System

Abstract

A system is provided.SOLUTION: The system includes a means for receiving a user input, a terminal means for converting the user input into a data format and transmitting it, a server means for analyzing the received data, a means for generating an answer based on the analysis result, a means for transmitting the answer to the terminal, and a means for displaying the answer to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's business environment, rapid and accurate analysis of financial data and feedback on the results are extremely important. However, traditional manual data entry and analysis methods require a lot of time and effort, and are prone to errors, especially when processing large amounts of data. Furthermore, if you lack the necessary data analysis expertise, it can be difficult to obtain appropriate analysis results and recommendations. For this reason, there is a need for the development of a system that allows anyone to easily analyze their financial data and receive appropriate recommendations. [Means for solving the problem]

[0005] The present invention provides a system including a means for receiving user input, a terminal means for converting the user input into a data format and transmitting it, a server means for analyzing the received data, a means for generating an answer based on the analysis results, a means for transmitting the answer to the terminal, and a means for displaying the answer to the user. The server means analyzes the data using a machine learning model, and the answer generation means generates a proposal based on business logic, thereby enabling fast and accurate data analysis and feedback. Furthermore, by automating the entire process from data input to display of results, time and effort are significantly reduced, making the system easy to use even for users lacking specialized knowledge. Furthermore, by including a means for validating the received data, the accuracy and reliability of the data can be ensured, and highly accurate analysis results can be provided.

[0006] "User input" refers to data or questions provided by users of the system.

[0007] "Data format" refers to the way data is represented according to a particular structure or protocol.

[0008] "Terminal" refers to a device through which a user accesses and operates the system.

[0009] "Server" means a central computer system that receives, processes, stores, and analyzes data.

[0010] "Analysis" refers to the process of examining input data and deriving meaningful information or conclusions.

[0011] "Answer" refers to a generated answer or suggestion in response to a user's input or question.

[0012] A "machine learning model" refers to an algorithm that is trained on large amounts of data to automatically perform specific tasks.

[0013] "Business logic" refers to processing rules and calculation methods based on specific business processes and workflows.

[0014] "Validation" refers to the process of verifying that data adheres to the correct structure and format and meets required conditions.

[0015] "Feedback" refers to the results or information that a system provides to the user. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

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

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

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

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

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

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0037] The present invention relates to a system that receives user input, analyzes the data, and provides a fast and accurate answer. The system includes a terminal operated by the user and a server that processes and analyzes the data.

[0038] User Input

[0039] Users use devices (such as PCs or smartphones) to input financial data and information related to business plans. For example, if a user wants to know the "sales forecast for the next fiscal year," they input past sales data and market conditions.

[0040] Data transmission

[0041] The device converts the input information into an appropriate format (e.g., JSON) and sends it to the server, which then receives the data and prepares to begin analyzing it.

[0042] Data analysis

[0043] The server validates the received data and analyzes it using machine learning models. Specifically, the server uses revenue forecasting models and cost management models to predict future revenues and costs. This analysis uses Python machine learning libraries (e.g., TENSORFLOW (registered trademark) and Scikit-learn).

[0044] Answer generation

[0045] The server generates answers or recommendations for the user based on the analysis results. At this stage, business logic is applied to generate specific recommendations (e.g., "Increase your marketing budget by 5%)."

[0046] Sending and displaying results

[0047] The server then converts the generated results back into JSON format and sends them to the device, which then parses the results and displays them in a user-friendly format, such as in a graph or table on the browser.

[0048] Specific examples

[0049] For example, if a user enters "Please prepare the income statement for next fiscal year," the flow is as follows:

[0050] 1. User: Enters bank transaction data, budget data, etc.

[0051] 2. Terminal: Converts input data into JSON format and sends it to the server.

[0052] 3. Server: Validates and analyzes the data received, e.g., generates a profit and loss statement based on sales, costs, operating expenses, etc.

[0053] 4. Server: Based on the analysis results, generate a profit and loss statement and send it to the terminal in JSON format.

[0054] 5. Terminal: Parses the received results and displays the P&L to the user.

[0055] In this way, the system generates and provides users with fast and accurate answers and suggestions based on the data they input, making the entire process from data entry to analysis and display of results efficient.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] Users input data from their terminals. For example, they might type, "Please tell me your sales forecast for next fiscal year," and then enter past sales data and market conditions.

[0059] Step 2:

[0060] The device converts the information entered by the user into JSON format and sends it to the server using an HTTP POST request.

[0061] Step 3:

[0062] The server receives the data sent from the terminal. Specifically, it deserializes the received JSON data and converts it into an object format.

[0063] Step 4:

[0064] The server validates the received data by checking whether the data format is correct, whether any items are missing, and whether the values ​​are appropriate.

[0065] Step 5:

[0066] The server then performs analysis on the validated data using a pre-trained machine learning model, such as a sales forecasting model.

[0067] Step 6:

[0068] The server generates a response based on the analysis results, such as a specific recommendation like "increase the marketing budget by 5%" based on business logic.

[0069] Step 7:

[0070] The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[0071] Step 8:

[0072] The device parses the JSON data received from the server and displays the results to the user, for example, in a browser in the form of a graph or table.

[0073] Step 9:

[0074] The user reviews the displayed results, asks more questions or enters more data if necessary, and steps 1 through 8 are repeated again.

[0075] Example 1

[0076] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0077] In today's business environment, there is a demand for the rapid and accurate analysis of large amounts of data and the provision of specific proposals. However, with existing systems, the process from data input to analysis and display of results is complex and time-consuming. Furthermore, the analytical precision and specificity of proposals are often insufficient. Therefore, there is a need for the development of an efficient and highly accurate data analysis system.

[0078] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0079] In this invention, the server includes a means for validating received data, a means for analyzing the validated data using a machine learning model, and a means for generating answers based on the analysis results, thereby enabling the server to quickly and accurately analyze data and provide specific suggestions to users.

[0080] "User input" means data entered by a user of the system using a terminal.

[0081] A "terminal" is a device that a user uses to access the system and input or display information, including, for example, a personal computer or smartphone.

[0082] The "Server" is the main component of the system that processes and analyzes data received from users and generates answers and suggestions.

[0083] Validation is the process of ensuring that received data is accurate and complete, including checking for required fields and validating the data format.

[0084] A "machine learning model" is an algorithm that learns from large amounts of data, extracts patterns and relationships from that data, and makes predictions and analyses.

[0085] "Analysis results" are the outputs or conclusions obtained after processing data using a machine learning model.

[0086] "Answer generation" is the process of creating answers or suggestions to provide to users based on the analysis results.

[0087] "Business logic" refers to the processing procedures and decision-making criteria that are specific to a specific business or industry, and is used to generate specific proposals and action plans for users.

[0088] A "Python machine learning library" is a library for machine learning used in the Python programming language, with representative examples being TensorFlow and Scikit-learn.

[0089] The present invention relates to a system that receives user input, analyzes the data, and provides fast and accurate answers and suggestions. The system includes a terminal operated by the user and a server that processes and analyzes the data.

[0090] Users use devices (e.g., PCs or smartphones) to input financial data and business plan information, for example, by entering a prompt such as "I would like to know the sales forecast for the next fiscal year," and provide past sales data and market conditions.

[0091] The terminal converts the input information into JSON format and sends it to the server via HTTPS. The server first validates the received data. Validation is performed using a Python data validation library (e.g., Cerberus) and includes checking for required fields and validating the data format.

[0092] For data that has been successfully validated, the server applies machine learning models. Specifically, it uses revenue forecasting models and cost management models to analyze the data using Python machine learning libraries (TensorFlow and Scikit-learn). For example, this can predict next fiscal year's sales based on past sales data and market conditions.

[0093] The server then generates a specific answer or recommendation for the user based on the analysis results, where business logic is applied to generate a specific action plan, such as "increase your marketing budget by 5%."

[0094] The server then converts the generated answers and suggestions back into JSON format and sends them to the device, which parses the results and displays them in a user-friendly format (e.g., graphs or tables).

[0095] For example, if a user requests "Please prepare the income statement for the next fiscal year," the flow is as follows:

[0096] The user inputs banking data or budget data. For example, a prompt such as "Please generate a profit and loss statement for 2023" is used. The terminal converts the input data into JSON format and sends it to the server. The server validates the data and uses machine learning models to generate a profit and loss statement based on sales, costs, operating expenses, etc. The server then sends the generated profit and loss statement in JSON format to the terminal, which parses the results and displays them to the user. For example, the profit and loss statement can be visually displayed using bar graphs or pie charts.

[0097] In this way, the system generates and provides users with fast and accurate answers and suggestions based on the data they enter, making the entire process from data entry to analysis and display of results efficient.

[0098] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0099] Step 1: User Input

[0100] The user uses a device (PC or smartphone) to input financial data and information about the business plan. For example, they input a prompt in text format such as, "I would like to know the sales forecast for next fiscal year." The information input includes past sales data and market conditions. The data provided by the user is sent to the device.

[0101] Step 2: Send data

[0102] The device converts the information entered by the user into JSON format. This conversion process ensures that the input data is properly formatted. The device then sends the JSON data to the server using HTTPS, which encrypts the data in transit and ensures a secure transfer.

[0103] Step 3: Data Receipt and Validation

[0104] The server receives the JSON data sent from the terminal. It validates the received data using a Python data validation library (for example, Cerberus). The purpose of validation is to check whether all required fields are filled in and whether the data format is correct. For example, if sales data is missing, an error message is generated. If validation is successful, the data proceeds to the parsing step.

[0105] Step 4: Data analysis

[0106] The server applies machine learning models to data that has passed validation. Specifically, it uses Python machine learning libraries (TensorFlow and Scikit-learn) to create revenue forecasting models and cost management models. In the analysis process, past sales data and market conditions are used as input data to predict future revenue and costs. For example, sales data from the past five years is used as input, and the output is a sales forecast for the next fiscal year.

[0107] Step 5: Answer Generation

[0108] The server generates specific answers and recommendations to provide to the user based on the analysis results. In this step, business logic is applied to derive the most beneficial recommendation for the user. For example, a specific recommendation such as "increase your marketing budget by 5%" is generated. The generated answers and recommendations are then converted back to JSON format.

[0109] Step 6: Send results

[0110] The server then converts the answers and suggestions into JSON format and sends them to the device. Again, data is encrypted during transmission and securely transferred. The server uses HTTPS to ensure confidentiality and integrity of the data.

[0111] Step 7: View the results

[0112] The terminal parses the JSON data received from the server and displays it in a user-friendly format. Specifically, it visualizes the results in graphs and tables on a web browser. For example, it displays the sales forecast results as a bar graph and the cost structure as a pie chart.

[0113] In this way, the user, terminal, and server work together at each step, enabling efficient processing from user input to analysis and display of results.

[0114] (Application example 1)

[0115] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0116] Conventional product recommendation systems for brick-and-mortar stores have struggled to effectively utilize users' purchasing history, reviews, inventory information, and other data to provide optimal product recommendations for each individual user. Furthermore, real-time data analysis and rapid feedback are required to improve the user experience in brick-and-mortar stores. However, existing systems were unable to meet these requirements.

[0117] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0118] In this invention, the server includes means for receiving user input, terminal means for converting the user input into a data format and transmitting it, means for analyzing the received data, means for generating a response based on the analysis result, means for transmitting the response to the terminal, means for displaying the response to the user, and means for reviewing the user input in the store and optimizing product suggestions based on data including purchase history and inventory information. This makes it possible to realize optimal product suggestions and promotions and provide real-time feedback in physical stores based on users' purchase history, reviews, and inventory information.

[0119] "User input" means information or data provided by a user to a system.

[0120] "Terminal means" refers to a device that processes data entered by a user, converts it into an appropriate format, and transmits it to the server.

[0121] The "server means" refers to a computer that analyzes the received data and generates a response based on the results.

[0122] The "analysis result" refers to the result obtained by the server means processing the data.

[0123] "Answer generation" refers to the process of creating feedback and suggestions for users based on the analysis results.

[0124] "Display means" refers to a device or method for visually presenting the generated answer to the user.

[0125] "Means for optimization" refers to a mechanism for processing product suggestions provided based on user-entered data in a way that is most beneficial to the user.

[0126] A "machine learning model" is a model that uses algorithms to make predictions and classifications based on large amounts of data.

[0127] "Business logic" refers to the standards and methods that guide rational decisions and actions in commercial activities.

[0128] The system of the present invention receives user input, analyzes the received data, and provides an optimal answer. An embodiment of the system will be described in detail below.

[0129] First, a user uses a device such as a smartphone or tablet to input information such as purchase history, product reviews, and the current contents of their cart. This device converts the input user information into an appropriate data format (e.g., JSON format) and sends the data to the server.

[0130] The server receives and analyzes the transmitted data. A machine learning model built using Python machine learning libraries (e.g., TensorFlow and Scikit-Learn) is installed on the server. This machine learning model learns user preferences and purchasing patterns based on past data, and generates optimal product suggestions and promotions for new data.

[0131] Based on the analysis results, the server generates an answer for the user. Business logic is applied to this answer generation process to create the most useful suggestions for the user. For example, the server may analyze the user's preferred product categories based on their purchase history and reviews, and prioritize suggestions for products in those categories.

[0132] The server then converts the generated response back into JSON format and sends it to the device, which parses the results and displays them visually to the user, typically in the form of graphs and tables showing product suggestions and promotional information.

[0133] This system allows for quick and accurate product suggestions in physical stores based on users' purchasing history, reviews, and inventory information.

[0134] Specific examples

[0135] Example 1: When a user scans an item in a store, the system will suggest the most suitable product based on their past purchase history and reviews.

[0136] Prompt: "Please suggest my next purchase based on past electronics purchase data."

[0137] Example 2: Based on inventory information, notify customers to purchase low-stock items as soon as possible.

[0138] Prompt: "Based on your inventory data, which item would you suggest this customer purchase sooner?"

[0139] To implement this invention, the following hardware and software are required:

[0140] Hardware: smartphones, tablets, servers

[0141] Software: Python, TensorFlow, Scikit-Learn, JSON parser, web framework (e.g., Flask, Django)

[0142] These configurations enable efficient data entry by users, analysis, generation of results, and display.

[0143] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0144] Step 1:

[0145] The user uses a smartphone or tablet to enter purchase history, product reviews, and current cart contents.

[0146] Specific operation: The user enters their purchase history, product reviews, and product information in the cart into the application's input form. This data is automatically saved in the input fields.

[0147] Input: Raw data entered by users such as purchase history, product reviews, and cart contents.

[0148] Output: The raw data that is passed to the next step.

[0149] Step 2:

[0150] The terminal converts the entered user information into JSON format and sends it to the server.

[0151] Specific operation: The terminal application retrieves data from the input field, and a parser runs to convert it to JSON format. The converted data is then sent to the server as an HTTP request.

[0152] Input: Raw data from the user.

[0153] Output: Data converted to JSON format.

[0154] Step 3:

[0155] The server receives the transmitted data and performs data validation.

[0156] Specific operation: The API receives an HTTP request on the server side, applies validation rules to check the format and content of the received data, and filters out invalid data.

[0157] Input: JSON data sent from the terminal.

[0158] Output: Clean data that passes validation.

[0159] Step 4:

[0160] The server uses machine learning models to analyze the data that passes validation.

[0161] How it works: Using Python libraries (TensorFlow or Scikit-Learn), the clean data is analyzed. Machine learning models predict purchasing patterns and user preferences and identify the next best product, taking into account the user's past behavior and external market data.

[0162] Input: Clean data after validation.

[0163] Output: Suggested products and promotions as analysis results.

[0164] Step 5:

[0165] Based on the analysis results, the server applies business logic to generate the optimal answer for the user.

[0166] What it does: Based on the analysis results, specific business logic (for example, a strategy aimed at increasing sales in a specific product category) is applied, and optimized product suggestions and promotions are generated in text format.

[0167] Input: Analysis results of machine learning models.

[0168] Output: Optimized answers (product suggestions and promotions) with business logic applied.

[0169] Step 6:

[0170] The server converts the generated response back into JSON format and sends it to the terminal.

[0171] Specific operation: The API operates to encode the text response generated by the server into JSON format and send it to the terminal as an HTTP response.

[0172] Input: The answer generated by applying business logic.

[0173] Output: The answer converted to JSON format.

[0174] Step 7:

[0175] The terminal receives the transmitted results and displays them to the user in a visually understandable manner.

[0176] What happens: The device application receives the HTTP response, decodes the data using a JSON parser, and displays it to the user in the form of a graph or table.

