databases, and past training data. The generated hypotheses are presented to the user through a hypothesis output device.

[0743] Furthermore, this system is equipped with an emotion engine that recognizes the user's emotions in real time. The emotion engine analyzes the user's emotions from their input data and behavior during operation, and dynamically adjusts the parameters of the hypothesis generation means based on the results. This function enables the system to propose optimal hypotheses according to the user's emotional state.

[0744] The method for collecting other people's case studies involves using external databases and publicly available information to collect relevant cases and analyze them. The emotion engine adjusts the order in which the analysis results are presented to the user based on their emotional state, providing information in a way that is most easily accepted by the user.

[0745] Furthermore, a precise simulation of the return on investment is performed for the reduction plan selected by the user. The results are then fed back to the user in an optimal format, taking into account their emotional state.

[0746] For example, consider a situation where a user is considering "cutting their marketing budget." If the system detects that the user is stressed, the emotion engine will generate a relaxing interface and prioritize presenting an easily understandable summary. This allows the user to efficiently receive information and make better decisions.

[0747] This system enables companies to develop more flexible and emotionally sensitive strategies, and to advance cost reduction processes more effectively.

[0748] The following describes the processing flow.

[0749] Step 1:

[0750] The user enters their company's cost-reduction challenges and desired goals into the terminal. The terminal formats the user's input data and prepares to send it to the server.

[0751] Step 2:

[0752] The device sends formatted user information to the server. Upon receiving the information, the server uses an emotion engine to simultaneously analyze the user's emotional state.

[0753] Step 3:

[0754] The server uses artificial intelligence to generate optimal hypotheses by referencing data submitted by the user, industry databases, and past learning results. The parameters for hypothesis generation are adjusted based on the results of the emotion engine.

[0755] Step 4:

[0756] The server generates hypotheses and presents them to the user through an appropriate interface based on their emotional state. A hypothesis output mechanism is used here, and the information is displayed to the user.

[0757] Step 5:

[0758] The system selects other users' case studies based on the categories the user has shown interest in. The device sends this information to the server, which then activates a system for collecting other users' case studies to gather relevant examples.

[0759] Step 6:

[0760] The server collects other people's cases related to a specified category from external databases and publicly available information. The collected data is analyzed using methods for analyzing other people's cases.

[0761] Step 7:

[0762] The server effectively presents analysis results, taking into account the user's emotional state. The emotion engine adjusts the order in which information is presented, ensuring that the information is delivered in the format most easily accepted by the user.

[0763] Step 8:

[0764] The user selects and enters specific cost-reduction proposals on the terminal. The terminal sends the information to the server, which prepares to simulate the return on investment.

[0765] Step 9:

[0766] The server uses artificial intelligence to simulate the return on investment for the selected reduction plan. Based on the analysis results from the emotion engine, the optimal method for displaying the results is selected.

[0767] Step 10:

[0768] The simulation results are displayed on the terminal, allowing the user to make strategic decisions based on the results.

[0769] (Example 2)

[0770] 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".

[0771] When companies seek to reduce costs, they need to consider not only the effectiveness of their strategies but also the emotions of those involved. However, conventional systems often derive hypotheses without adequately considering the user's emotional state, which can lead to situations where users are reluctant to accept proposals. Furthermore, the resulting proposals and simulation results may be presented in a way that does not alleviate the user's stress or anxiety. Thus, the lack of systems that can reflect user emotions in strategic planning is a challenge.

[0772] 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.

[0773] In this invention, the server includes emotion analysis means for analyzing the user's emotional state in real time, means for adjusting the parameters of hypothesis generation means based on the emotional state, and means for dynamically adjusting the user interface according to the emotional state. This enables the generation of optimal hypotheses that take the user's emotional state into consideration and the presentation of information in an easily acceptable format.

[0774] "Information input means" refers to a device or method for users to input information regarding a company's challenges and expected outcomes.

[0775] "Artificial intelligence means" refers to a system that uses machine learning algorithms and database lookups to generate hypotheses based on input information.

[0776] "Means for outputting a hypothesis" refers to a device or method for presenting the generated hypothesis to the user.

[0777] "Means for collecting examples from others" refers to devices or methods for collecting relevant examples from external databases or publicly available information.

[0778] "Means of analyzing the cases of others" refers to a device or method that analyzes collected cases and uses the results to aid in strategic planning.

