system

Abstract

Provide a system. 【Solution means】 Data collection means, Data processing means for integrating the collected data and performing preprocessing, Model selection means for selecting and applying an analysis model based on the preprocessed data, Result generation means for generating and visualizing the analysis result, Proposal creation means for generating a proposal for business improvement based on the analysis result, Interface means for providing the proposal to the user and collecting responses, Response processing means for improving the model based on the response, Planning optimization means for assisting in the handling plan of articles in the warehouse, Anomaly detection means for detecting anomalies using the information and sending warnings, A system including.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventionally, the management issues faced by small and medium-sized enterprises included high costs, dependence on subjective consulting services, and lack of sufficient data analysis for rapid decision-making. For this reason, it was difficult to optimally allocate management resources and enhance competitiveness. Furthermore, the quality control of the collected data and the need for rapid update of the model in response to changes in the external environment were also issues.

Means for Solving the Problems

[0005] This invention relates to a data-driven AI business consultant system that acquires various types of corporate data using data collection means, integrates and preprocesses the data using data processing means to ensure data quality. Furthermore, it selects an appropriate analysis model using model selection means, performs analysis using result generation means, and presents the results visually. It documents optimal management improvement measures in natural language using advice creation means and provides them to the user through interface means. By receiving feedback from the user and improving the model using feedback processing means, it provides the latest and most optimal advice at all times, thereby solving management challenges effectively and at low cost.

[0006] "Data collection means" refers to a function that automatically acquires necessary data from various data sources within a company.

[0007] "Data processing means" refers to functions that integrate collected data and perform tasks such as imputing missing values ​​and correcting outliers for the purpose of ensuring quality.

[0008] A "model selection means" is a function that selects and applies an analysis model suitable for the problem based on pre-processed data.

[0009] The "result generation means" is a function that generates the output of the applied analysis model in a visually understandable format.

[0010] The "advice generation tool" is a function that documents specific suggestions for business improvement in natural language based on the analysis results.

[0011] An "interface means" is a function for providing generated advice to the user and for collecting feedback from the user.

[0012] A "feedback processing mechanism" is a function that re-evaluates the analysis model based on user feedback and improves it as needed. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

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

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

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The AI ​​business consultant system according to the present invention is designed to support corporate decision-making by automating the entire process from the collection and analysis of relevant data to the provision of results. The entire system operates between a server, a terminal, and a user.

[0035] The server first periodically accesses the company's data sources to collect necessary information. It retrieves data from various sources, such as ERP systems, CRM systems, and external market databases, and manages it centrally.

[0036] Next, the server uses data processing tools to integrate and preprocess the collected data. Since the collected data may contain missing or outlier values, the accuracy of the analysis is improved by appropriately imputing or correcting these.

[0037] Based on the processed data, the server uses a model selection mechanism to choose the optimal analysis model and applies that model. In this process, the server utilizes machine learning and statistical analysis algorithms to select the most suitable model according to the characteristics of the data.

[0038] Once the analysis is complete, the server visually represents the results through a results generation mechanism. These results are presented not only as numerical data but also in a graphical format, supporting corporate decision-making.

[0039] The terminal provides the user with the generated analysis results and advice. The advice generation mechanism presents these results to the user in an easy-to-understand report format using natural language processing technology.

[0040] At that time, the user reviews the advice provided via the terminal and provides feedback. This feedback includes the effectiveness of the suggested advice and the results of its application. Based on this, the server re-evaluates the model using the feedback processing mechanism and makes improvements.

[0041] For example, if a small or medium-sized enterprise is considering launching a new product, this system analyzes market data and historical sales data to suggest the optimal launch timing and target market. It can also evaluate the effectiveness of the suggestions after implementation, contributing to the development of future strategies.

[0042] Thus, the present invention provides data-driven analysis and advice, thereby helping to move away from conventional subjective decision-making and support the formulation of sophisticated business strategies.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server accesses various data sources within the company and periodically collects the necessary data using APIs and data import tools. This ensures that the system incorporates the latest information.

[0046] Step 2:

[0047] The server integrates the collected data using data processing tools and performs data cleansing. Missing values ​​are imputed based on past trends and averages, and outliers are identified and corrected. These processes are performed automatically to ensure data quality.

[0048] Step 3:

[0049] Based on the preprocessed data, the server uses a model selection mechanism to choose the optimal analysis model. For example, a time series forecasting model or a clustering algorithm may be selected, and the most suitable application is made according to the data characteristics.