[0177] Input: The JSON response sent by the server.

[0178] Output: Offers and promotions visually displayed to the user.

[0179] In this way, the data entered by the user is analyzed efficiently, and optimal product suggestions and promotions are realized.

[0180] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0181] This invention relates to a system that receives user input, analyzes the data, and provides fast and accurate responses. This system includes a terminal operated by the user and a server that processes and analyzes the data. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, more personalized responses are possible.

[0182] User Input

[0183] A user uses a device (such as a PC or smartphone) to input financial data and information about a business plan and request an analysis. For example, the user might input "Please tell me the sales forecast for next fiscal year," and then input past sales data and market conditions. In this case, the device recognizes not only the data entered by the user, but also the user's emotions.

[0184] emotion recognition

[0185] The device uses natural language processing and machine learning to recognize emotions from users' text inputs and voices, and the emotion engine generates user emotion data along with the input data.

[0186] Data transmission

[0187] The device converts the input information, including the recognized emotion data, into JSON format and sends it to the server using an HTTP POST request. The server receives this data and is ready to begin analysis.

[0188] Data analysis

[0189] The server validates the received data and analyzes it using machine learning models, such as revenue forecasting and cost management models, to predict future revenues and costs. This analysis uses Python machine learning libraries (e.g., TensorFlow and Scikit-learn).

[0190] Emotion-based answer generation

[0191] The server takes the emotion engine's output into account when generating answers and suggestions for the user based on the analysis results. For example, if it recognizes that the user is feeling stressed, it will provide a simpler suggestion with less emphasis. It then applies business logic to generate a specific suggestion (e.g., "Increase your marketing budget by 5%)."

[0192] Sending and displaying results

[0193] The server converts the generated results back into JSON format and sends them to the terminal as an HTTP response. The terminal parses the received results and displays them in a user-friendly format, for example, in a graph or table format on the browser.

[0194] Specific examples

[0195] For example, if a user enters "Please prepare the income statement for next fiscal year," the flow is as follows:

[0196] 1. User: Enters banking data, budget data, etc., while the system recognizes the user's emotions.

[0197] 2. Terminal: Converts input data and recognized emotion data into JSON format and sends it to the server.

[0198] 3. Server: Validates and analyzes the data received, e.g., generates a profit and loss statement based on sales, costs, operating expenses, etc.

[0199] 4. Server: Based on the analysis results, generate a profit and loss statement taking into account the user's emotions and make recommendations with the appropriate tone and level of detail.

[0200] 5. Server: Sends the generated results to the device.

[0201] 6. Terminal: Parses the received results and displays the P&L to the user.

[0202] In this way, the system generates and provides users with fast and accurate answers and suggestions based on the user's input data and emotional data, thereby efficiently carrying out the entire process from data input to analysis and display of results, and providing personalized services that respond to the user's emotions.

[0203] The processing flow will be explained below.

[0204] Step 1:

[0205] The user inputs data into the device. For example, they might type, "Please tell me your sales forecast for next fiscal year," and then enter past sales data and market conditions. At this time, the device recognizes emotions from the user's text input and voice.

[0206] Step 2:

[0207] The device converts the information entered by the user into JSON format, attaches the recognized emotion data, and sends it to the server as an HTTP POST request.

[0208] Step 3:

[0209] The server receives the data sent from the terminal. Specifically, it deserializes the received JSON data and converts it into an object format.

[0210] Step 4:

[0211] The server validates the received data by checking whether the data format is correct, whether any items are missing, and whether the values ​​are appropriate.

[0212] Step 5:

[0213] The server then performs analysis using the validated data, using a pre-trained machine learning model, such as a sales forecasting model.

[0214] Step 6:

[0215] The server adjusts its analysis based on the output of the emotion engine, for example softening the tone of suggestions and feedback if the user is feeling stressed.

[0216] Step 7:

[0217] The server generates specific proposals based on business logic, such as "increase marketing budget by 5%."

[0218] Step 8:

[0219] The server converts the generated response back into JSON format and sends it to the terminal as an HTTP response.

[0220] Step 9:

[0221] The device parses the JSON data received from the server and displays the results to the user, for example, in a browser in the form of a graph or table.

[0222] Step 10:

[0223] The user reviews the displayed results and enters further questions or data as needed, in which case steps 1 through 9 are repeated again.

[0224] Example 2

[0225] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0226] Conventional systems have difficulty considering the user's emotions when analyzing user input and generating answers, resulting in impersonal responses. Furthermore, they lack personalized responses based on the user's emotional state, making it difficult to improve the user experience.

[0227] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes terminal means for converting a user's input into a data format and generating emotion data, means for transmitting input information including the recognized emotion data to the server, means for validating the received data, means for analyzing the data using a machine learning model, and means for generating a response according to the emotion based on the analysis result. This enables a personalized response that takes the user's emotion into consideration.

[0228] "User input" means information or data provided by a user to a system through a terminal.

[0229] "Terminal means" refers to a device or software that receives input from a user, converts it into a data format, and generates emotion data as needed.

[0230] "Emotional data" refers to information that represents a user's emotional state as recognized from the user's input.

[0231] "Server means" refers to devices and software that receive data sent from a terminal and process and analyze it.

[0232] "Validation" is the process of verifying that the format and content of received data are correct.

[0233] A "machine learning model" is a mathematical and statistical model that learns patterns and knowledge from data and performs analysis and predictions.

[0234] "Analysis Results" means the results obtained after processing and analyzing data using a machine learning model.

[0235] "Answer generation means" refers to a device or software that generates an answer to be provided to the user based on the analysis results.

[0236] This invention relates to a system that receives user input, analyzes the data, and provides fast and accurate responses. The system includes a terminal operated by the user and a server that processes and analyzes the data. It also incorporates an emotion engine that recognizes the user's emotions, enabling more personalized responses.

[0237] User Input

[0238] A user uses a device (such as a PC or smartphone) to input financial data and information about a business plan and request an analysis. For example, the user might type, "Please tell me the sales forecast for next fiscal year," and then input past sales data and market conditions into the device. In this case, the device recognizes not only the data entered by the user, but also the user's emotions.

[0239] emotion recognition

[0240] The device uses SpaCy, a natural language processing (NLP) library, to analyze the user's text input. In addition, when voice input is performed, the device converts the voice data into text using a speech recognition library (e.g., Google® Speech-to-Text API). The device then recognizes the user's emotions using the NLP analysis results and a machine learning model (e.g., Scikit-learn's emotion classification model). The emotion engine generates user emotion data in conjunction with the input data.

[0241] Data transmission

[0242] The device converts the input information, including the recognized emotion data, into JSON format and sends it to the server using an HTTP POST request. For example, it generates the following JSON data:

[0243] json

[0244] {

[0245] "user_input": "Please tell us your sales forecast for next fiscal year",

[0246] "sentiment": "anxiety"

[0247] }

[0248] Send this data through a RESTful API.

[0249] Data analysis

[0250] The server validates the received data. First, it checks whether the input data and sentiment data are correctly formatted. If validation is successful, the server analyzes the data using a machine learning model (e.g., a model using TensorFlow). For example, it predicts future sales based on past sales data and market conditions.

[0251] Emotion-based answer generation

[0252] The server takes the output of the emotion engine into consideration when generating answers and suggestions for the user based on the analysis results. For example, if the user is feeling anxious, it will generate a message in a simple language that gives a sense of security. Specifically, it will generate a sentence such as, "Sales forecast for next fiscal year is 5 million yen. Don't worry, everything is going well."

[0253] Sending and displaying results

[0254] The server then converts the generated results back into JSON format and sends them to the device as an HTTP response. The device then parses the results and displays them in a user-friendly format. For example, the browser might display sales forecasts in graphs and tables, along with personalized messages based on user sentiment.

[0255] Specific examples

[0256] For example, if a user types "Please prepare the income statement for next period," the flow would be as follows:

[0257] 1. User: Enters banking data, budget data, etc. The system recognizes the user's emotions.

[0258] 2. Terminal: Converts input data and recognized emotion data into JSON format and sends it to the server.

[0259] 3. Server: Validates and analyzes the data received, e.g., generates a profit and loss statement based on sales, costs, operating expenses, etc.

[0260] 4. Server: Based on the analysis results, generate a profit and loss statement taking into account the user's emotions and make recommendations with the appropriate tone and level of detail.

[0261] 5. Server: Sends the generated results to the device.

[0262] 6. Terminal: Parses the received results and displays the P&L to the user.

[0263] Example prompt sentence:

[0264] "What are your sales forecasts for next fiscal year? Last year's sales data and market conditions are as follows: [data]."

[0265] This series of processes enables the system to provide fast and accurate answers and suggestions based on the user's input data and emotional data, thereby efficiently carrying out the entire process from data input to analysis and display of results, while also providing personalized services that respond to the user's emotions.

[0266] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0267] Step 1:

[0268] Receiving user input

[0269] Users use devices (such as PCs or smartphones) to input financial data and information about business plans. Examples of input content include, "Please tell me your sales forecast for next fiscal year." The data entered by users is stored in text format on the device.

[0270] Input: User text input

[0271] Output: Saved user text data

[0272] Step 2:

[0273] Performing emotion recognition

[0274] The device uses the natural language processing (NLP) library SpaCy to analyze the user's text input. It also converts voice input into text using a speech recognition library (e.g., Google Speech-to-Text API). It then uses the NLP analysis results and a machine learning model (e.g., Scikit-learn's emotion classification model) to recognize the user's emotions.

[0275] Input: User text input, voice data

[0276] Output: User sentiment data

[0277] Step 3:

[0278] Data conversion and transmission

[0279] The device converts the user's input data and the recognized emotion data into JSON format. For example, it generates the following JSON data:

[0280] json

[0281] {

[0282] "user_input": "Please tell us your sales forecast for next fiscal year",

[0283] "sentiment": "anxiety"

[0284] }

[0285] The resulting JSON data is then sent to the server using an HTTP POST request.

[0286] Input: User input data, emotion data

[0287] Output: JSON data sent to the server

[0288] Step 4:

[0289] Data Validation

[0290] The server validates the data it receives. First, it checks whether the input data and emotion data are correctly formatted. The software used includes validation tools such as JSON Schema. It checks for missing data or formatting errors.

[0291] Input: Received JSON data

[0292] Output: Validation result (success or error)

[0293] Step 5:

[0294] Performing data analysis

[0295] The server begins analysis based on the successfully validated data. It uses a machine learning model (for example, a model using TensorFlow) to predict future sales based on past sales data and market conditions. Specific analysis operations include data preprocessing, feature extraction, and application of the predictive model.

[0296] Input: Data that has been successfully validated

[0297] Output: Analysis results (e.g., sales forecast for the next fiscal year)

[0298] Step 6:

[0299] Emotion-based answer generation

[0300] The server takes into account the output of the emotion engine when generating an answer to provide to the user based on the analysis results. For example, if the user is feeling anxious, it generates a simple, reassuring message. The generated answer might look like this: "Sales forecast for next fiscal year is 5 million yen. Don't worry, everything is going well."

[0301] Input: Analysis results, emotion data

[0302] Output: Sentiment-based response data

[0303] Step 7:

[0304] Sending and displaying results

[0305] The server then converts the generated response data back into JSON format and sends it to the device as an HTTP response. The device then parses the results and displays the sales forecast in a browser in graph and table format, along with a message based on the user's emotions.

[0306] Input: Response data

[0307] Output: The result displayed to the user

[0308] (Application example 2)

[0309] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0310] Conventional systems analyze data and generate suggestions based on user input, but because they do not take into account the user's emotional state, it is difficult to provide personalized advice that takes into account factors such as stress and fatigue. This is particularly true for robot operators on factory floors, who are given uniform maintenance and operation instructions without considering their emotional state, which creates a problem of not being able to optimize workload and efficiency.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0312] In this invention, the server includes means for receiving user input, means for converting the user input into a data format and transmitting it, means for analyzing the received data, means for generating an answer based on the analysis result, means for displaying the answer to the user, emotion recognition means for recognizing the user's emotional state and generating data on that, and emotion reflection means for generating an answer based on the user's emotional state, thereby enabling personalized advice and suggestions that take the user's emotional state into consideration.

[0313] "User input" refers to information or instructions provided by a user operating a system.

[0314] "Terminal means" refers to a device that converts user input into a data format and transmits and receives it.

[0315] The "server means" is a device that analyzes the received data and generates a response based on the results.

[0316] The "answer generation means" is a device that creates answers and suggestions for users based on the results of data analysis.

[0317] An "emotion recognition means" is a device that recognizes the user's emotional state and generates data on it.

[0318] The "emotion reflection means" is a device that generates answers and suggestions by reflecting the user's emotional state generated by the emotion recognition means.

[0319] "Machine Learning Model" means a machine learning algorithm or system used to perform data analysis on the server means.

[0320] "Business logic" refers to logic or rules based on specific business objectives or conditions that are used by the answer generation means.

[0321] As an embodiment of the present invention, consider a smartphone application used by a robot operator in a factory. The application is a system in which the operator inputs data about the robot's operational status and the site environment, and the data is analyzed in real time. The smartphone receives user input, converts it into a data format, and sends it to a server. The server analyzes the received data and generates a response based on the analysis results.

[0322] First, the operator inputs the robot's operating time, number of errors, vibration data, etc. into a smartphone (iOS or ANDROID (registered trademark)), and also obtains the robot's emotional state through voice input. The input data is converted into JSON format and sent to the server via an HTTP POST request. The server receives this data, validates it, and then analyzes it using a machine learning model (such as TensorFlow). Based on the analysis results, for example, if a certain number of errors or vibration level is exceeded, it will recognize that maintenance is necessary. In addition, an emotion recognition means takes into account the user's stress level and fatigue level, and generates advice and suggestions that reflect the user's emotional state.

[0323] Specifically, the system uses a front-end and back-end system written in Python. Data acquired by this system is analyzed using a machine learning model using TensorFlow to generate appropriate maintenance instructions and operation suggestions. Emotion recognition is also performed using the Google Cloud Natural Language API.

[0324] For example, if a user inputs "80 hours of operation, 5 errors, vibration level 3.2" into their smartphone and reports "stress level 2" by voice, the server will analyze these inputs. If the emotion recognition means detects a high stress state, the server will add advice such as "We recommend taking a break" in addition to suggesting maintenance based on the analysis results.

[0325] Examples of prompts for generative AI models are as follows:

[0326] Context: This is an application used by factory robot operators to provide optimal maintenance and rest instructions based on the robot's operating status and the operator's emotional state.

[0327] Question: If a robot has 80 hours of operation, has 5 errors, and the operator's stress level is 2, what maintenance instructions should be given?

[0328] These prompts can be used as input to an AI model to efficiently generate optimal maintenance and rest instructions, allowing operators to perform their work efficiently and safely.

[0329] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0330] Step 1:

[0331] The user uses a smartphone to input operational data such as the robot's operating time, number of errors, vibration data, and stress level. At the same time, an emotion recognition engine is used to obtain emotional data such as stress level from voice. The input data is in text and audio format.

[0332] Step 2:

[0333] The device converts the text data and emotion data entered by the user into JSON format. Specifically, it creates a JSON object with a dictionary-style data structure, with operating time, number of errors, vibration level, and stress level as keys. This becomes the input data for the next step.

[0334] Step 3:

[0335] The JSON data sent from the device is sent to the server using an HTTP POST request, which also includes metadata such as the user ID and timestamp to manage the data transmission and reception.

[0336] Step 4:

[0337] The server parses and validates the received JSON data. For example, it checks that the uptime is greater than or equal to zero and that the number of errors is not a negative value. Only data that passes this validation is analyzed in the next step.

[0338] Step 5:

[0339] The server inputs the validated data into a machine learning model (such as TensorFlow). The machine learning model analyzes the robot's operational data and predicts the need for maintenance, for example, if a certain number of errors or vibration levels exceed a certain standard. This analysis is based on the data the model has previously learned.

[0340] Step 6:

[0341] The server generates answers and suggestions based on the analysis results of the machine learning model. Specifically, it takes into account the analysis results as well as the user's emotional data, and adds easy-to-understand messages and instructions to take a break if the stress level is high. The answer generation means applies business logic to form specific suggestions for maintenance and operational adjustments.

[0342] Step 7:

[0343] The server then converts the generated answers and suggestions back into JSON format and sends them back to the device as an HTTP response, which includes the analysis results and sentiment-based advice.