[0779] "Means for simulating return on investment" refers to a device or method for precisely evaluating the cost-effectiveness of a strategic plan selected by the user.

[0780] "Emotional analysis means" refers to a device or method that analyzes a user's emotional state in real time based on the user's input or operations.

[0781] "Means for adjusting parameters" refers to a device or method for dynamically changing settings in the hypothesis generation process based on the results of sentiment analysis.

[0782] "Means for dynamically adjusting the user interface" refers to a device or method that adjusts the display and operation of the user interface according to the emotional state.

[0783] This invention is a system for generating effective proposals while taking into account the emotional state of users when companies formulate strategies. The system mainly consists of the following elements:

[0784] Users input information about their company's challenges and expected outcomes into a terminal and send it to a server. The terminal can use a touchscreen or keyboard as a means of inputting information. The server uses artificial intelligence to generate efficient hypotheses based on the input information. The AI ​​model used here is called a generative AI model, which derives the optimal hypothesis by referring to industry databases and past training data.

[0785] Furthermore, the server uses emotion analysis tools to analyze the user's emotional state in real time from their input and actions. This makes it possible to consider emotions when generating hypotheses and adjusting the user interface. Emotion analysis is performed using natural language processing technology.

[0786] The generated hypotheses are presented to the user through a means of outputting those hypotheses. The user interface is dynamically adjusted according to the user's emotional state, and information is provided in an easily digestible format. This allows the user to receive information efficiently without experiencing stress.

[0787] A concrete example would be a user considering "reducing their marketing budget." If the server recognizes the user's stress level through emotion analysis, it will automatically generate a relaxing interface and prioritize presenting easily understandable content.

[0788] The following is an example of a prompt message to input into the generating AI model.

[0789] "Analyze the emotional state of the user, determine which data should be prioritized, and generate appropriate hypotheses."

[0790] In this way, the system can more effectively support companies in reducing costs and developing strategies.

[0791] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0792] Step 1:

[0793] Users input information about their company's challenges and expected outcomes into a terminal. The terminal receives the data entered using a touchscreen or keyboard. The entered information is then transmitted to a server as digital data.

[0794] Step 2:

[0795] The server generates hypotheses using artificial intelligence based on the received user data. Here, the server uses a generation AI model, referencing industry databases and historical training data. Data processing involves extracting relevant information from the input data and creating new hypotheses through machine learning algorithms. The generated hypotheses are then presented to the user in the next stage.

[0796] Step 3:

[0797] The server analyzes the user's emotional state in real time from their input data and behavior during operation using emotion analysis tools. Natural language processing techniques are used to analyze the input data's text and speech to determine the user's emotions. The results of the emotion analysis are used to adjust parameters in hypothesis generation.

[0798] Step 4:

[0799] The server dynamically adjusts the parameters for hypothesis generation based on the results obtained from sentiment analysis. This ensures that the generated hypotheses are appropriate to the user's emotional state. The adjusted hypotheses are then presented in a way that is more acceptable and easier for the user to understand.

[0800] Step 5:

[0801] The terminal displays generated hypotheses sent from the server as suggestions in the user interface. The interface design is dynamically adjusted according to the user's emotional state; for example, relaxing colors and fonts are adopted. This reduces stress and improves receptivity.

[0802] Step 6:

[0803] If necessary, the server activates methods for collecting other users' case data, gathering relevant cases from external databases and publicly available information. This case data is analyzed and presented to the user in visual or text format. Based on the sentiment analysis results, the presentation order and format are also dynamically adjusted.

[0804] Step 7:

[0805] The server performs a return on investment (ROI) simulation for the hypotheses and strategies selected by the user. Economic data analysis algorithms are used for the simulation data calculations, and the derived results are fed back to the user visually or as text via the terminal.

[0806] (Application Example 2)

[0807] 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".

[0808] In modern cities, efficiently providing public services and increasing citizen satisfaction are crucial challenges. However, conventional systems struggle to generate flexible proposals and provide information that take into account citizens' emotional states. Therefore, it is necessary to support optimized decision-making in citizen-proposed reservations and usage plans for public facilities.

[0809] 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.