[0050] Step 4:

[0051] The server applies the selected model to analyze the data. The analysis results are output as numerical data, which are then visualized in graph or dashboard format by a results generation tool.

[0052] Step 5:

[0053] Based on the analysis results, the server uses an advice generation system to create specific business improvement advice. This advice is documented using natural language processing technology and compiled into a report.

[0054] Step 6:

[0055] The terminal notifies the user of the generated report and displays the details through a dedicated interface. Based on this, the user makes decisions and develops actionable strategies.

[0056] Step 7:

[0057] The user provides feedback to the server via their terminal, showing the results after implementing the suggested advice. This feedback includes information about the effectiveness of the advice and the results of its application.

[0058] Step 8:

[0059] The server collects user feedback and uses feedback processing to evaluate the model. It adjusts the analysis model as needed to improve the accuracy of subsequent analyses.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] Businesses and organizations require vast amounts of diverse data to make informed business decisions. However, efficiently collecting this data, analyzing it consistently, and providing appropriate advice is challenging. Furthermore, data preprocessing to improve quality and adapting models to dynamic market environments are necessary, but performing these manually is time-consuming and costly. This invention aims to solve these problems and provide an automated, data-driven decision support system.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for accessing information sources and collecting relevant information, data processing means for integrating and preprocessing the collected information, including imputing missing values ​​and correcting outliers, and model selection means for selecting and applying the optimal analysis model based on the preprocessed information. This makes it possible to efficiently process diverse data and quickly provide accurate analysis results.

[0065] "Information source" refers to an external or internal data provider from which a system collects data, and the source from which information is provided.

[0066] "Data processing means" refers to the process of preparing collected data for analysis, and includes means that perform functions such as imputing missing values ​​and correcting outliers.

[0067] A "model selection means" is a function that selects and applies the optimal analysis model based on pre-processed information.

[0068] The "result generation means" is a function that generates analysis results in numerical and graphical formats and presents them in a visually easy-to-understand manner.

[0069] A "guideline creation tool" is a function that generates and provides policies for business improvement based on analysis results.

[0070] "Means of communication" refers to means of providing guidance to users and receiving their feedback.

[0071] A "feedback processing mechanism" is a function for re-evaluating and improving the analysis model based on the collected feedback.

[0072] A "generative AI model" is a component of artificial intelligence that generates appropriate output from given input data, enabling analysis and prompt generation for decision support.

[0073] A "prompt" is a sentence that serves as an instruction or question to a generative AI model, providing guidance for the model to perform a specific task.

[0074] Modes for carrying out the invention

[0075] The AI ​​business consultant system of the present invention supports management decision-making by automating the collection, processing, and analysis of relevant information and the provision of feedback to the user. The main components of this system are realized through the interaction of a server, a terminal, and the user.

[0076] Data collection and processing

[0077] The server periodically accesses corporate data sources and automatically collects information from ERP systems, CRMs, external market databases, and other sources. This information may be obtained through various APIs or downloaded in file format and aggregated in one location. The server then integrates this collected information using data processing tools and performs preprocessing, including imputing missing values ​​and correcting outliers. Specific data processing software used includes Python libraries such as Pandas and NumPy.

[0078] Model selection and result generation

[0079] The server uses pre-processed information to select the most appropriate analysis model. Here, machine learning libraries such as TENSORFLOW® and Scikit-learn are utilized to perform modeling necessary for sales forecasting, market analysis, and other applications. The modeled results are visualized using Matplotlib and Tableau, and generated as graphs and dashboards.

[0080] Providing advice and feedback

[0081] The terminal receives analysis results generated from the server and uses natural language processing technology to create reports that are easy for the user to understand. This allows the user to receive detailed guidance on future market trend forecasts and product launch strategies. For example, based on the scenario "What is the optimal marketing strategy for the next quarter?", the system inputs the prompt "Predict market trends for the next quarter and indicate which product categories should be focused on" into the AI ​​model and proposes the optimal strategy.

[0082] Feedback and model improvement

[0083] Users make decisions based on guidelines received via their devices and provide feedback on the results. This feedback information is analyzed by the server and used for re-evaluation during model selection and data processing. This allows the system to continuously learn and improve, enabling it to continue providing highly accurate consulting tailored to user needs.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The server accesses sources such as ERP systems, CRMs, and external market databases to collect data. Inputs are provided in the form of APIs or data files. In this process, the server retrieves relevant information periodically as a scheduled task and integrates it into a centralized dataset. Output is the collected raw data, which is stored in a database.