[0344] Step 8:

[0345] The device parses the received JSON data and displays it in a user-friendly format. Specifically, it displays the results in text and graph format on the smartphone application screen, highlighting important suggestions and advice. It also uses prompts to the generative AI model to prepare for the next input.

[0346] Context: This is an application used by factory robot operators to provide optimal maintenance and rest instructions based on the robot's operating status and the operator's emotional state.

[0347] Question: If a robot has 80 hours of operation, has 5 errors, and the operator's stress level is 2, what maintenance instructions should be given?

[0348] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0349] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0350] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0351] [Second embodiment]

[0352] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0353] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0354] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0355] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0356] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0357] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0358] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0359] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0360] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0361] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0362] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0363] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0364] The present invention relates to a system that receives user input, analyzes the data, and provides a fast and accurate answer. The system includes a terminal operated by the user and a server that processes and analyzes the data.

[0365] User Input

[0366] Users use devices (such as PCs or smartphones) to input financial data and information related to business plans. For example, if a user wants to know the "sales forecast for the next fiscal year," they input past sales data and market conditions.

[0367] Data transmission

[0368] The device converts the input information into an appropriate format (e.g., JSON) and sends it to the server, which then receives the data and prepares to begin analyzing it.

[0369] Data analysis

[0370] The server validates the received data and analyzes it using machine learning models. Specifically, the server uses revenue forecasting and cost management models to predict future revenue and costs. This analysis is performed using Python machine learning libraries (e.g., TensorFlow and Scikit-learn).

[0371] Answer generation

[0372] The server generates answers or recommendations for the user based on the analysis results. At this stage, business logic is applied to generate specific recommendations (e.g., "Increase your marketing budget by 5%)."

[0373] Sending and displaying results

[0374] The server then converts the generated results back into JSON format and sends them to the device, which then parses the results and displays them in a user-friendly format, such as in a graph or table on the browser.

[0375] Specific examples

[0376] For example, if a user enters "Please prepare the income statement for next fiscal year," the flow is as follows:

[0377] 1. User: Enters bank transaction data, budget data, etc.

[0378] 2. Terminal: Converts input data into JSON format and sends it to the server.

[0379] 3. Server: Validates and analyzes the data received, e.g., generates a profit and loss statement based on sales, costs, operating expenses, etc.

[0380] 4. Server: Based on the analysis results, generate a profit and loss statement and send it to the terminal in JSON format.

[0381] 5. Terminal: Parses the received results and displays the P&L to the user.

[0382] In this way, the system generates and provides users with fast and accurate answers and suggestions based on the data they input, making the entire process from data entry to analysis and display of results efficient.

[0383] The processing flow will be explained below.

[0384] Step 1:

[0385] Users input data from their terminals. For example, they might type, "Please tell me your sales forecast for next fiscal year," and then enter past sales data and market conditions.

[0386] Step 2:

[0387] The device converts the information entered by the user into JSON format and sends it to the server using an HTTP POST request.

[0388] Step 3:

[0389] The server receives the data sent from the terminal. Specifically, it deserializes the received JSON data and converts it into an object format.

[0390] Step 4:

[0391] The server validates the received data by checking whether the data format is correct, whether any items are missing, and whether the values ​​are appropriate.

[0392] Step 5:

[0393] The server then performs analysis on the validated data using a pre-trained machine learning model, such as a sales forecasting model.

[0394] Step 6:

[0395] The server generates a response based on the analysis results, such as a specific recommendation like "increase the marketing budget by 5%" based on business logic.

[0396] Step 7:

[0397] The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[0398] Step 8:

[0399] The device parses the JSON data received from the server and displays the results to the user, for example, in a browser in the form of a graph or table.

[0400] Step 9:

[0401] The user reviews the displayed results, asks more questions or enters more data if necessary, and steps 1 through 8 are repeated again.

[0402] Example 1

[0403] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0404] In today's business environment, there is a demand for the rapid and accurate analysis of large amounts of data and the provision of specific proposals. However, with existing systems, the process from data input to analysis and display of results is complex and time-consuming. Furthermore, the analytical precision and specificity of proposals are often insufficient. Therefore, there is a need for the development of an efficient and highly accurate data analysis system.

[0405] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0406] In this invention, the server includes a means for validating received data, a means for analyzing the validated data using a machine learning model, and a means for generating answers based on the analysis results, thereby enabling the server to quickly and accurately analyze data and provide specific suggestions to users.

[0407] "User input" means data entered by a user of the system using a terminal.

[0408] A "terminal" is a device that a user uses to access the system and input or display information, including, for example, a personal computer or smartphone.

[0409] The "Server" is the main component of the system that processes and analyzes data received from users and generates answers and suggestions.

[0410] Validation is the process of ensuring that received data is accurate and complete, including checking for required fields and validating the data format.

[0411] A "machine learning model" is an algorithm that learns from large amounts of data, extracts patterns and relationships from that data, and makes predictions and analyses.

[0412] "Analysis results" are the outputs or conclusions obtained after processing data using a machine learning model.

[0413] "Answer generation" is the process of creating answers or suggestions to provide to users based on the analysis results.

[0414] "Business logic" refers to the processing procedures and decision-making criteria that are specific to a specific business or industry, and is used to generate specific proposals and action plans for users.

[0415] A "Python machine learning library" is a library for machine learning used in the Python programming language, with representative examples being TensorFlow and Scikit-learn.

[0416] The present invention relates to a system that receives user input, analyzes the data, and provides fast and accurate answers and suggestions. The system includes a terminal operated by the user and a server that processes and analyzes the data.

[0417] Users use devices (e.g., PCs or smartphones) to input financial data and business plan information, for example, by entering a prompt such as "I would like to know the sales forecast for the next fiscal year," and provide past sales data and market conditions.

[0418] The terminal converts the input information into JSON format and sends it to the server via HTTPS. The server first validates the received data. Validation is performed using a Python data validation library (e.g., Cerberus) and includes checking for required fields and validating the data format.

[0419] For data that has been successfully validated, the server applies machine learning models. Specifically, it uses revenue forecasting models and cost management models to analyze the data using Python machine learning libraries (TensorFlow and Scikit-learn). For example, this can predict next fiscal year's sales based on past sales data and market conditions.

[0420] The server then generates a specific answer or recommendation for the user based on the analysis results, where business logic is applied to generate a specific action plan, such as "increase your marketing budget by 5%."

[0421] The server then converts the generated answers and suggestions back into JSON format and sends them to the device, which parses the results and displays them in a user-friendly format (e.g., graphs or tables).

[0422] For example, if a user requests "Please prepare the income statement for the next fiscal year," the flow is as follows:

[0423] The user inputs banking data or budget data. For example, a prompt such as "Please generate a profit and loss statement for 2023" is used. The terminal converts the input data into JSON format and sends it to the server. The server validates the data and uses machine learning models to generate a profit and loss statement based on sales, costs, operating expenses, etc. The server then sends the generated profit and loss statement in JSON format to the terminal, which parses the results and displays them to the user. For example, the profit and loss statement can be visually displayed using bar graphs or pie charts.

[0424] In this way, the system generates and provides users with fast and accurate answers and suggestions based on the data they enter, making the entire process from data entry to analysis and display of results efficient.

[0425] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0426] Step 1: User Input

[0427] The user uses a device (PC or smartphone) to input financial data and information about the business plan. For example, they input a prompt in text format such as, "I would like to know the sales forecast for next fiscal year." The information input includes past sales data and market conditions. The data provided by the user is sent to the device.

[0428] Step 2: Send data

[0429] The device converts the information entered by the user into JSON format. This conversion process ensures that the input data is properly formatted. The device then sends the JSON data to the server using HTTPS, which encrypts the data in transit and ensures a secure transfer.

[0430] Step 3: Data Receipt and Validation

[0431] The server receives the JSON data sent from the terminal. It validates the received data using a Python data validation library (for example, Cerberus). The purpose of validation is to check whether all required fields are filled in and whether the data format is correct. For example, if sales data is missing, an error message is generated. If validation is successful, the data proceeds to the parsing step.

[0432] Step 4: Data analysis

[0433] The server applies machine learning models to data that has passed validation. Specifically, it uses Python machine learning libraries (TensorFlow and Scikit-learn) to create revenue forecasting models and cost management models. In the analysis process, past sales data and market conditions are used as input data to predict future revenue and costs. For example, sales data from the past five years is used as input, and the output is a sales forecast for the next fiscal year.

[0434] Step 5: Answer Generation

[0435] The server generates specific answers and recommendations to provide to the user based on the analysis results. In this step, business logic is applied to derive the most beneficial recommendation for the user. For example, a specific recommendation such as "increase your marketing budget by 5%" is generated. The generated answers and recommendations are then converted back to JSON format.

[0436] Step 6: Send results

[0437] The server then converts the answers and suggestions into JSON format and sends them to the device. Again, data is encrypted during transmission and securely transferred. The server uses HTTPS to ensure confidentiality and integrity of the data.

[0438] Step 7: View the results

[0439] The terminal parses the JSON data received from the server and displays it in a user-friendly format. Specifically, it visualizes the results in graphs and tables on a web browser. For example, it displays the sales forecast results as a bar graph and the cost structure as a pie chart.

[0440] In this way, the user, terminal, and server work together at each step, enabling efficient processing from user input to analysis and display of results.

[0441] (Application example 1)

[0442] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0443] Conventional product recommendation systems for brick-and-mortar stores have struggled to effectively utilize users' purchasing history, reviews, inventory information, and other data to provide optimal product recommendations for each individual user. Furthermore, real-time data analysis and rapid feedback are required to improve the user experience in brick-and-mortar stores. However, existing systems were unable to meet these requirements.

[0444] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0445] In this invention, the server includes means for receiving user input, terminal means for converting the user input into a data format and transmitting it, means for analyzing the received data, means for generating a response based on the analysis result, means for transmitting the response to the terminal, means for displaying the response to the user, and means for reviewing the user input in the store and optimizing product suggestions based on data including purchase history and inventory information. This makes it possible to realize optimal product suggestions and promotions and provide real-time feedback in physical stores based on users' purchase history, reviews, and inventory information.

[0446] "User input" means information or data provided by a user to a system.

[0447] "Terminal means" refers to a device that processes data entered by a user, converts it into an appropriate format, and transmits it to the server.

[0448] The "server means" refers to a computer that analyzes the received data and generates a response based on the results.

[0449] The "analysis result" refers to the result obtained by the server means processing the data.

[0450] "Answer generation" refers to the process of creating feedback and suggestions for users based on the analysis results.

[0451] "Display means" refers to a device or method for visually presenting the generated answer to the user.

[0452] "Means for optimization" refers to a mechanism for processing product suggestions provided based on user-entered data in a way that is most beneficial to the user.

[0453] A "machine learning model" is a model that uses algorithms to make predictions and classifications based on large amounts of data.

[0454] "Business logic" refers to the standards and methods that guide rational decisions and actions in commercial activities.

[0455] The system of the present invention receives user input, analyzes the received data, and provides an optimal answer. An embodiment of the system will be described in detail below.

[0456] First, a user uses a device such as a smartphone or tablet to input information such as purchase history, product reviews, and the current contents of their cart. This device converts the input user information into an appropriate data format (e.g., JSON format) and sends the data to the server.

[0457] The server receives and analyzes the transmitted data. A machine learning model built using Python machine learning libraries (e.g., TensorFlow and Scikit-Learn) is installed on the server. This machine learning model learns user preferences and purchasing patterns based on past data, and generates optimal product suggestions and promotions for new data.

[0458] Based on the analysis results, the server generates an answer for the user. Business logic is applied to this answer generation process to create the most useful suggestions for the user. For example, the server may analyze the user's preferred product categories based on their purchase history and reviews, and prioritize suggestions for products in those categories.

[0459] The server then converts the generated response back into JSON format and sends it to the device, which parses the results and displays them visually to the user, typically in the form of graphs and tables showing product suggestions and promotional information.

[0460] This system allows for quick and accurate product suggestions in physical stores based on users' purchasing history, reviews, and inventory information.

[0461] Specific examples

[0462] Example 1: When a user scans an item in a store, the system will suggest the most suitable product based on their past purchase history and reviews.

[0463] Prompt: "Please suggest my next purchase based on past electronics purchase data."

[0464] Example 2: Based on inventory information, notify customers to purchase low-stock items as soon as possible.

[0465] Prompt: "Based on your inventory data, which item would you suggest this customer purchase sooner?"

[0466] To implement this invention, the following hardware and software are required:

[0467] Hardware: smartphones, tablets, servers

[0468] Software: Python, TensorFlow, Scikit-Learn, JSON parser, web framework (e.g., Flask, Django)

[0469] These configurations enable efficient data entry by users, analysis, generation of results, and display.

[0470] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0471] Step 1:

[0472] The user uses a smartphone or tablet to enter purchase history, product reviews, and current cart contents.

[0473] Specific operation: The user enters their purchase history, product reviews, and product information in the cart into the application's input form. This data is automatically saved in the input fields.

[0474] Input: Raw data entered by users such as purchase history, product reviews, and cart contents.

[0475] Output: The raw data that is passed to the next step.

[0476] Step 2:

[0477] The terminal converts the entered user information into JSON format and sends it to the server.

[0478] Specific operation: The terminal application retrieves data from the input field, and a parser runs to convert it to JSON format. The converted data is then sent to the server as an HTTP request.

[0479] Input: Raw data from the user.

[0480] Output: Data converted to JSON format.

[0481] Step 3:

[0482] The server receives the transmitted data and performs data validation.

[0483] Specific operation: The API receives an HTTP request on the server side, applies validation rules to check the format and content of the received data, and filters out invalid data.

[0484] Input: JSON data sent from the terminal.

[0485] Output: Clean data that passes validation.

[0486] Step 4:

[0487] The server uses machine learning models to analyze the data that passes validation.

[0488] How it works: Using Python libraries (TensorFlow or Scikit-Learn), the clean data is analyzed. Machine learning models predict purchasing patterns and user preferences and identify the next best product, taking into account the user's past behavior and external market data.

[0489] Input: Clean data after validation.

[0490] Output: Suggested products and promotions as analysis results.

[0491] Step 5:

[0492] Based on the analysis results, the server applies business logic to generate the optimal answer for the user.

[0493] What it does: Based on the analysis results, specific business logic (for example, a strategy aimed at increasing sales in a specific product category) is applied, and optimized product suggestions and promotions are generated in text format.

[0494] Input: Analysis results of machine learning models.

[0495] Output: Optimized answers (product suggestions and promotions) with business logic applied.

[0496] Step 6:

[0497] The server converts the generated response back into JSON format and sends it to the terminal.

[0498] Specific operation: The API operates to encode the text response generated by the server into JSON format and send it to the terminal as an HTTP response.

[0499] Input: The answer generated by applying business logic.

[0500] Output: The answer converted to JSON format.

[0501] Step 7:

[0502] The terminal receives the transmitted results and displays them to the user in a visually understandable manner.

[0503] What happens: The device application receives the HTTP response, decodes the data using a JSON parser, and displays it to the user in the form of a graph or table.

[0504] Input: The JSON response sent by the server.

[0505] Output: Offers and promotions visually displayed to the user.

[0506] In this way, the data entered by the user is analyzed efficiently, and optimal product suggestions and promotions are realized.

[0507] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0508] This invention relates to a system that receives user input, analyzes the data, and provides fast and accurate responses. This system includes a terminal operated by the user and a server that processes and analyzes the data. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, more personalized responses are possible.

[0509] User Input

[0510] A user uses a device (such as a PC or smartphone) to input financial data and information about a business plan and request an analysis. For example, the user might input "Please tell me the sales forecast for next fiscal year," and then input past sales data and market conditions. In this case, the device recognizes not only the data entered by the user, but also the user's emotions.

[0511] emotion recognition

[0512] The device uses natural language processing and machine learning to recognize emotions from users' text inputs and voices, and the emotion engine generates user emotion data along with the input data.

[0513] Data transmission

[0514] The device converts the input information, including the recognized emotion data, into JSON format and sends it to the server using an HTTP POST request. The server receives this data and is ready to begin analysis.

[0515] Data analysis

[0516] The server validates the received data and analyzes it using machine learning models, such as revenue forecasting and cost management models, to predict future revenues and costs. This analysis uses Python machine learning libraries (e.g., TensorFlow and Scikit-learn).

[0517] Emotion-based answer generation

[0518] The server takes the emotion engine's output into account when generating answers and suggestions for the user based on the analysis results. For example, if it recognizes that the user is feeling stressed, it will provide a simpler suggestion with less emphasis. It then applies business logic to generate a specific suggestion (e.g., "Increase your marketing budget by 5%)."