[0810] In this invention, the server includes information acquisition means, machine learning means, display means, information collection means, analysis means, evaluation means, sentiment analysis means, and adaptation means. This makes it possible to analyze the emotional state of citizens in real time and customize suggestions based on the results, thereby supporting the provision of optimal public services.

[0811] "Information acquisition means" refers to a device or process for collecting user input information and using it as basic data for processing.

[0812] "Machine learning methods" refer to algorithms or techniques used to automatically generate hypotheses based on collected information.

[0813] A "display means" is an interface for visually presenting the results of analysis or simulation to the user.

[0814] "Information gathering means" refers to the process or device for collecting necessary data from external information management systems or publicly available information.

[0815] "Analysis methods" refer to techniques or processes for analyzing collected data and extracting specific insights or patterns.

[0816] "Evaluation means" refers to a device or process for simulating return on investment and other performance indicators, and for evaluating the results.

[0817] "Emotional analysis means" refers to technology or devices for recognizing and analyzing a user's emotional state from their facial expressions, voice, etc.

[0818] "Adaptive measures" refer to technologies or processes that dynamically adjust system parameters in response to emotion analysis results to provide the user with the optimal outcome.

[0819] To realize this invention, the server executes a series of programs. Information acquisition means collects suggested information related to public services from user terminals. Machine learning means generates hypotheses based on the collected information. In this process, advanced suggestions become possible by referring to the data aggregation system and past learning results.

[0820] The server analyzes user emotions in real time from collected facial expressions and voices using emotion analysis tools. The analysis results are used to dynamically adjust the parameters of the hypothesis generation tool through an adaptation tool. Specifically, it is expected that an emotion engine (e.g., Microsoft Azure's Emotion API) will be used.

[0821] The display means visually presents hypotheses and analysis results to the user. Here, the user is supported in making appropriate decisions based on information customized according to their emotions.

[0822] The information gathering means collects relevant data using external information management systems and publicly available information, and this data is analyzed by the analysis means. The evaluation means simulates and outputs the return on investment of the proposed hypothesis.

[0823] As a concrete example, when suggesting the efficient use of public facilities, users can respond to the suggestions, and the system will customize the suggestions based on their feedback. An example of a prompt message might be, "When formulating plans for the use of public facilities proposed by citizens, please consider citizens' feelings and customize the suggestions to reduce stress."

[0824] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0825] Step 1:

[0826] The terminal collects suggested information and related requests entered by the user using information acquisition means. The entered information is sent to the server and stored as basic data for hypothesis generation.

[0827] Step 2:

[0828] The server generates hypotheses using machine learning methods based on the received information. It references user input, data aggregation systems, and past learning results, and uses a generative AI model to output hypotheses suitable for the proposal.

[0829] Step 3:

[0830] The device collects the user's facial expressions and voice information and analyzes it using emotion analysis tools. The facial expressions and voice, as input data, are processed to identify the emotional state, and the result is output as the emotional state.

[0831] Step 4:

[0832] Based on the results of the emotion analysis, the server dynamically adjusts the parameters of the hypothesis generation mechanism using adaptive means. This regenerates the optimal hypothesis according to the user's emotions, and the adjusted hypothesis is output.

[0833] Step 5:

[0834] The server uses information gathering tools to collect supplementary data from external information management systems. The collected data is analyzed by analytical tools and output as insights to refine the proposed content.

[0835] Step 6:

[0836] The server simulates the return on investment of hypotheses generated using evaluation tools. Based on the generated hypotheses and supplementary data as input data, evaluation calculations are performed and the simulation results are output.

[0837] Step 7:

[0838] The terminal visually and dynamically presents the final proposal and simulation results to the user through a display device. The results are customized and displayed in a format that is easy for the user to understand.

[0839] 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.

[0840] 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.

[0841] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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."

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] The following is further disclosed regarding the embodiments described above.

[0861] (Claim 1)

[0862] Information input means and

[0863] An artificial intelligence means for generating hypotheses based on the aforementioned information,

[0864] A means for outputting the generated hypothesis,

[0865] Means of collecting examples from others,

[0866] The means for analyzing the aforementioned cases of others,

[0867] Methods for simulating return on investment,

[0868] A system including means for outputting the aforementioned simulation results.

[0869] (Claim 2)

[0870] The system according to claim 1, wherein the hypothesis generation means generates hypotheses by referring to an industry database and past learning data.