[0087] Step 2:

[0088] The server preprocesses the collected data using data processing tools. The input is the raw data collected in step 1. Specifically, it uses the Python library Pandas to computationally impute missing values ​​and detect and remove outliers. This data processing results in a clean and consistent dataset.

[0089] Step 3:

[0090] The server selects and applies the optimal analysis model based on pre-processed data as input. It uses a machine learning library (e.g., Scikit-learn) to select a model based on data trends. In this case, models for sales forecasting and market trend analysis are selected and applied. The output consists of predicted data and trend visualizations as analysis results.

[0091] Step 4:

[0092] The server visualizes the analysis results and expresses them as numerical data and diagrams. The input is the analysis results generated in step 3. Specific operations include generating graphs using Matplotlib and creating dashboards using Tableau. The output is a report in a format that facilitates visual understanding.

[0093] Step 5:

[0094] The terminal uses the visualized results received from the server to generate a report using natural language processing technology. The input is the visualized data from step 4. Specifically, it uses a natural language generation library to output text that is easy for the AI ​​model to understand. The output is a guideline report to support user decision-making.

[0095] Step 6:

[0096] The user receives guidance from the terminal and makes decisions based on it. The input is the report from step 5. Specifically, the user inputs feedback into the terminal and evaluates its effectiveness and the validity of the suggestions. The output is sent back to the system as feedback information and used by the server to improve the model and advice generation process.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] Planning the handling of goods in a logistics center requires careful inventory management and optimization of shipping schedules. However, traditional methods make it difficult to effectively analyze large amounts of data, potentially leading to inefficient planning and incorrect decisions. A system is needed to solve these problems and improve the operational efficiency of logistics centers.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes data aggregation means, data processing means for integrating and pre-processing the collected data, model selection means for selecting and applying an analysis model based on the pre-processed data, planning optimization means for supporting the planning of goods handling in a warehouse, and anomaly detection means for detecting anomalies using the information and sending warnings. This enables optimization of operational plans and rapid response to anomalies in a logistics center.

[0102] A "data aggregation method" is a function that periodically acquires necessary information from internal and external sources within a company and stores it in a database.

[0103] "Data processing means" refers to a function that integrates collected information and formats it into an analyzable state by imputing missing values ​​and correcting outliers.

[0104] A "model selection means" is a function that includes an algorithm for selecting and applying the optimal analysis model based on preprocessed information.

[0105] A "result generation means" is a function for visually representing the results of the analysis as text or graphs.

[0106] A "proposal generation tool" is a function that generates proposals for business improvement based on analysis results.

[0107] An "interface means" is a function that provides suggestions to users and collects feedback from them.

[0108] A "response processing means" is a function that improves the analysis model based on feedback from the user.

[0109] "Planning optimization means" refers to functions that support the improvement of efficiency in goods management and shipping planning at logistics facilities.

[0110] An "anomaly detection method" is a function that identifies anomalies based on analysis results and real-time data, and issues warnings in a timely manner.

[0111] The server periodically collects necessary information from internal and external sources, such as ERP systems and market databases, using data aggregation tools. This information is stored in a database and used for subsequent processing. The collected information is integrated by data processing tools, and missing values ​​are imputed and outliers are corrected. This creates a dataset suitable for analysis.

[0112] Next, the server analyzes this preprocessed data by using a model selection mechanism to determine and apply the optimal analysis model. By utilizing machine learning algorithms and statistical analysis, advanced analysis tailored to the data characteristics is achieved. The analysis results are visualized as graphs and charts by a results generation mechanism. This provides information in a way that users can intuitively understand.

[0113] Furthermore, the server uses a proposal generation mechanism to generate business improvement proposals based on the analysis results. These proposals are expressed in an easy-to-understand format using natural language processing technology and provided to the user via a terminal. The user reviews the proposals via the terminal and provides a response, which the response processing mechanism then uses to improve the model.

[0114] As a concrete example, in inventory management at a logistics center, this system combines real-time inventory data with market demand forecast data to propose optimal replenishment plans and shipping strategies. Furthermore, if the anomaly detection mechanism detects an anomaly, it immediately sends a warning to the user, prompting quick action. An example of a prompt for the generated AI model is: "Select an analytical model for inventory optimization based on the following two data sets, and report the results in natural language. Inventory data: {inventory_data} Market demand data: {demand_data}".