[0519] Sending and displaying results

[0520] The server converts the generated results back into JSON format and sends them to the terminal as an HTTP response. The terminal parses the received results and displays them in a user-friendly format, for example, in a graph or table format on the browser.

[0521] Specific examples

[0522] For example, if a user enters "Please prepare the income statement for next fiscal year," the flow is as follows:

[0523] 1. User: Enters banking data, budget data, etc., while the system recognizes the user's emotions.

[0524] 2. Terminal: Converts input data and recognized emotion data into JSON format and sends it to the server.

[0525] 3. Server: Validates and analyzes the data received, e.g., generates a profit and loss statement based on sales, costs, operating expenses, etc.

[0526] 4. Server: Based on the analysis results, generate a profit and loss statement taking into account the user's emotions and make recommendations with the appropriate tone and level of detail.

[0527] 5. Server: Sends the generated results to the device.

[0528] 6. Terminal: Parses the received results and displays the P&L to the user.

[0529] In this way, the system generates and provides users with fast and accurate answers and suggestions based on the user's input data and emotional data, thereby efficiently carrying out the entire process from data input to analysis and display of results, and providing personalized services that respond to the user's emotions.

[0530] The processing flow will be explained below.

[0531] Step 1:

[0532] The user inputs data into the device. For example, they might type, "Please tell me your sales forecast for next fiscal year," and then enter past sales data and market conditions. At this time, the device recognizes emotions from the user's text input and voice.

[0533] Step 2:

[0534] The device converts the information entered by the user into JSON format, attaches the recognized emotion data, and sends it to the server as an HTTP POST request.

[0535] Step 3:

[0536] The server receives the data sent from the terminal. Specifically, it deserializes the received JSON data and converts it into an object format.

[0537] Step 4:

[0538] The server validates the received data by checking whether the data format is correct, whether any items are missing, and whether the values ​​are appropriate.

[0539] Step 5:

[0540] The server then performs analysis using the validated data, using a pre-trained machine learning model, such as a sales forecasting model.

[0541] Step 6:

[0542] The server adjusts its analysis based on the output of the emotion engine, for example softening the tone of suggestions and feedback if the user is feeling stressed.

[0543] Step 7:

[0544] The server generates specific proposals based on business logic, such as "increase marketing budget by 5%."

[0545] Step 8:

[0546] The server converts the generated response back into JSON format and sends it to the terminal as an HTTP response.

[0547] Step 9:

[0548] The device parses the JSON data received from the server and displays the results to the user, for example, in a browser in the form of a graph or table.

[0549] Step 10:

[0550] The user reviews the displayed results and enters further questions or data as needed, in which case steps 1 through 9 are repeated again.

[0551] Example 2

[0552] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0553] Conventional systems have difficulty considering the user's emotions when analyzing user input and generating answers, resulting in impersonal responses. Furthermore, they lack personalized responses based on the user's emotional state, making it difficult to improve the user experience.

[0554] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes terminal means for converting a user's input into a data format and generating emotion data, means for transmitting input information including the recognized emotion data to the server, means for validating the received data, means for analyzing the data using a machine learning model, and means for generating a response according to the emotion based on the analysis result. This enables a personalized response that takes the user's emotion into consideration.

[0555] "User input" means information or data provided by a user to a system through a terminal.

[0556] "Terminal means" refers to a device or software that receives input from a user, converts it into a data format, and generates emotion data as needed.

[0557] "Emotional data" refers to information that represents a user's emotional state as recognized from the user's input.

[0558] "Server means" refers to devices and software that receive data sent from a terminal and process and analyze it.

[0559] "Validation" is the process of verifying that the format and content of received data are correct.

[0560] A "machine learning model" is a mathematical and statistical model that learns patterns and knowledge from data and performs analysis and predictions.

[0561] "Analysis Results" means the results obtained after processing and analyzing data using a machine learning model.

[0562] "Answer generation means" refers to a device or software that generates an answer to be provided to the user based on the analysis results.

[0563] This invention relates to a system that receives user input, analyzes the data, and provides fast and accurate responses. The system includes a terminal operated by the user and a server that processes and analyzes the data. It also incorporates an emotion engine that recognizes the user's emotions, enabling more personalized responses.

[0564] User Input

[0565] A user uses a device (such as a PC or smartphone) to input financial data and information about a business plan and request an analysis. For example, the user might type, "Please tell me the sales forecast for next fiscal year," and then input past sales data and market conditions into the device. In this case, the device recognizes not only the data entered by the user, but also the user's emotions.

[0566] emotion recognition

[0567] The device uses the natural language processing (NLP) library SpaCy to analyze the user's text input. It also converts voice input into text using a speech recognition library (e.g., Google Speech-to-Text API). It then uses the NLP analysis results and a machine learning model (e.g., Scikit-learn's emotion classification model) to recognize the user's emotions. The emotion engine generates user emotion data in conjunction with the input data.

[0568] Data transmission

[0569] The device converts the input information, including the recognized emotion data, into JSON format and sends it to the server using an HTTP POST request. For example, it generates the following JSON data:

[0570] json

[0571] {

[0572] "user_input": "Please tell us your sales forecast for next fiscal year",

[0573] "sentiment": "anxiety"

[0574] }

[0575] Send this data through a RESTful API.

[0576] Data analysis

[0577] The server validates the received data. First, it checks whether the input data and sentiment data are correctly formatted. If validation is successful, the server analyzes the data using a machine learning model (e.g., a model using TensorFlow). For example, it predicts future sales based on past sales data and market conditions.

[0578] Emotion-based answer generation

[0579] The server takes the output of the emotion engine into consideration when generating answers and suggestions for the user based on the analysis results. For example, if the user is feeling anxious, it will generate a message in a simple language that gives a sense of security. Specifically, it will generate a sentence such as, "Sales forecast for next fiscal year is 5 million yen. Don't worry, everything is going well."

[0580] Sending and displaying results

[0581] The server then converts the generated results back into JSON format and sends them to the device as an HTTP response. The device then parses the results and displays them in a user-friendly format. For example, the browser might display sales forecasts in graphs and tables, along with personalized messages based on user sentiment.

[0582] Specific examples

[0583] For example, if a user types "Please prepare the income statement for next period," the flow would be as follows:

[0584] 1. User: Enters banking data, budget data, etc. The system recognizes the user's emotions.

[0585] 2. Terminal: Converts input data and recognized emotion data into JSON format and sends it to the server.

[0586] 3. Server: Validates and analyzes the data received, e.g., generates a profit and loss statement based on sales, costs, operating expenses, etc.

[0587] 4. Server: Based on the analysis results, generate a profit and loss statement taking into account the user's emotions and make recommendations with the appropriate tone and level of detail.

[0588] 5. Server: Sends the generated results to the device.

[0589] 6. Terminal: Parses the received results and displays the P&L to the user.

[0590] Example prompt sentence:

[0591] "What are your sales forecasts for next fiscal year? Last year's sales data and market conditions are as follows: [data]."

[0592] This series of processes enables the system to provide fast and accurate answers and suggestions based on the user's input data and emotional data, thereby efficiently carrying out the entire process from data input to analysis and display of results, while also providing personalized services that respond to the user's emotions.

[0593] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0594] Step 1:

[0595] Receiving user input

[0596] Users use devices (such as PCs or smartphones) to input financial data and information about business plans. Examples of input content include, "Please tell me your sales forecast for next fiscal year." The data entered by users is stored in text format on the device.

[0597] Input: User text input

[0598] Output: Saved user text data

[0599] Step 2:

[0600] Performing emotion recognition

[0601] The device uses the natural language processing (NLP) library SpaCy to analyze the user's text input. It also converts voice input into text using a speech recognition library (e.g., Google Speech-to-Text API). It then uses the NLP analysis results and a machine learning model (e.g., Scikit-learn's emotion classification model) to recognize the user's emotions.

[0602] Input: User text input, voice data

[0603] Output: User sentiment data

[0604] Step 3:

[0605] Data conversion and transmission

[0606] The device converts the user's input data and the recognized emotion data into JSON format. For example, it generates the following JSON data:

[0607] json

[0608] {

[0609] "user_input": "Please tell us your sales forecast for next fiscal year",

[0610] "sentiment": "anxiety"

[0611] }

[0612] The resulting JSON data is then sent to the server using an HTTP POST request.

[0613] Input: User input data, emotion data

[0614] Output: JSON data sent to the server

[0615] Step 4:

[0616] Data Validation

[0617] The server validates the data it receives. First, it checks whether the input data and emotion data are correctly formatted. The software used includes validation tools such as JSON Schema. It checks for missing data or formatting errors.

[0618] Input: Received JSON data

[0619] Output: Validation result (success or error)

[0620] Step 5:

[0621] Performing data analysis

[0622] The server begins analysis based on the successfully validated data. It uses a machine learning model (for example, a model using TensorFlow) to predict future sales based on past sales data and market conditions. Specific analysis operations include data preprocessing, feature extraction, and application of the predictive model.

[0623] Input: Data that has been successfully validated

[0624] Output: Analysis results (e.g., sales forecast for the next fiscal year)

[0625] Step 6:

[0626] Emotion-based answer generation

[0627] The server takes into account the output of the emotion engine when generating an answer to provide to the user based on the analysis results. For example, if the user is feeling anxious, it generates a simple, reassuring message. The generated answer might look like this: "Sales forecast for next fiscal year is 5 million yen. Don't worry, everything is going well."

[0628] Input: Analysis results, emotion data

[0629] Output: Sentiment-based response data

[0630] Step 7:

[0631] Sending and displaying results

[0632] The server then converts the generated response data back into JSON format and sends it to the device as an HTTP response. The device then parses the results and displays the sales forecast in a browser in graph and table format, along with a message based on the user's emotions.

[0633] Input: Response data

[0634] Output: The result displayed to the user

[0635] (Application example 2)

[0636] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0637] Conventional systems analyze data and generate suggestions based on user input, but because they do not take into account the user's emotional state, it is difficult to provide personalized advice that takes into account factors such as stress and fatigue. This is particularly true for robot operators on factory floors, who are given uniform maintenance and operation instructions without considering their emotional state, which creates a problem of not being able to optimize workload and efficiency.

[0638] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0639] In this invention, the server includes means for receiving user input, means for converting the user input into a data format and transmitting it, means for analyzing the received data, means for generating an answer based on the analysis result, means for displaying the answer to the user, emotion recognition means for recognizing the user's emotional state and generating data on that, and emotion reflection means for generating an answer based on the user's emotional state, thereby enabling personalized advice and suggestions that take the user's emotional state into consideration.

[0640] "User input" refers to information or instructions provided by a user operating a system.

[0641] "Terminal means" refers to a device that converts user input into a data format and transmits and receives it.

[0642] The "server means" is a device that analyzes the received data and generates a response based on the results.

[0643] The "answer generation means" is a device that creates answers and suggestions for users based on the results of data analysis.

[0644] An "emotion recognition means" is a device that recognizes the user's emotional state and generates data on it.

[0645] The "emotion reflection means" is a device that generates answers and suggestions by reflecting the user's emotional state generated by the emotion recognition means.

[0646] "Machine Learning Model" means a machine learning algorithm or system used to perform data analysis on the server means.

[0647] "Business logic" refers to logic or rules based on specific business objectives or conditions that are used by the answer generation means.

[0648] As an embodiment of the present invention, consider a smartphone application used by a robot operator in a factory. The application is a system in which the operator inputs data about the robot's operational status and the site environment, and the data is analyzed in real time. The smartphone receives user input, converts it into a data format, and sends it to a server. The server analyzes the received data and generates a response based on the analysis results.

[0649] First, the operator inputs the robot's operating time, number of errors, vibration data, etc. via a smartphone (iOS or Android), and also obtains the robot's emotional state via voice input. The input data is converted into JSON format and sent to the server via an HTTP POST request. The server receives this data, validates it, and then analyzes it using a machine learning model (such as TensorFlow). Based on the analysis results, for example, if a certain number of errors or vibration level is exceeded, it will recognize that maintenance is necessary. In addition, an emotion recognition means takes into account the user's stress level and fatigue level, and generates advice and suggestions that reflect the user's emotional state.

[0650] Specifically, the system uses a front-end and back-end system written in Python. Data acquired by this system is analyzed using a machine learning model using TensorFlow to generate appropriate maintenance instructions and operation suggestions. Emotion recognition is also performed using the Google Cloud Natural Language API.

[0651] For example, if a user inputs "80 hours of operation, 5 errors, vibration level 3.2" into their smartphone and reports "stress level 2" by voice, the server will analyze these inputs. If the emotion recognition means detects a high stress state, the server will add advice such as "We recommend taking a break" in addition to suggesting maintenance based on the analysis results.

[0652] Examples of prompts for generative AI models are as follows:

[0653] Context: This is an application used by factory robot operators to provide optimal maintenance and rest instructions based on the robot's operating status and the operator's emotional state.

[0654] Question: If a robot has 80 hours of operation, has 5 errors, and the operator's stress level is 2, what maintenance instructions should be given?

[0655] These prompts can be used as input to an AI model to efficiently generate optimal maintenance and rest instructions, allowing operators to perform their work efficiently and safely.

[0656] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0657] Step 1:

[0658] The user uses a smartphone to input operational data such as the robot's operating time, number of errors, vibration data, and stress level. At the same time, an emotion recognition engine is used to obtain emotional data such as stress level from voice. The input data is in text and audio format.

[0659] Step 2:

[0660] The device converts the text data and emotion data entered by the user into JSON format. Specifically, it creates a JSON object with a dictionary-style data structure, with operating time, number of errors, vibration level, and stress level as keys. This becomes the input data for the next step.

[0661] Step 3:

[0662] The JSON data sent from the device is sent to the server using an HTTP POST request, which also includes metadata such as the user ID and timestamp to manage the data transmission and reception.

[0663] Step 4:

[0664] The server parses and validates the received JSON data. For example, it checks that the uptime is greater than or equal to zero and that the number of errors is not a negative value. Only data that passes this validation is analyzed in the next step.

[0665] Step 5:

[0666] The server inputs the validated data into a machine learning model (such as TensorFlow). The machine learning model analyzes the robot's operational data and predicts the need for maintenance, for example, if a certain number of errors or vibration levels exceed a certain standard. This analysis is based on the data the model has previously learned.

[0667] Step 6:

[0668] The server generates answers and suggestions based on the analysis results of the machine learning model. Specifically, it takes into account the analysis results as well as the user's emotional data, and adds easy-to-understand messages and instructions to take a break if the stress level is high. The answer generation means applies business logic to form specific suggestions for maintenance and operational adjustments.

[0669] Step 7:

[0670] The server then converts the generated answers and suggestions back into JSON format and sends them back to the device as an HTTP response, which includes the analysis results and sentiment-based advice.

[0671] Step 8:

[0672] The device parses the received JSON data and displays it in a user-friendly format. Specifically, it displays the results in text and graph format on the smartphone application screen, highlighting important suggestions and advice. It also uses prompts to the generative AI model to prepare for the next input.

[0673] Context: This is an application used by factory robot operators to provide optimal maintenance and rest instructions based on the robot's operating status and the operator's emotional state.

[0674] Question: If a robot has 80 hours of operation, has 5 errors, and the operator's stress level is 2, what maintenance instructions should be given?

[0675] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0676] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0677] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0678] [Third embodiment]

[0679] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0680] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0681] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0682] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0683] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0684] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0685] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0686] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0687] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0688] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0689] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0690] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0691] The present invention relates to a system that receives user input, analyzes the data, and provides a fast and accurate answer. The system includes a terminal operated by the user and a server that processes and analyzes the data.

[0692] User Input

[0693] Users use devices (such as PCs or smartphones) to input financial data and information related to business plans. For example, if a user wants to know the "sales forecast for the next fiscal year," they input past sales data and market conditions.

[0694] Data transmission

[0695] The device converts the input information into an appropriate format (e.g., JSON) and sends it to the server, which then receives the data and prepares to begin analyzing it.

[0696] Data analysis

[0697] The server validates the received data and analyzes it using machine learning models. Specifically, the server uses revenue forecasting and cost management models to predict future revenue and costs. This analysis is performed using Python machine learning libraries (e.g., TensorFlow and Scikit-learn).

[0698] Answer generation

[0699] The server generates answers or recommendations for the user based on the analysis results. At this stage, business logic is applied to generate specific recommendations (e.g., "Increase your marketing budget by 5%)."