[0871] (Claim 3)

[0872] The system according to claim 1, wherein the means for collecting other people's case studies collects other people's case studies using an external database and publicly available information.

[0873] "Example 1"

[0874] (Claim 1)

[0875] Information input means and

[0876] An artificial intelligence means for generating hypotheses based on the aforementioned information,

[0877] A means for outputting the generated hypothesis,

[0878] Means of collecting examples from others,

[0879] The means for analyzing the aforementioned cases of others,

[0880] A means of simulating the return on investment using historical data and statistical models to make predictions regarding specific reduction proposals,

[0881] A system including means for visualizing and outputting the aforementioned simulation results.

[0882] (Claim 2)

[0883] The system according to claim 1, wherein the hypothesis generation means constructs a hypothesis based on industrial data and past reference information.

[0884] (Claim 3)

[0885] The system according to claim 1, wherein the means for collecting other people's case studies obtains other people's case studies using external information sources and publicly available data.

[0886] "Application Example 1"

[0887] (Claim 1)

[0888] Information gathering methods,

[0889] A knowledge processing means for generating hypotheses based on the aforementioned information,

[0890] A display means for outputting the generated hypothesis,

[0891] Information gathering methods for collecting examples from others,

[0892] The aforementioned data processing means for analyzing the cases of others,

[0893] An evaluation method for simulating the ratio of resources input to results,

[0894] A presentation means for outputting the aforementioned simulation results,

[0895] An information input means that inputs usage information and consumption information of operational machinery and presents methods for improving operations using a knowledge processing means,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The system according to claim 1, wherein the hypothesis generation means generates hypotheses by referring to an industrial database and past analysis data.

[0899] (Claim 3)

[0900] The system according to claim 1, wherein the means for collecting other people's case studies collects other people's case studies using external information sources and publicly available information.

[0901] "Example 2 of combining an emotion engine"

[0902] (Claim 1)

[0903] Information input means and

[0904] An artificial intelligence means for generating hypotheses based on the aforementioned information,

[0905] A means for outputting the generated hypothesis,

[0906] Means of collecting examples from others,

[0907] The means for analyzing the aforementioned cases of others,

[0908] Methods for simulating return on investment,

[0909] Means for outputting the aforementioned simulation results,

[0910] A sentiment analysis method that analyzes the user's emotional state in real time,

[0911] Means for adjusting the parameters of the hypothesis generation means based on the emotional state,

[0912] A system including means for dynamically adjusting the user interface according to the emotional state.

[0913] (Claim 2)

[0914] The system according to claim 1, wherein the hypothesis generation means generates hypotheses by referring to an industry database and past learning data.

[0915] (Claim 3)

[0916] The system according to claim 1, wherein the means for collecting other people's case studies collects other people's case studies using an external database and publicly available information.

[0917] "Application example 2 when combining with an emotional engine"

[0918] (Claim 1)

[0919] Means of obtaining information,

[0920] A machine learning means for generating hypotheses based on the aforementioned information,

[0921] A display means for outputting the generated hypothesis,

[0922] Information gathering methods for collecting examples from others,

[0923] The aforementioned analytical means for analyzing the cases of others,

[0924] Evaluation methods for simulating return on investment,

[0925] A display means for outputting the evaluation results,

[0926] A means of sentiment analysis that recognizes and analyzes the emotional state of a user,

[0927] An adaptive means for adjusting the parameters of the hypothesis generation means based on the emotion analysis results,

[0928] A system that includes this.

[0929] (Claim 2)

[0930] The system according to claim 1, wherein the hypothesis generation means generates hypotheses by referring to a data collection system and past learning results.

[0931] (Claim 3)

[0932] The system according to claim 1, wherein the means for collecting other people's case studies collects other people's case studies using an external information management system and publicly available information. [Explanation of symbols]

[0933] 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. Information input means and An artificial intelligence means for generating hypotheses based on the aforementioned information, A means for outputting the generated hypothesis, Means of collecting examples from others, The means for analyzing the aforementioned cases of others, Methods for simulating return on investment, A system including means for outputting the aforementioned simulation results.

2. The system according to claim 1, wherein the hypothesis generation means generates hypotheses by referring to an industry database and past learning data.

3. The system according to claim 1, wherein the means for collecting other people's case studies collects other people's case studies using an external database and publicly available information.

Images