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

[0116] Step 1:

[0117] The server uses data aggregation tools to periodically collect necessary data from sources such as ERP systems and market databases. In this step, the inputs include company inventory data and market demand data, and the output is the collected raw data stored in the database. The data collection process is periodically triggered by automated scripts to maintain data integrity.

[0118] Step 2:

[0119] The server uses data processing tools to integrate the collected raw data, imputing missing values ​​and correcting outliers. In this step, the raw data collected in step 1 is taken as input, and formatted data suitable for analysis is generated as output. Specifically, the data is cleansed to extract only the information necessary for analysis.

[0120] Step 3:

[0121] The server uses a model selection mechanism to select and apply the optimal analysis model based on the pre-processed data. In this step, the input is pre-processed data, and the output is the analysis results generated by the model. Machine learning algorithms are applied to perform predictions and clustering according to the data characteristics.

[0122] Step 4:

[0123] The server uses a results generation mechanism to visualize the analysis results in graphs and charts. In this step, the analysis results from step 3 are taken as input, and a visualized report is generated as output. The visualization tool organizes the information in an intuitively easy-to-understand format.

[0124] Step 5:

[0125] The server uses a proposal generation tool to generate proposals for business improvement based on visualized analysis results. In this step, visualized information is taken as input, and a proposal document expressed in natural language is generated as output. Natural language processing technology is used to convert complex data into concise sentences.

[0126] Step 6:

[0127] The terminal uses an interface to provide suggestions to the user. It then receives responses from the user. In this step, the input is a proposal document, and the output is the collection of user feedback. The user reviews the proposal on the terminal screen and inputs their own opinions and suggestions for improvement.

[0128] Step 7:

[0129] The server uses a response processing mechanism to improve the analysis model based on user feedback. In this step, user feedback is the input, and the improved analysis model is the output. The feedback information is used to adjust model parameters and train new data.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] This invention incorporates an emotion engine into an AI business consultant system, making it possible to provide business improvement advice that takes into account the user's emotional state. This system employs a more human-centered approach based on the interaction between the server, terminal, and user.

[0132] The server first automatically collects various types of corporate data and performs preprocessing of the integrated data. In addition to conventional data processing functions, it utilizes an emotion engine to analyze user emotion data collected during feedback. After data processing, the server selects an appropriate analysis model, analyzes the data, and generates results.

[0133] The generated analysis results are not simply presented as numerical data or graphical visual information, but are also adjusted to align with the user's emotions as analyzed by the emotion engine. This allows the server to create advice that takes the user's emotional state into account through an advice generation mechanism, and then compile it into a report format in natural language.

[0134] The terminal notifies the user of the generated report and allows the user to review the advice through the interface. The user receives the advice via the terminal, reviews its contents, and then considers its feasibility.

[0135] Furthermore, when users provide feedback on the effects after implementation, the emotion engine recognizes and classifies emotions from the user's text data. This feedback process allows the server to improve the model and adjust it so that future suggestions are more relatable and provide more effective advice to the user.

[0136] For example, in the case of a company considering new business development, this system utilizes historical market data and user feedback to not only analyze points of differentiation from competitors and market needs in detail, but also provides an approach that emphasizes risk mitigation measures if the user is feeling anxious. As a result, it can realize a next-generation consulting service that is more user-centric than traditional business advice.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The server accesses various data sources within the company and automatically collects the necessary data via APIs. Furthermore, it also incorporates data related to user sentiment during feedback.

[0140] Step 2:

[0141] The server integrates the collected data and performs preprocessing using data processing tools. Missing values ​​are imputed using mean values ​​or modes, and outliers are detected and corrected using a rule-based approach.

[0142] Step 3:

[0143] The server activates the emotion engine and analyzes the user's emotions from the collected feedback data. It then classifies these emotions into categories (e.g., positive, negative, neutral) using natural language processing.

[0144] Step 4:

[0145] The server selects the optimal analysis model based on the data and analyzed sentiment information. For example, it uses the ARIMA model for sales forecasting and a clustering algorithm for user interest analysis.

[0146] Step 5:

[0147] The server applies the selected analytical model and performs data analysis. The generated analysis results are visualized in the form of graphs and dashboards.

[0148] Step 6:

[0149] The server interprets the analysis results based on the user's emotions obtained from the emotion engine and generates advice. If the user expresses anxiety, the advice will emphasize risk avoidance measures.

[0150] Step 7:

[0151] The terminal notifies the user of the generated advice and displays a report. The user reviews the details of the advice through the interface.