[0700] Sending and displaying results

[0701] The server then converts the generated results back into JSON format and sends them to the device, which then parses the results and displays them in a user-friendly format, such as in a graph or table on the browser.

[0702] Specific examples

[0703] For example, if a user enters "Please prepare the income statement for next fiscal year," the flow is as follows:

[0704] 1. User: Enters bank transaction data, budget data, etc.

[0705] 2. Terminal: Converts input data into JSON format and sends it to the server.

[0706] 3. Server: Validates and analyzes the data received, e.g., generates a profit and loss statement based on sales, costs, operating expenses, etc.

[0707] 4. Server: Based on the analysis results, generate a profit and loss statement and send it to the terminal in JSON format.

[0708] 5. Terminal: Parses the received results and displays the P&L to the user.

[0709] In this way, the system generates and provides users with fast and accurate answers and suggestions based on the data they input, making the entire process from data entry to analysis and display of results efficient.

[0710] The processing flow will be explained below.

[0711] Step 1:

[0712] Users input data from their terminals. For example, they might type, "Please tell me your sales forecast for next fiscal year," and then enter past sales data and market conditions.

[0713] Step 2:

[0714] The device converts the information entered by the user into JSON format and sends it to the server using an HTTP POST request.

[0715] Step 3:

[0716] The server receives the data sent from the terminal. Specifically, it deserializes the received JSON data and converts it into an object format.

[0717] Step 4:

[0718] The server validates the received data by checking whether the data format is correct, whether any items are missing, and whether the values ​​are appropriate.

[0719] Step 5:

[0720] The server then performs analysis on the validated data using a pre-trained machine learning model, such as a sales forecasting model.

[0721] Step 6:

[0722] The server generates a response based on the analysis results, such as a specific recommendation like "increase the marketing budget by 5%" based on business logic.

[0723] Step 7:

[0724] The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[0725] Step 8:

[0726] The device parses the JSON data received from the server and displays the results to the user, for example, in a browser in the form of a graph or table.

[0727] Step 9:

[0728] The user reviews the displayed results, asks more questions or enters more data if necessary, and steps 1 through 8 are repeated again.

[0729] Example 1

[0730] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0731] In today's business environment, there is a demand for the rapid and accurate analysis of large amounts of data and the provision of specific proposals. However, with existing systems, the process from data input to analysis and display of results is complex and time-consuming. Furthermore, the analytical precision and specificity of proposals are often insufficient. Therefore, there is a need for the development of an efficient and highly accurate data analysis system.

[0732] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0733] In this invention, the server includes a means for validating received data, a means for analyzing the validated data using a machine learning model, and a means for generating answers based on the analysis results, thereby enabling the server to quickly and accurately analyze data and provide specific suggestions to users.

[0734] "User input" means data entered by a user of the system using a terminal.

[0735] A "terminal" is a device that a user uses to access the system and input or display information, including, for example, a personal computer or smartphone.

[0736] The "Server" is the main component of the system that processes and analyzes data received from users and generates answers and suggestions.

[0737] Validation is the process of ensuring that received data is accurate and complete, including checking for required fields and validating the data format.

[0738] A "machine learning model" is an algorithm that learns from large amounts of data, extracts patterns and relationships from that data, and makes predictions and analyses.

[0739] "Analysis results" are the outputs or conclusions obtained after processing data using a machine learning model.

[0740] "Answer generation" is the process of creating answers or suggestions to provide to users based on the analysis results.

[0741] "Business logic" refers to the processing procedures and decision-making criteria that are specific to a specific business or industry, and is used to generate specific proposals and action plans for users.

[0742] A "Python machine learning library" is a library for machine learning used in the Python programming language, with representative examples being TensorFlow and Scikit-learn.

[0743] The present invention relates to a system that receives user input, analyzes the data, and provides fast and accurate answers and suggestions. The system includes a terminal operated by the user and a server that processes and analyzes the data.

[0744] Users use devices (e.g., PCs or smartphones) to input financial data and business plan information, for example, by entering a prompt such as "I would like to know the sales forecast for the next fiscal year," and provide past sales data and market conditions.

[0745] The terminal converts the input information into JSON format and sends it to the server via HTTPS. The server first validates the received data. Validation is performed using a Python data validation library (e.g., Cerberus) and includes checking for required fields and validating the data format.

[0746] For data that has been successfully validated, the server applies machine learning models. Specifically, it uses revenue forecasting models and cost management models to analyze the data using Python machine learning libraries (TensorFlow and Scikit-learn). For example, this can predict next fiscal year's sales based on past sales data and market conditions.

[0747] The server then generates a specific answer or recommendation for the user based on the analysis results, where business logic is applied to generate a specific action plan, such as "increase your marketing budget by 5%."

[0748] The server then converts the generated answers and suggestions back into JSON format and sends them to the device, which parses the results and displays them in a user-friendly format (e.g., graphs or tables).

[0749] For example, if a user requests "Please prepare the income statement for the next fiscal year," the flow is as follows:

[0750] The user inputs banking data or budget data. For example, a prompt such as "Please generate a profit and loss statement for 2023" is used. The terminal converts the input data into JSON format and sends it to the server. The server validates the data and uses machine learning models to generate a profit and loss statement based on sales, costs, operating expenses, etc. The server then sends the generated profit and loss statement in JSON format to the terminal, which parses the results and displays them to the user. For example, the profit and loss statement can be visually displayed using bar graphs or pie charts.

[0751] In this way, the system generates and provides users with fast and accurate answers and suggestions based on the data they enter, making the entire process from data entry to analysis and display of results efficient.

[0752] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0753] Step 1: User Input

[0754] The user uses a device (PC or smartphone) to input financial data and information about the business plan. For example, they input a prompt in text format such as, "I would like to know the sales forecast for next fiscal year." The information input includes past sales data and market conditions. The data provided by the user is sent to the device.

[0755] Step 2: Send data

[0756] The device converts the information entered by the user into JSON format. This conversion process ensures that the input data is properly formatted. The device then sends the JSON data to the server using HTTPS, which encrypts the data in transit and ensures a secure transfer.

[0757] Step 3: Data Receipt and Validation

[0758] The server receives the JSON data sent from the terminal. It validates the received data using a Python data validation library (for example, Cerberus). The purpose of validation is to check whether all required fields are filled in and whether the data format is correct. For example, if sales data is missing, an error message is generated. If validation is successful, the data proceeds to the parsing step.

[0759] Step 4: Data analysis

[0760] The server applies machine learning models to data that has passed validation. Specifically, it uses Python machine learning libraries (TensorFlow and Scikit-learn) to create revenue forecasting models and cost management models. In the analysis process, past sales data and market conditions are used as input data to predict future revenue and costs. For example, sales data from the past five years is used as input, and the output is a sales forecast for the next fiscal year.

[0761] Step 5: Answer Generation

[0762] The server generates specific answers and recommendations to provide to the user based on the analysis results. In this step, business logic is applied to derive the most beneficial recommendation for the user. For example, a specific recommendation such as "increase your marketing budget by 5%" is generated. The generated answers and recommendations are then converted back to JSON format.

[0763] Step 6: Send results

[0764] The server then converts the answers and suggestions into JSON format and sends them to the device. Again, data is encrypted during transmission and securely transferred. The server uses HTTPS to ensure confidentiality and integrity of the data.

[0765] Step 7: View the results

[0766] The terminal parses the JSON data received from the server and displays it in a user-friendly format. Specifically, it visualizes the results in graphs and tables on a web browser. For example, it displays the sales forecast results as a bar graph and the cost structure as a pie chart.

[0767] In this way, the user, terminal, and server work together at each step, enabling efficient processing from user input to analysis and display of results.

[0768] (Application example 1)

[0769] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0770] Conventional product recommendation systems for brick-and-mortar stores have struggled to effectively utilize users' purchasing history, reviews, inventory information, and other data to provide optimal product recommendations for each individual user. Furthermore, real-time data analysis and rapid feedback are required to improve the user experience in brick-and-mortar stores. However, existing systems were unable to meet these requirements.

[0771] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0772] In this invention, the server includes means for receiving user input, terminal means for converting the user input into a data format and transmitting it, means for analyzing the received data, means for generating a response based on the analysis result, means for transmitting the response to the terminal, means for displaying the response to the user, and means for reviewing the user input in the store and optimizing product suggestions based on data including purchase history and inventory information. This makes it possible to realize optimal product suggestions and promotions and provide real-time feedback in physical stores based on users' purchase history, reviews, and inventory information.

[0773] "User input" means information or data provided by a user to a system.

[0774] "Terminal means" refers to a device that processes data entered by a user, converts it into an appropriate format, and transmits it to the server.

[0775] The "server means" refers to a computer that analyzes the received data and generates a response based on the results.

[0776] The "analysis result" refers to the result obtained by the server means processing the data.

[0777] "Answer generation" refers to the process of creating feedback and suggestions for users based on the analysis results.

[0778] "Display means" refers to a device or method for visually presenting the generated answer to the user.

[0779] "Means for optimization" refers to a mechanism for processing product suggestions provided based on user-entered data in a way that is most beneficial to the user.

[0780] A "machine learning model" is a model that uses algorithms to make predictions and classifications based on large amounts of data.

[0781] "Business logic" refers to the standards and methods that guide rational decisions and actions in commercial activities.

[0782] The system of the present invention receives user input, analyzes the received data, and provides an optimal answer. An embodiment of the system will be described in detail below.

[0783] First, a user uses a device such as a smartphone or tablet to input information such as purchase history, product reviews, and the current contents of their cart. This device converts the input user information into an appropriate data format (e.g., JSON format) and sends the data to the server.

[0784] The server receives and analyzes the transmitted data. A machine learning model built using Python machine learning libraries (e.g., TensorFlow and Scikit-Learn) is installed on the server. This machine learning model learns user preferences and purchasing patterns based on past data, and generates optimal product suggestions and promotions for new data.

[0785] Based on the analysis results, the server generates an answer for the user. Business logic is applied to this answer generation process to create the most useful suggestions for the user. For example, the server may analyze the user's preferred product categories based on their purchase history and reviews, and prioritize suggestions for products in those categories.

[0786] The server then converts the generated response back into JSON format and sends it to the device, which parses the results and displays them visually to the user, typically in the form of graphs and tables showing product suggestions and promotional information.

[0787] This system allows for quick and accurate product suggestions in physical stores based on users' purchasing history, reviews, and inventory information.

[0788] Specific examples

[0789] Example 1: When a user scans an item in a store, the system will suggest the most suitable product based on their past purchase history and reviews.

[0790] Prompt: "Please suggest my next purchase based on past electronics purchase data."

[0791] Example 2: Based on inventory information, notify customers to purchase low-stock items as soon as possible.

[0792] Prompt: "Based on your inventory data, which item would you suggest this customer purchase sooner?"

[0793] To implement this invention, the following hardware and software are required:

[0794] Hardware: smartphones, tablets, servers

[0795] Software: Python, TensorFlow, Scikit-Learn, JSON parser, web framework (e.g., Flask, Django)

[0796] These configurations enable efficient data entry by users, analysis, generation of results, and display.

[0797] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0798] Step 1:

[0799] The user uses a smartphone or tablet to enter purchase history, product reviews, and current cart contents.

[0800] Specific operation: The user enters their purchase history, product reviews, and product information in the cart into the application's input form. This data is automatically saved in the input fields.

[0801] Input: Raw data entered by users such as purchase history, product reviews, and cart contents.

[0802] Output: The raw data that is passed to the next step.

[0803] Step 2:

[0804] The terminal converts the entered user information into JSON format and sends it to the server.

[0805] Specific operation: The terminal application retrieves data from the input field, and a parser runs to convert it to JSON format. The converted data is then sent to the server as an HTTP request.

[0806] Input: Raw data from the user.

[0807] Output: Data converted to JSON format.

[0808] Step 3:

[0809] The server receives the transmitted data and performs data validation.

[0810] Specific operation: The API receives an HTTP request on the server side, applies validation rules to check the format and content of the received data, and filters out invalid data.

[0811] Input: JSON data sent from the terminal.

[0812] Output: Clean data that passes validation.

[0813] Step 4:

[0814] The server uses machine learning models to analyze the data that passes validation.

[0815] How it works: Using Python libraries (TensorFlow or Scikit-Learn), the clean data is analyzed. Machine learning models predict purchasing patterns and user preferences and identify the next best product, taking into account the user's past behavior and external market data.

[0816] Input: Clean data after validation.

[0817] Output: Suggested products and promotions as analysis results.

[0818] Step 5:

[0819] Based on the analysis results, the server applies business logic to generate the optimal answer for the user.

[0820] What it does: Based on the analysis results, specific business logic (for example, a strategy aimed at increasing sales in a specific product category) is applied, and optimized product suggestions and promotions are generated in text format.

[0821] Input: Analysis results of machine learning models.

[0822] Output: Optimized answers (product suggestions and promotions) with business logic applied.

[0823] Step 6:

[0824] The server converts the generated response back into JSON format and sends it to the terminal.

[0825] Specific operation: The API operates to encode the text response generated by the server into JSON format and send it to the terminal as an HTTP response.

[0826] Input: The answer generated by applying business logic.

[0827] Output: The answer converted to JSON format.

[0828] Step 7:

[0829] The terminal receives the transmitted results and displays them to the user in a visually understandable manner.

[0830] What happens: The device application receives the HTTP response, decodes the data using a JSON parser, and displays it to the user in the form of a graph or table.

[0831] Input: The JSON response sent by the server.

[0832] Output: Offers and promotions visually displayed to the user.

[0833] In this way, the data entered by the user is analyzed efficiently, and optimal product suggestions and promotions are realized.

[0834] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0835] This invention relates to a system that receives user input, analyzes the data, and provides fast and accurate responses. This system includes a terminal operated by the user and a server that processes and analyzes the data. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, more personalized responses are possible.

[0836] User Input

[0837] A user uses a device (such as a PC or smartphone) to input financial data and information about a business plan and request an analysis. For example, the user might input "Please tell me the sales forecast for next fiscal year," and then input past sales data and market conditions. In this case, the device recognizes not only the data entered by the user, but also the user's emotions.

[0838] emotion recognition

[0839] The device uses natural language processing and machine learning to recognize emotions from users' text inputs and voices, and the emotion engine generates user emotion data along with the input data.

[0840] Data transmission

[0841] The device converts the input information, including the recognized emotion data, into JSON format and sends it to the server using an HTTP POST request. The server receives this data and is ready to begin analysis.

[0842] Data analysis

[0843] The server validates the received data and analyzes it using machine learning models, such as revenue forecasting and cost management models, to predict future revenues and costs. This analysis uses Python machine learning libraries (e.g., TensorFlow and Scikit-learn).

[0844] Emotion-based answer generation

[0845] The server takes the emotion engine's output into account when generating answers and suggestions for the user based on the analysis results. For example, if it recognizes that the user is feeling stressed, it will provide a simpler suggestion with less emphasis. It then applies business logic to generate a specific suggestion (e.g., "Increase your marketing budget by 5%)."

[0846] Sending and displaying results

[0847] The server converts the generated results back into JSON format and sends them to the terminal as an HTTP response. The terminal parses the received results and displays them in a user-friendly format, for example, in a graph or table format on the browser.

[0848] Specific examples

[0849] For example, if a user enters "Please prepare the income statement for next fiscal year," the flow is as follows:

[0850] 1. User: Enters banking data, budget data, etc., while the system recognizes the user's emotions.

[0851] 2. Terminal: Converts input data and recognized emotion data into JSON format and sends it to the server.

[0852] 3. Server: Validates and analyzes the data received, e.g., generates a profit and loss statement based on sales, costs, operating expenses, etc.

[0853] 4. Server: Based on the analysis results, generate a profit and loss statement taking into account the user's emotions and make recommendations with the appropriate tone and level of detail.

[0854] 5. Server: Sends the generated results to the device.

[0855] 6. Terminal: Parses the received results and displays the P&L to the user.

[0856] In this way, the system generates and provides users with fast and accurate answers and suggestions based on the user's input data and emotional data, thereby efficiently carrying out the entire process from data input to analysis and display of results, and providing personalized services that respond to the user's emotions.

[0857] The processing flow will be explained below.

[0858] Step 1:

[0859] The user inputs data into the device. For example, they might type, "Please tell me your sales forecast for next fiscal year," and then enter past sales data and market conditions. At this time, the device recognizes emotions from the user's text input and voice.

[0860] Step 2:

[0861] The device converts the information entered by the user into JSON format, attaches the recognized emotion data, and sends it to the server as an HTTP POST request.

[0862] Step 3:

[0863] The server receives the data sent from the terminal. Specifically, it deserializes the received JSON data and converts it into an object format.

[0864] Step 4:

[0865] The server validates the received data by checking whether the data format is correct, whether any items are missing, and whether the values ​​are appropriate.

[0866] Step 5:

[0867] The server then performs analysis using the validated data, using a pre-trained machine learning model, such as a sales forecasting model.

[0868] Step 6:

[0869] The server adjusts its analysis based on the output of the emotion engine, for example softening the tone of suggestions and feedback if the user is feeling stressed.

[0870] Step 7:

[0871] The server generates specific proposals based on business logic, such as "increase marketing budget by 5%."

[0872] Step 8:

[0873] The server converts the generated response back into JSON format and sends it to the terminal as an HTTP response.

[0874] Step 9:

[0875] The device parses the JSON data received from the server and displays the results to the user, for example, in a browser in the form of a graph or table.

[0876] Step 10:

[0877] The user reviews the displayed results and enters further questions or data as needed, in which case steps 1 through 9 are repeated again.

[0878] Example 2

[0879] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0880] Conventional systems have difficulty considering the user's emotions when analyzing user input and generating answers, resulting in impersonal responses. Furthermore, they lack personalized responses based on the user's emotional state, making it difficult to improve the user experience.

[0881] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes terminal means for converting a user's input into a data format and generating emotion data, means for transmitting input information including the recognized emotion data to the server, means for validating the received data, means for analyzing the data using a machine learning model, and means for generating a response according to the emotion based on the analysis result. This enables a personalized response that takes the user's emotion into consideration.

[0882] "User input" means information or data provided by a user to a system through a terminal.

[0883] "Terminal means" refers to a device or software that receives input from a user, converts it into a data format, and generates emotion data as needed.

[0884] "Emotional data" refers to information that represents a user's emotional state as recognized from the user's input.

[0885] "Server means" refers to devices and software that receive data sent from a terminal and process and analyze it.

[0886] "Validation" is the process of verifying that the format and content of received data are correct.

[0887] A "machine learning model" is a mathematical and statistical model that learns patterns and knowledge from data and performs analysis and predictions.

[0888] "Analysis Results" means the results obtained after processing and analyzing data using a machine learning model.

[0889] "Answer generation means" refers to a device or software that generates an answer to be provided to the user based on the analysis results.

[0890] This invention relates to a system that receives user input, analyzes the data, and provides fast and accurate responses. The system includes a terminal operated by the user and a server that processes and analyzes the data. It also incorporates an emotion engine that recognizes the user's emotions, enabling more personalized responses.

[0891] User Input

[0892] A user uses a device (such as a PC or smartphone) to input financial data and information about a business plan and request an analysis. For example, the user might type, "Please tell me the sales forecast for next fiscal year," and then input past sales data and market conditions into the device. In this case, the device recognizes not only the data entered by the user, but also the user's emotions.

[0893] emotion recognition

[0894] The device uses the natural language processing (NLP) library SpaCy to analyze the user's text input. It also converts voice input into text using a speech recognition library (e.g., Google Speech-to-Text API). It then uses the NLP analysis results and a machine learning model (e.g., Scikit-learn's emotion classification model) to recognize the user's emotions. The emotion engine generates user emotion data in conjunction with the input data.

[0895] Data transmission

[0896] The device converts the input information, including the recognized emotion data, into JSON format and sends it to the server using an HTTP POST request. For example, it generates the following JSON data:

[0897] json

[0898] {

[0899] "user_input": "Please tell us your sales forecast for next fiscal year",

[0900] "sentiment": "anxiety"

[0901] }

[0902] Send this data through a RESTful API.

[0903] Data analysis

[0904] The server validates the received data. First, it checks whether the input data and sentiment data are correctly formatted. If validation is successful, the server analyzes the data using a machine learning model (e.g., a model using TensorFlow). For example, it predicts future sales based on past sales data and market conditions.

[0905] Emotion-based answer generation

[0906] The server takes the output of the emotion engine into consideration when generating answers and suggestions for the user based on the analysis results. For example, if the user is feeling anxious, it will generate a message in a simple language that gives a sense of security. Specifically, it will generate a sentence such as, "Sales forecast for next fiscal year is 5 million yen. Don't worry, everything is going well."

[0907] Sending and displaying results

[0908] The server then converts the generated results back into JSON format and sends them to the device as an HTTP response. The device then parses the results and displays them in a user-friendly format. For example, the browser might display sales forecasts in graphs and tables, along with personalized messages based on user sentiment.

[0909] Specific examples

[0910] For example, if a user types "Please prepare the income statement for next period," the flow would be as follows:

[0911] 1. User: Enters banking data, budget data, etc. The system recognizes the user's emotions.

[0912] 2. Terminal: Converts input data and recognized emotion data into JSON format and sends it to the server.

[0913] 3. Server: Validates and analyzes the data received, e.g., generates a profit and loss statement based on sales, costs, operating expenses, etc.

[0914] 4. Server: Based on the analysis results, generate a profit and loss statement taking into account the user's emotions and make recommendations with the appropriate tone and level of detail.

[0915] 5. Server: Sends the generated results to the device.

[0916] 6. Terminal: Parses the received results and displays the P&L to the user.

[0917] Example prompt sentence:

[0918] "What are your sales forecasts for next fiscal year? Last year's sales data and market conditions are as follows: [data]."

[0919] This series of processes enables the system to provide fast and accurate answers and suggestions based on the user's input data and emotional data, thereby efficiently carrying out the entire process from data input to analysis and display of results, while also providing personalized services that respond to the user's emotions.

[0920] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0921] Step 1:

[0922] Receiving user input

[0923] Users use devices (such as PCs or smartphones) to input financial data and information about business plans. Examples of input content include, "Please tell me your sales forecast for next fiscal year." The data entered by users is stored in text format on the device.

[0924] Input: User text input

[0925] Output: Saved user text data

[0926] Step 2:

[0927] Performing emotion recognition

[0928] The device uses the natural language processing (NLP) library SpaCy to analyze the user's text input. It also converts voice input into text using a speech recognition library (e.g., Google Speech-to-Text API). It then uses the NLP analysis results and a machine learning model (e.g., Scikit-learn's emotion classification model) to recognize the user's emotions.

[0929] Input: User text input, voice data

[0930] Output: User sentiment data

[0931] Step 3:

[0932] Data conversion and transmission

[0933] The device converts the user's input data and the recognized emotion data into JSON format. For example, it generates the following JSON data:

[0934] json

[0935] {

[0936] "user_input": "Please tell us your sales forecast for next fiscal year",

[0937] "sentiment": "anxiety"

[0938] }

[0939] The resulting JSON data is then sent to the server using an HTTP POST request.

[0940] Input: User input data, emotion data

[0941] Output: JSON data sent to the server

[0942] Step 4:

[0943] Data Validation

[0944] The server validates the data it receives. First, it checks whether the input data and emotion data are correctly formatted. The software used includes validation tools such as JSON Schema. It checks for missing data or formatting errors.

[0945] Input: Received JSON data

[0946] Output: Validation result (success or error)

[0947] Step 5:

[0948] Performing data analysis

[0949] The server begins analysis based on the successfully validated data. It uses a machine learning model (for example, a model using TensorFlow) to predict future sales based on past sales data and market conditions. Specific analysis operations include data preprocessing, feature extraction, and application of the predictive model.

[0950] Input: Data that has been successfully validated

[0951] Output: Analysis results (e.g., sales forecast for the next fiscal year)

[0952] Step 6:

[0953] Emotion-based answer generation

[0954] The server takes into account the output of the emotion engine when generating an answer to provide to the user based on the analysis results. For example, if the user is feeling anxious, it generates a simple, reassuring message. The generated answer might look like this: "Sales forecast for next fiscal year is 5 million yen. Don't worry, everything is going well."

[0955] Input: Analysis results, emotion data

[0956] Output: Sentiment-based response data

[0957] Step 7:

[0958] Sending and displaying results

[0959] The server then converts the generated response data back into JSON format and sends it to the device as an HTTP response. The device then parses the results and displays the sales forecast in a browser in graph and table format, along with a message based on the user's emotions.

[0960] Input: Response data

[0961] Output: The result displayed to the user

[0962] (Application example 2)

[0963] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0964] Conventional systems analyze data and generate suggestions based on user input, but because they do not take into account the user's emotional state, it is difficult to provide personalized advice that takes into account factors such as stress and fatigue. This is particularly true for robot operators on factory floors, who are given uniform maintenance and operation instructions without considering their emotional state, which creates a problem of not being able to optimize workload and efficiency.

[0965] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0966] In this invention, the server includes means for receiving user input, means for converting the user input into a data format and transmitting it, means for analyzing the received data, means for generating an answer based on the analysis result, means for displaying the answer to the user, emotion recognition means for recognizing the user's emotional state and generating data on that, and emotion reflection means for generating an answer based on the user's emotional state, thereby enabling personalized advice and suggestions that take the user's emotional state into consideration.

[0967] "User input" refers to information or instructions provided by a user operating a system.

[0968] "Terminal means" refers to a device that converts user input into a data format and transmits and receives it.

[0969] The "server means" is a device that analyzes the received data and generates a response based on the results.

[0970] The "answer generation means" is a device that creates answers and suggestions for users based on the results of data analysis.

[0971] An "emotion recognition means" is a device that recognizes the user's emotional state and generates data on it.

[0972] The "emotion reflection means" is a device that generates answers and suggestions by reflecting the user's emotional state generated by the emotion recognition means.

[0973] "Machine Learning Model" means a machine learning algorithm or system used to perform data analysis on the server means.

[0974] "Business logic" refers to logic or rules based on specific business objectives or conditions that are used by the answer generation means.

[0975] As an embodiment of the present invention, consider a smartphone application used by a robot operator in a factory. The application is a system in which the operator inputs data about the robot's operational status and the site environment, and the data is analyzed in real time. The smartphone receives user input, converts it into a data format, and sends it to a server. The server analyzes the received data and generates a response based on the analysis results.

[0976] First, the operator inputs the robot's operating time, number of errors, vibration data, etc. via a smartphone (iOS or Android), and also obtains the robot's emotional state via voice input. The input data is converted into JSON format and sent to the server via an HTTP POST request. The server receives this data, validates it, and then analyzes it using a machine learning model (such as TensorFlow). Based on the analysis results, for example, if a certain number of errors or vibration level is exceeded, it will recognize that maintenance is necessary. In addition, an emotion recognition means takes into account the user's stress level and fatigue level, and generates advice and suggestions that reflect the user's emotional state.

[0977] Specifically, the system uses a front-end and back-end system written in Python. Data acquired by this system is analyzed using a machine learning model using TensorFlow to generate appropriate maintenance instructions and operation suggestions. Emotion recognition is also performed using the Google Cloud Natural Language API.

[0978] For example, if a user inputs "80 hours of operation, 5 errors, vibration level 3.2" into their smartphone and reports "stress level 2" by voice, the server will analyze these inputs. If the emotion recognition means detects a high stress state, the server will add advice such as "We recommend taking a break" in addition to suggesting maintenance based on the analysis results.

[0979] Examples of prompts for generative AI models are as follows:

[0980] Context: This is an application used by factory robot operators to provide optimal maintenance and rest instructions based on the robot's operating status and the operator's emotional state.

[0981] Question: If a robot has 80 hours of operation, has 5 errors, and the operator's stress level is 2, what maintenance instructions should be given?

[0982] These prompts can be used as input to an AI model to efficiently generate optimal maintenance and rest instructions, allowing operators to perform their work efficiently and safely.

[0983] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0984] Step 1:

[0985] The user uses a smartphone to input operational data such as the robot's operating time, number of errors, vibration data, and stress level. At the same time, an emotion recognition engine is used to obtain emotional data such as stress level from voice. The input data is in text and audio format.

[0986] Step 2:

[0987] The device converts the text data and emotion data entered by the user into JSON format. Specifically, it creates a JSON object with a dictionary-style data structure, with operating time, number of errors, vibration level, and stress level as keys. This becomes the input data for the next step.

[0988] Step 3:

[0989] The JSON data sent from the device is sent to the server using an HTTP POST request, which also includes metadata such as the user ID and timestamp to manage the data transmission and reception.

[0990] Step 4:

[0991] The server parses and validates the received JSON data. For example, it checks that the uptime is greater than or equal to zero and that the number of errors is not a negative value. Only data that passes this validation is analyzed in the next step.

[0992] Step 5:

[0993] The server inputs the validated data into a machine learning model (such as TensorFlow). The machine learning model analyzes the robot's operational data and predicts the need for maintenance, for example, if a certain number of errors or vibration levels exceed a certain standard. This analysis is based on the data the model has previously learned.

[0994] Step 6:

[0995] The server generates answers and suggestions based on the analysis results of the machine learning model. Specifically, it takes into account the analysis results as well as the user's emotional data, and adds easy-to-understand messages and instructions to take a break if the stress level is high. The answer generation means applies business logic to form specific suggestions for maintenance and operational adjustments.

[0996] Step 7:

[0997] The server then converts the generated answers and suggestions back into JSON format and sends them back to the device as an HTTP response, which includes the analysis results and sentiment-based advice.

[0998] Step 8:

[0999] The device parses the received JSON data and displays it in a user-friendly format. Specifically, it displays the results in text and graph format on the smartphone application screen, highlighting important suggestions and advice. It also uses prompts to the generative AI model to prepare for the next input.

[1000] Context: This is an application used by factory robot operators to provide optimal maintenance and rest instructions based on the robot's operating status and the operator's emotional state.

[1001] Question: If a robot has 80 hours of operation, has 5 errors, and the operator's stress level is 2, what maintenance instructions should be given?

[1002] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1003] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1004] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1005] [Fourth embodiment]

[1006] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1007] 7, a 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.

[1008] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1009] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1010] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1011] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1012] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1013] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1014] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1015] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1016] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1017] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1018] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1019] The present invention relates to a system that receives user input, analyzes the data, and provides a fast and accurate answer. The system includes a terminal operated by the user and a server that processes and analyzes the data.

[1020] User Input

[1021] Users use devices (such as PCs or smartphones) to input financial data and information related to business plans. For example, if a user wants to know the "sales forecast for the next fiscal year," they input past sales data and market conditions.

[1022] Data transmission

[1023] The device converts the input information into an appropriate format (e.g., JSON) and sends it to the server, which then receives the data and prepares to begin analyzing it.

[1024] Data analysis

[1025] The server validates the received data and analyzes it using machine learning models. Specifically, the server uses revenue forecasting and cost management models to predict future revenue and costs. This analysis is performed using Python machine learning libraries (e.g., TensorFlow and Scikit-learn).

[1026] Answer generation

[1027] The server generates answers or recommendations for the user based on the analysis results. At this stage, business logic is applied to generate specific recommendations (e.g., "Increase your marketing budget by 5%)."

[1028] Sending and displaying results

[1029] The server then converts the generated results back into JSON format and sends them to the device, which then parses the results and displays them in a user-friendly format, such as in a graph or table on the browser.

[1030] Specific examples

[1031] For example, if a user enters "Please prepare the income statement for next fiscal year," the flow is as follows:

[1032] 1. User: Enters bank transaction data, budget data, etc.

[1033] 2. Terminal: Converts input data into JSON format and sends it to the server.

[1034] 3. Server: Validates and analyzes the data received, e.g., generates a profit and loss statement based on sales, costs, operating expenses, etc.

[1035] 4. Server: Based on the analysis results, generate a profit and loss statement and send it to the terminal in JSON format.

[1036] 5. Terminal: Parses the received results and displays the P&L to the user.

[1037] In this way, the system generates and provides users with fast and accurate answers and suggestions based on the data they input, making the entire process from data entry to analysis and display of results efficient.

[1038] The processing flow will be explained below.

[1039] Step 1:

[1040] Users input data from their terminals. For example, they might type, "Please tell me your sales forecast for next fiscal year," and then enter past sales data and market conditions.

[1041] Step 2:

[1042] The device converts the information entered by the user into JSON format and sends it to the server using an HTTP POST request.

[1043] Step 3:

[1044] The server receives the data sent from the terminal. Specifically, it deserializes the received JSON data and converts it into an object format.

[1045] Step 4:

[1046] The server validates the received data by checking whether the data format is correct, whether any items are missing, and whether the values ​​are appropriate.

[1047] Step 5:

[1048] The server then performs analysis on the validated data using a pre-trained machine learning model, such as a sales forecasting model.

[1049] Step 6:

[1050] The server generates a response based on the analysis results, such as a specific recommendation like "increase the marketing budget by 5%" based on business logic.

[1051] Step 7:

[1052] The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[1053] Step 8:

[1054] The device parses the JSON data received from the server and displays the results to the user, for example, in a browser in the form of a graph or table.

[1055] Step 9:

[1056] The user reviews the displayed results, asks more questions or enters more data if necessary, and steps 1 through 8 are repeated again.

[1057] Example 1

[1058] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1059] In today's business environment, there is a demand for the rapid and accurate analysis of large amounts of data and the provision of specific proposals. However, with existing systems, the process from data input to analysis and display of results is complex and time-consuming. Furthermore, the analytical precision and specificity of proposals are often insufficient. Therefore, there is a need for the development of an efficient and highly accurate data analysis system.

[1060] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1061] In this invention, the server includes a means for validating received data, a means for analyzing the validated data using a machine learning model, and a means for generating answers based on the analysis results, thereby enabling the server to quickly and accurately analyze data and provide specific suggestions to users.

[1062] "User input" means data entered by a user of the system using a terminal.

[1063] A "terminal" is a device that a user uses to access the system and input or display information, including, for example, a personal computer or smartphone.

[1064] The "Server" is the main component of the system that processes and analyzes data received from users and generates answers and suggestions.

[1065] Validation is the process of ensuring that received data is accurate and complete, including checking for required fields and validating the data format.

[1066] A "machine learning model" is an algorithm that learns from large amounts of data, extracts patterns and relationships from that data, and makes predictions and analyses.

[1067] "Analysis results" are the outputs or conclusions obtained after processing data using a machine learning model.

[1068] "Answer generation" is the process of creating answers or suggestions to provide to users based on the analysis results.

[1069] "Business logic" refers to the processing procedures and decision-making criteria that are specific to a specific business or industry, and is used to generate specific proposals and action plans for users.

[1070] A "Python machine learning library" is a library for machine learning used in the Python programming language, with representative examples being TensorFlow and Scikit-learn.

[1071] The present invention relates to a system that receives user input, analyzes the data, and provides fast and accurate answers and suggestions. The system includes a terminal operated by the user and a server that processes and analyzes the data.

[1072] Users use devices (e.g., PCs or smartphones) to input financial data and business plan information, for example, by entering a prompt such as "I would like to know the sales forecast for the next fiscal year," and provide past sales data and market conditions.

[1073] The terminal converts the input information into JSON format and sends it to the server via HTTPS. The server first validates the received data. Validation is performed using a Python data validation library (e.g., Cerberus) and includes checking for required fields and validating the data format.

[1074] For data that has been successfully validated, the server applies machine learning models. Specifically, it uses revenue forecasting models and cost management models to analyze the data using Python machine learning libraries (TensorFlow and Scikit-learn). For example, this can predict next fiscal year's sales based on past sales data and market conditions.

[1075] The server then generates a specific answer or recommendation for the user based on the analysis results, where business logic is applied to generate a specific action plan, such as "increase your marketing budget by 5%."

[1076] The server then converts the generated answers and suggestions back into JSON format and sends them to the device, which parses the results and displays them in a user-friendly format (e.g., graphs or tables).

[1077] For example, if a user requests "Please prepare the income statement for the next fiscal year," the flow is as follows:

[1078] The user inputs banking data or budget data. For example, a prompt such as "Please generate a profit and loss statement for 2023" is used. The terminal converts the input data into JSON format and sends it to the server. The server validates the data and uses machine learning models to generate a profit and loss statement based on sales, costs, operating expenses, etc. The server then sends the generated profit and loss statement in JSON format to the terminal, which parses the results and displays them to the user. For example, the profit and loss statement can be visually displayed using bar graphs or pie charts.

[1079] In this way, the system generates and provides users with fast and accurate answers and suggestions based on the data they enter, making the entire process from data entry to analysis and display of results efficient.

[1080] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1081] Step 1: User Input

[1082] The user uses a device (PC or smartphone) to input financial data and information about the business plan. For example, they input a prompt in text format such as, "I would like to know the sales forecast for next fiscal year." The information input includes past sales data and market conditions. The data provided by the user is sent to the device.

[1083] Step 2: Send data

[1084] The device converts the information entered by the user into JSON format. This conversion process ensures that the input data is properly formatted. The device then sends the JSON data to the server using HTTPS, which encrypts the data in transit and ensures a secure transfer.

[1085] Step 3: Data Receipt and Validation

[1086] The server receives the JSON data sent from the terminal. It validates the received data using a Python data validation library (for example, Cerberus). The purpose of validation is to check whether all required fields are filled in and whether the data format is correct. For example, if sales data is missing, an error message is generated. If validation is successful, the data proceeds to the parsing step.

[1087] Step 4: Data analysis

[1088] The server applies machine learning models to data that has passed validation. Specifically, it uses Python machine learning libraries (TensorFlow and Scikit-learn) to create revenue forecasting models and cost management models. In the analysis process, past sales data and market conditions are used as input data to predict future revenue and costs. For example, sales data from the past five years is used as input, and the output is a sales forecast for the next fiscal year.

[1089] Step 5: Answer Generation

[1090] The server generates specific answers and recommendations to provide to the user based on the analysis results. In this step, business logic is applied to derive the most beneficial recommendation for the user. For example, a specific recommendation such as "increase your marketing budget by 5%" is generated. The generated answers and recommendations are then converted back to JSON format.

[1091] Step 6: Send results

[1092] The server then converts the answers and suggestions into JSON format and sends them to the device. Again, data is encrypted during transmission and securely transferred. The server uses HTTPS to ensure confidentiality and integrity of the data.

[1093] Step 7: View the results

[1094] The terminal parses the JSON data received from the server and displays it in a user-friendly format. Specifically, it visualizes the results in graphs and tables on a web browser. For example, it displays the sales forecast results as a bar graph and the cost structure as a pie chart.

[1095] In this way, the user, terminal, and server work together at each step, enabling efficient processing from user input to analysis and display of results.

[1096] (Application example 1)

[1097] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1098] Conventional product recommendation systems for brick-and-mortar stores have struggled to effectively utilize users' purchasing history, reviews, inventory information, and other data to provide optimal product recommendations for each individual user. Furthermore, real-time data analysis and rapid feedback are required to improve the user experience in brick-and-mortar stores. However, existing systems were unable to meet these requirements.

[1099] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1100] In this invention, the server includes means for receiving user input, terminal means for converting the user input into a data format and transmitting it, means for analyzing the received data, means for generating a response based on the analysis result, means for transmitting the response to the terminal, means for displaying the response to the user, and means for reviewing the user input in the store and optimizing product suggestions based on data including purchase history and inventory information. This makes it possible to realize optimal product suggestions and promotions and provide real-time feedback in physical stores based on users' purchase history, reviews, and inventory information.

[1101] "User input" means information or data provided by a user to a system.

[1102] "Terminal means" refers to a device that processes data entered by a user, converts it into an appropriate format, and transmits it to the server.

[1103] The "server means" refers to a computer that analyzes the received data and generates a response based on the results.

[1104] The "analysis result" refers to the result obtained by the server means processing the data.

[1105] "Answer generation" refers to the process of creating feedback and suggestions for users based on the analysis results.

[1106] "Display means" refers to a device or method for visually presenting the generated answer to the user.

[1107] "Means for optimization" refers to a mechanism for processing product suggestions provided based on user-entered data in a way that is most beneficial to the user.

[1108] A "machine learning model" is a model that uses algorithms to make predictions and classifications based on large amounts of data.

[1109] "Business logic" refers to the standards and methods that guide rational decisions and actions in commercial activities.

[1110] The system of the present invention receives user input, analyzes the received data, and provides an optimal answer. An embodiment of the system will be described in detail below.

[1111] First, a user uses a device such as a smartphone or tablet to input information such as purchase history, product reviews, and the current contents of their cart. This device converts the input user information into an appropriate data format (e.g., JSON format) and sends the data to the server.

[1112] The server receives and analyzes the transmitted data. A machine learning model built using Python machine learning libraries (e.g., TensorFlow and Scikit-Learn) is installed on the server. This machine learning model learns user preferences and purchasing patterns based on past data, and generates optimal product suggestions and promotions for new data.

[1113] Based on the analysis results, the server generates an answer for the user. Business logic is applied to this answer generation process to create the most useful suggestions for the user. For example, the server may analyze the user's preferred product categories based on their purchase history and reviews, and prioritize suggestions for products in those categories.

[1114] The server then converts the generated response back into JSON format and sends it to the device, which parses the results and displays them visually to the user, typically in the form of graphs and tables showing product suggestions and promotional information.

[1115] This system allows for quick and accurate product suggestions in physical stores based on users' purchasing history, reviews, and inventory information.

[1116] Specific examples

[1117] Example 1: When a user scans an item in a store, the system will suggest the most suitable product based on their past purchase history and reviews.

[1118] Prompt: "Please suggest my next purchase based on past electronics purchase data."

[1119] Example 2: Based on inventory information, notify customers to purchase low-stock items as soon as possible.

[1120] Prompt: "Based on your inventory data, which item would you suggest this customer purchase sooner?"

[1121] To implement this invention, the following hardware and software are required:

[1122] Hardware: smartphones, tablets, servers

[1123] Software: Python, TensorFlow, Scikit-Learn, JSON parser, web framework (e.g., Flask, Django)

[1124] These configurations enable efficient data entry by users, analysis, generation of results, and display.

[1125] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1126] Step 1:

[1127] The user uses a smartphone or tablet to enter purchase history, product reviews, and current cart contents.

[1128] Specific operation: The user enters their purchase history, product reviews, and product information in the cart into the application's input form. This data is automatically saved in the input fields.

[1129] Input: Raw data entered by users such as purchase history, product reviews, and cart contents.

[1130] Output: The raw data that is passed to the next step.

[1131] Step 2:

[1132] The terminal converts the entered user information into JSON format and sends it to the server.

[1133] Specific operation: The terminal application retrieves data from the input field, and a parser runs to convert it to JSON format. The converted data is then sent to the server as an HTTP request.

[1134] Input: Raw data from the user.

[1135] Output: Data converted to JSON format.

[1136] Step 3:

[1137] The server receives the transmitted data and performs data validation.

[1138] Specific operation: The API receives an HTTP request on the server side, applies validation rules to check the format and content of the received data, and filters out invalid data.

[1139] Input: JSON data sent from the terminal.

[1140] Output: Clean data that passes validation.

[1141] Step 4:

[1142] The server uses machine learning models to analyze the data that passes validation.

[1143] How it works: Using Python libraries (TensorFlow or Scikit-Learn), the clean data is analyzed. Machine learning models predict purchasing patterns and user preferences and identify the next best product, taking into account the user's past behavior and external market data.

[1144] Input: Clean data after validation.

[1145] Output: Suggested products and promotions as analysis results.

[1146] Step 5:

[1147] Based on the analysis results, the server applies business logic to generate the optimal answer for the user.

[1148] What it does: Based on the analysis results, specific business logic (for example, a strategy aimed at increasing sales in a specific product category) is applied, and optimized product suggestions and promotions are generated in text format.

[1149] Input: Analysis results of machine learning models.

[1150] Output: Optimized answers (product suggestions and promotions) with business logic applied.

[1151] Step 6:

[1152] The server converts the generated response back into JSON format and sends it to the terminal.

[1153] Specific operation: The API operates to encode the text response generated by the server into JSON format and send it to the terminal as an HTTP response.

[1154] Input: The answer generated by applying business logic.

[1155] Output: The answer converted to JSON format.

[1156] Step 7:

[1157] The terminal receives the transmitted results and displays them to the user in a visually understandable manner.

[1158] What happens: The device application receives the HTTP response, decodes the data using a JSON parser, and displays it to the user in the form of a graph or table.

[1159] Input: The JSON response sent by the server.

[1160] Output: Offers and promotions visually displayed to the user.

[1161] In this way, the data entered by the user is analyzed efficiently, and optimal product suggestions and promotions are realized.

[1162] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1163] This invention relates to a system that receives user input, analyzes the data, and provides fast and accurate responses. This system includes a terminal operated by the user and a server that processes and analyzes the data. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, more personalized responses are possible.

[1164] User Input

[1165] A user uses a device (such as a PC or smartphone) to input financial data and information about a business plan and request an analysis. For example, the user might input "Please tell me the sales forecast for next fiscal year," and then input past sales data and market conditions. In this case, the device recognizes not only the data entered by the user, but also the user's emotions.

[1166] emotion recognition

[1167] The device uses natural language processing and machine learning to recognize emotions from users' text inputs and voices, and the emotion engine generates user emotion data along with the input data.

[1168] Data transmission

[1169] The device converts the input information, including the recognized emotion data, into JSON format and sends it to the server using an HTTP POST request. The server receives this data and is ready to begin analysis.

[1170] Data analysis

[1171] The server validates the received data and analyzes it using machine learning models, such as revenue forecasting and cost management models, to predict future revenues and costs. This analysis uses Python machine learning libraries (e.g., TensorFlow and Scikit-learn).

[1172] Emotion-based answer generation

[1173] The server takes the emotion engine's output into account when generating answers and suggestions for the user based on the analysis results. For example, if it recognizes that the user is feeling stressed, it will provide a simpler suggestion with less emphasis. It then applies business logic to generate a specific suggestion (e.g., "Increase your marketing budget by 5%)."

[1174] Sending and displaying results

[1175] The server converts the generated results back into JSON format and sends them to the terminal as an HTTP response. The terminal parses the received results and displays them in a user-friendly format, for example, in a graph or table format on the browser.

[1176] Specific examples

[1177] For example, if a user enters "Please prepare the income statement for next fiscal year," the flow is as follows:

[1178] 1. User: Enters banking data, budget data, etc., while the system recognizes the user's emotions.

[1179] 2. Terminal: Converts input data and recognized emotion data into JSON format and sends it to the server.

[1180] 3. Server: Validates and analyzes the data received, e.g., generates a profit and loss statement based on sales, costs, operating expenses, etc.

[1181] 4. Server: Based on the analysis results, generate a profit and loss statement taking into account the user's emotions and make recommendations with the appropriate tone and level of detail.

[1182] 5. Server: Sends the generated results to the device.

[1183] 6. Terminal: Parses the received results and displays the P&L to the user.

[1184] In this way, the system generates and provides users with fast and accurate answers and suggestions based on the user's input data and emotional data, thereby efficiently carrying out the entire process from data input to analysis and display of results, and providing personalized services that respond to the user's emotions.

[1185] The processing flow will be explained below.

[1186] Step 1:

[1187] The user inputs data into the device. For example, they might type, "Please tell me your sales forecast for next fiscal year," and then enter past sales data and market conditions. At this time, the device recognizes emotions from the user's text input and voice.

[1188] Step 2:

[1189] The device converts the information entered by the user into JSON format, attaches the recognized emotion data, and sends it to the server as an HTTP POST request.

[1190] Step 3:

[1191] The server receives the data sent from the terminal. Specifically, it deserializes the received JSON data and converts it into an object format.

[1192] Step 4:

[1193] The server validates the received data by checking whether the data format is correct, whether any items are missing, and whether the values ​​are appropriate.

[1194] Step 5:

[1195] The server then performs analysis using the validated data, using a pre-trained machine learning model, such as a sales forecasting model.

[1196] Step 6:

[1197] The server adjusts its analysis based on the output of the emotion engine, for example softening the tone of suggestions and feedback if the user is feeling stressed.

[1198] Step 7:

[1199] The server generates specific proposals based on business logic, such as "increase marketing budget by 5%."

[1200] Step 8:

[1201] The server converts the generated response back into JSON format and sends it to the terminal as an HTTP response.

[1202] Step 9:

[1203] The device parses the JSON data received from the server and displays the results to the user, for example, in a browser in the form of a graph or table.

[1204] Step 10:

[1205] The user reviews the displayed results and enters further questions or data as needed, in which case steps 1 through 9 are repeated again.

[1206] Example 2

[1207] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1208] Conventional systems have difficulty considering the user's emotions when analyzing user input and generating answers, resulting in impersonal responses. Furthermore, they lack personalized responses based on the user's emotional state, making it difficult to improve the user experience.

[1209] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes terminal means for converting a user's input into a data format and generating emotion data, means for transmitting input information including the recognized emotion data to the server, means for validating the received data, means for analyzing the data using a machine learning model, and means for generating a response according to the emotion based on the analysis result. This enables a personalized response that takes the user's emotion into consideration.

[1210] "User input" means information or data provided by a user to a system through a terminal.

[1211] "Terminal means" refers to a device or software that receives input from a user, converts it into a data format, and generates emotion data as needed.

[1212] "Emotional data" refers to information that represents a user's emotional state as recognized from the user's input.

[1213] "Server means" refers to devices and software that receive data sent from a terminal and process and analyze it.

[1214] "Validation" is the process of verifying that the format and content of received data are correct.

[1215] A "machine learning model" is a mathematical and statistical model that learns patterns and knowledge from data and performs analysis and predictions.

[1216] "Analysis Results" means the results obtained after processing and analyzing data using a machine learning model.

[1217] "Answer generation means" refers to a device or software that generates an answer to be provided to the user based on the analysis results.

[1218] This invention relates to a system that receives user input, analyzes the data, and provides fast and accurate responses. The system includes a terminal operated by the user and a server that processes and analyzes the data. It also incorporates an emotion engine that recognizes the user's emotions, enabling more personalized responses.

[1219] User Input

[1220] A user uses a device (such as a PC or smartphone) to input financial data and information about a business plan and request an analysis. For example, the user might type, "Please tell me the sales forecast for next fiscal year," and then input past sales data and market conditions into the device. In this case, the device recognizes not only the data entered by the user, but also the user's emotions.

[1221] emotion recognition

[1222] The device uses the natural language processing (NLP) library SpaCy to analyze the user's text input. It also converts voice input into text using a speech recognition library (e.g., Google Speech-to-Text API). It then uses the NLP analysis results and a machine learning model (e.g., Scikit-learn's emotion classification model) to recognize the user's emotions. The emotion engine generates user emotion data in conjunction with the input data.

[1223] Data transmission

[1224] The device converts the input information, including the recognized emotion data, into JSON format and sends it to the server using an HTTP POST request. For example, it generates the following JSON data:

[1225] json

[1226] {

[1227] "user_input": "Please tell us your sales forecast for next fiscal year",

[1228] "sentiment": "anxiety"

[1229] }

[1230] Send this data through a RESTful API.

[1231] Data analysis

[1232] The server validates the received data. First, it checks whether the input data and sentiment data are correctly formatted. If validation is successful, the server analyzes the data using a machine learning model (e.g., a model using TensorFlow). For example, it predicts future sales based on past sales data and market conditions.

[1233] Emotion-based answer generation

[1234] The server takes the output of the emotion engine into consideration when generating answers and suggestions for the user based on the analysis results. For example, if the user is feeling anxious, it will generate a message in a simple language that gives a sense of security. Specifically, it will generate a sentence such as, "Sales forecast for next fiscal year is 5 million yen. Don't worry, everything is going well."

[1235] Sending and displaying results

[1236] The server then converts the generated results back into JSON format and sends them to the device as an HTTP response. The device then parses the results and displays them in a user-friendly format. For example, the browser might display sales forecasts in graphs and tables, along with personalized messages based on user sentiment.

[1237] Specific examples

[1238] For example, if a user types "Please prepare the income statement for next period," the flow would be as follows:

[1239] 1. User: Enters banking data, budget data, etc. The system recognizes the user's emotions.

[1240] 2. Terminal: Converts input data and recognized emotion data into JSON format and sends it to the server.

[1241] 3. Server: Validates and analyzes the data received, e.g., generates a profit and loss statement based on sales, costs, operating expenses, etc.

[1242] 4. Server: Based on the analysis results, generate a profit and loss statement taking into account the user's emotions and make recommendations with the appropriate tone and level of detail.

[1243] 5. Server: Sends the generated results to the device.

[1244] 6. Terminal: Parses the received results and displays the P&L to the user.

[1245] Example prompt sentence:

[1246] "What are your sales forecasts for next fiscal year? Last year's sales data and market conditions are as follows: [data]."

[1247] This series of processes enables the system to provide fast and accurate answers and suggestions based on the user's input data and emotional data, thereby efficiently carrying out the entire process from data input to analysis and display of results, while also providing personalized services that respond to the user's emotions.

[1248] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1249] Step 1:

[1250] Receiving user input

[1251] Users use devices (such as PCs or smartphones) to input financial data and information about business plans. Examples of input content include, "Please tell me your sales forecast for next fiscal year." The data entered by users is stored in text format on the device.

[1252] Input: User text input

[1253] Output: Saved user text data

[1254] Step 2:

[1255] Performing emotion recognition

[1256] The device uses the natural language processing (NLP) library SpaCy to analyze the user's text input. It also converts voice input into text using a speech recognition library (e.g., Google Speech-to-Text API). It then uses the NLP analysis results and a machine learning model (e.g., Scikit-learn's emotion classification model) to recognize the user's emotions.

[1257] Input: User text input, voice data

[1258] Output: User sentiment data

[1259] Step 3:

[1260] Data conversion and transmission

[1261] The device converts the user's input data and the recognized emotion data into JSON format. For example, it generates the following JSON data:

[1262] json

[1263] {

[1264] "user_input": "Please tell us your sales forecast for next fiscal year",

[1265] "sentiment": "anxiety"

[1266] }

[1267] The resulting JSON data is then sent to the server using an HTTP POST request.

[1268] Input: User input data, emotion data

[1269] Output: JSON data sent to the server

[1270] Step 4:

[1271] Data Validation

[1272] The server validates the data it receives. First, it checks whether the input data and emotion data are correctly formatted. The software used includes validation tools such as JSON Schema. It checks for missing data or formatting errors.

[1273] Input: Received JSON data

[1274] Output: Validation result (success or error)

[1275] Step 5:

[1276] Performing data analysis

[1277] The server begins analysis based on the successfully validated data. It uses a machine learning model (for example, a model using TensorFlow) to predict future sales based on past sales data and market conditions. Specific analysis operations include data preprocessing, feature extraction, and application of the predictive model.

[1278] Input: Data that has been successfully validated

[1279] Output: Analysis results (e.g., sales forecast for the next fiscal year)

[1280] Step 6:

[1281] Emotion-based answer generation

[1282] The server takes into account the output of the emotion engine when generating an answer to provide to the user based on the analysis results. For example, if the user is feeling anxious, it generates a simple, reassuring message. The generated answer might look like this: "Sales forecast for next fiscal year is 5 million yen. Don't worry, everything is going well."

[1283] Input: Analysis results, emotion data

[1284] Output: Sentiment-based response data

[1285] Step 7:

[1286] Sending and displaying results

[1287] The server then converts the generated response data back into JSON format and sends it to the device as an HTTP response. The device then parses the results and displays the sales forecast in a browser in graph and table format, along with a message based on the user's emotions.

[1288] Input: Response data

[1289] Output: The result displayed to the user

[1290] (Application example 2)

[1291] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1292] Conventional systems analyze data and generate suggestions based on user input, but because they do not take into account the user's emotional state, it is difficult to provide personalized advice that takes into account factors such as stress and fatigue. This is particularly true for robot operators on factory floors, who are given uniform maintenance and operation instructions without considering their emotional state, which creates a problem of not being able to optimize workload and efficiency.

[1293] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1294] In this invention, the server includes means for receiving user input, means for converting the user input into a data format and transmitting it, means for analyzing the received data, means for generating an answer based on the analysis result, means for displaying the answer to the user, emotion recognition means for recognizing the user's emotional state and generating data on that, and emotion reflection means for generating an answer based on the user's emotional state, thereby enabling personalized advice and suggestions that take the user's emotional state into consideration.

[1295] "User input" refers to information or instructions provided by a user operating a system.

[1296] "Terminal means" refers to a device that converts user input into a data format and transmits and receives it.

[1297] The "server means" is a device that analyzes the received data and generates a response based on the results.

[1298] The "answer generation means" is a device that creates answers and suggestions for users based on the results of data analysis.

[1299] An "emotion recognition means" is a device that recognizes the user's emotional state and generates data on it.

[1300] The "emotion reflection means" is a device that generates answers and suggestions by reflecting the user's emotional state generated by the emotion recognition means.

[1301] "Machine Learning Model" means a machine learning algorithm or system used to perform data analysis on the server means.

[1302] "Business logic" refers to logic or rules based on specific business objectives or conditions that are used by the answer generation means.

[1303] As an embodiment of the present invention, consider a smartphone application used by a robot operator in a factory. The application is a system in which the operator inputs data about the robot's operational status and the site environment, and the data is analyzed in real time. The smartphone receives user input, converts it into a data format, and sends it to a server. The server analyzes the received data and generates a response based on the analysis results.

[1304] First, the operator inputs the robot's operating time, number of errors, vibration data, etc. via a smartphone (iOS or Android), and also obtains the robot's emotional state via voice input. The input data is converted into JSON format and sent to the server via an HTTP POST request. The server receives this data, validates it, and then analyzes it using a machine learning model (such as TensorFlow). Based on the analysis results, for example, if a certain number of errors or vibration level is exceeded, it will recognize that maintenance is necessary. In addition, an emotion recognition means takes into account the user's stress level and fatigue level, and generates advice and suggestions that reflect the user's emotional state.

[1305] Specifically, the system uses a front-end and back-end system written in Python. Data acquired by this system is analyzed using a machine learning model using TensorFlow to generate appropriate maintenance instructions and operation suggestions. Emotion recognition is also performed using the Google Cloud Natural Language API.

[1306] For example, if a user inputs "80 hours of operation, 5 errors, vibration level 3.2" into their smartphone and reports "stress level 2" by voice, the server will analyze these inputs. If the emotion recognition means detects a high stress state, the server will add advice such as "We recommend taking a break" in addition to suggesting maintenance based on the analysis results.

[1307] Examples of prompts for generative AI models are as follows:

[1308] Context: This is an application used by factory robot operators to provide optimal maintenance and rest instructions based on the robot's operating status and the operator's emotional state.

[1309] Question: If a robot has 80 hours of operation, has 5 errors, and the operator's stress level is 2, what maintenance instructions should be given?

[1310] These prompts can be used as input to an AI model to efficiently generate optimal maintenance and rest instructions, allowing operators to perform their work efficiently and safely.

[1311] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1312] Step 1:

[1313] The user uses a smartphone to input operational data such as the robot's operating time, number of errors, vibration data, and stress level. At the same time, an emotion recognition engine is used to obtain emotional data such as stress level from voice. The input data is in text and audio format.

[1314] Step 2:

[1315] The device converts the text data and emotion data entered by the user into JSON format. Specifically, it creates a JSON object with a dictionary-style data structure, with operating time, number of errors, vibration level, and stress level as keys. This becomes the input data for the next step.

[1316] Step 3:

[1317] The JSON data sent from the device is sent to the server using an HTTP POST request, which also includes metadata such as the user ID and timestamp to manage the data transmission and reception.

[1318] Step 4:

[1319] The server parses and validates the received JSON data. For example, it checks that the uptime is greater than or equal to zero and that the number of errors is not a negative value. Only data that passes this validation is analyzed in the next step.

[1320] Step 5:

[1321] The server inputs the validated data into a machine learning model (such as TensorFlow). The machine learning model analyzes the robot's operational data and predicts the need for maintenance, for example, if a certain number of errors or vibration levels exceed a certain standard. This analysis is based on the data the model has previously learned.

[1322] Step 6:

[1323] The server generates answers and suggestions based on the analysis results of the machine learning model. Specifically, it takes into account the analysis results as well as the user's emotional data, and adds easy-to-understand messages and instructions to take a break if the stress level is high. The answer generation means applies business logic to form specific suggestions for maintenance and operational adjustments.

[1324] Step 7:

[1325] The server then converts the generated answers and suggestions back into JSON format and sends them back to the device as an HTTP response, which includes the analysis results and sentiment-based advice.

[1326] Step 8:

[1327] The device parses the received JSON data and displays it in a user-friendly format. Specifically, it displays the results in text and graph format on the smartphone application screen, highlighting important suggestions and advice. It also uses prompts to the generative AI model to prepare for the next input.

[1328] Context: This is an application used by factory robot operators to provide optimal maintenance and rest instructions based on the robot's operating status and the operator's emotional state.

[1329] Question: If a robot has 80 hours of operation, has 5 errors, and the operator's stress level is 2, what maintenance instructions should be given?

[1330] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1331] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1332] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1333] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1334] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1335] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1336] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1337] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1338] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1339] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1340] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1341] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1342] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1343] 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.

[1344] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1345] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1346] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1347] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1348] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1349] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1350] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1351] The following is further disclosed regarding the above embodiment.

[1352] (Claim 1)

[1353] means for receiving user input;

[1354] terminal means for converting user input into a data format and transmitting the data;

[1355] Server means for analyzing the received data;

[1356] means for generating an answer based on the analysis results;

[1357] means for transmitting the response to a terminal;

[1358] means for displaying said answer to a user;

[1359] A system including:

[1360] (Claim 2)

[1361] 10. The system of claim 1, wherein the server means includes means for analyzing data using a machine learning model.

[1362] (Claim 3)

[1363] 10. The system of claim 1, wherein the answer generating means includes means for generating business logic-based suggestions.

[1364] (Claim 4)

[1365] 10. The system of claim 1, further comprising means for validating the received data.

[1366] "Example 1"

[1367] (Claim 1)

[1368] means for receiving user input;

[1369] terminal means for converting user input into a data format and transmitting the data;

[1370] a server means for validating received data;

[1371] a server means for analyzing the validated data using a machine learning model;

[1372] means for generating an answer based on the analysis results;

[1373] means for transmitting the response to a terminal;

[1374] means for displaying said answer to a user;

[1375] A system including:

[1376] (Claim 2)

[1377] The system of claim 1, wherein the analysis used by the server means includes a Python machine learning library.

[1378] (Claim 3)

[1379] 10. The system of claim 1, wherein the answer generating means includes means for generating a business logic-based suggestion (e.g., adjusting a marketing budget).

[1380] "Application Example 1"

[1381] (Claim 1)

[1382] means for receiving user input;

[1383] terminal means for converting user input into a data format and transmitting the data;

[1384] Server means for analyzing the received data;

[1385] means for generating an answer based on the analysis results;

[1386] means for transmitting the response to a terminal;

[1387] means for displaying said answer to a user;

[1388] The system includes a means for reviewing user input in-store and optimizing product recommendations from data including purchase history and inventory information.

[1389] (Claim 2)

[1390] 10. The system of claim 1, wherein the server means includes means for analyzing data using a machine learning model.

[1391] (Claim 3)

[1392] 10. The system of claim 1, wherein the answer generating means includes means for generating business logic-based suggestions.

[1393] "Example 2: Combining Emotion Engines"

[1394] (Claim 1)

[1395] means for receiving user input;

[1396] a terminal means for converting a user's input into a data format and generating emotion data;

[1397] means for transmitting input information including the recognized emotion data to a server;

[1398] a server means for validating received data;

[1399] a means of analyzing the data using machine learning models;

[1400] A means for generating an answer according to the emotion based on the analysis result;

[1401] means for transmitting the response to a terminal;

[1402] means for displaying said answer to a user;

[1403] A system including:

[1404] (Claim 2)

[1405] 10. The system of claim 1, further comprising means for recognizing emotions using a machine learning library.

[1406] (Claim 3)

[1407] 10. The system of claim 1, further comprising means for providing a personalized response based on the recognized emotion data.

[1408] "Application example 2 when combining emotion engines"

[1409] (Claim 1)

[1410] means for receiving user input;

[1411] terminal means for converting user input into a data format and transmitting the data;

[1412] Server means for analyzing the received data;

[1413] means for generating an answer based on the analysis results;

[1414] means for transmitting the response to a terminal;

[1415] means for displaying said answer to a user;

[1416] an emotion recognition means for recognizing an emotional state of a user and generating data thereon;

[1417] an emotion reflection means for generating an answer based on the user's emotional state;

[1418] A system including:

[1419] (Claim 2)

[1420] 10. The system of claim 1, wherein the server means includes means for analyzing data using a machine learning model.

[1421] (Claim 3)

[1422] 10. The system of claim 1, wherein the answer generating means includes means for generating business logic-based suggestions. [Explanation of symbols]

[1423] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving user input; terminal means for converting user input into a data format and transmitting the data; Server means for analyzing the received data; means for generating an answer based on the analysis results; means for transmitting the response to a terminal; means for displaying said answer to a user; A system including:

2. The system of claim 1 , wherein the server means includes means for analyzing data using a machine learning model.

3. The system of claim 1 , wherein the answer generating means includes means for generating business logic-based suggestions.

4. 10. The system of claim 1, further comprising means for validating the received data.

Images