[0152] Step 8:

[0153] Users follow the advice and provide feedback on the results. This feedback, including emotional input, is sent to the server via the device.

[0154] Step 9:

[0155] The server receives feedback data and uses feedback processing mechanisms to improve the model. User sentiment is reconsidered, and adjustments are made to reflect it in future advice.

[0156] (Example 2)

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

[0158] Traditional business consulting systems provide advice based on data analysis, but they have difficulty considering the user's emotional state. This has resulted in a lack of optimal advice tailored to the user's emotions, leading to problems with its feasibility and acceptability.

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

[0160] In this invention, the server includes data collection means, data processing means for integrating and pre-processing the collected data, and sentiment analysis means for analyzing the pre-processed data together with sentiment data. This makes it possible to provide business improvement advice that takes into account the user's emotional state, thereby improving feasibility and acceptability.

[0161] "Data collection means" refers to functions for automatically collecting various types of information related to a company, and it is possible to obtain necessary data from database connections and online information sources.

[0162] "Data processing means" refers to a process that integrates collected raw data, performs functions such as imputing missing values ​​and correcting outliers, and extracts sentiment data.

[0163] "Emotional analysis means" refers to a processing function that analyzes emotional states from user feedback and text data and assigns specific emotional tags to them.

[0164] "Model selection means" refers to a function that selects the optimal analytical model according to the analyzed data and applies it to the data to extract business insights.

[0165] "Result generation means" refers to a function that visualizes the results of data analysis as numbers and graphs, and further adjusts the expression of advice according to the user's emotional state.

[0166] "Advice generation method" refers to a function that uses a generative AI model and prompt text to document management improvement advice for users in natural language based on the analysis results obtained.

[0167] "Interface means" refers to an interactive platform that provides generated advice to the user and effectively collects feedback from the user.

[0168] "Feedback processing means" refers to a function that analyzes feedback collected from users, performs sentiment analysis, and improves the suggestion model based on the results to enhance the quality of advice for future use.

[0169] The embodiment of this invention is a system that is made possible by the collaboration of a server, a terminal, and a user.

[0170] The server uses a database connection to automatically collect various types of company information. This allows for the acquisition of diverse data such as sales data, customer feedback, and market research results. Data processing involves manipulating dataframes using the Python Pandas library, including imputing missing values ​​and correcting outliers. Furthermore, text analysis libraries such as Natural Language Toolkit are used to extract sentiment data from user feedback. The sentiment analysis system analyzes the user's emotional state based on this data and assigns sentiment tags. The analyzed data is then analyzed using machine learning models such as scikit-learn. The result generation system visualizes the data analysis results and adjusts them to take user emotions into consideration. Using a generative AI model, prompt sentences are used, and advice is documented using natural language processing techniques. This process ensures that the generated advice is easy for users to understand and leads to actual action.

[0171] The terminal notifies the user of advice generated by the server and provides a platform for the user to review the advice through an interface. Since this utilizes applications on smartphones and PCs, users can receive advice regardless of their location.

[0172] Users review the advice provided through their device and consider its feasibility. They then return feedback to the system, including the results of implementing the advice and their opinions. This feedback is then analyzed again by sentiment analysis tools and assigned sentiment tags. Using these results, the server can improve its next suggestion model and provide more personalized advice.

[0173] As a concrete example, a company considering a new business venture would utilize past market data and user feedback to analyze in detail its points of differentiation from competitors and market needs. In this case, an example of a prompt given to the AI ​​model would be: "For companies considering a new business venture, please analyze specific points of differentiation and market needs based on past market data and feedback, and propose measures to alleviate user concerns." This allows users to receive emotionally resonant and more actionable advice.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The server collects data related to the company. Input for data collection includes data from databases and external APIs. It uses SQL queries and API requests to retrieve sales data and customer feedback, and stores them in local storage. The output is an integrated dataset.

[0177] Step 2:

[0178] The server preprocesses the collected data. The input for this step is the integrated dataset obtained in step 1. Specifically, it uses the Python Pandas library to impute missing values ​​and correct outliers. The output is an improved dataset.

[0179] Step 3:

[0180] The server analyzes user feedback using sentiment analysis tools. The input is user feedback in text format. Using the Natural Language Toolkit, sentiment data is extracted from the feedback text, and specific sentiment tags are assigned to classify the emotional state. The output is feedback data with sentiment tags.

[0181] Step 4:

[0182] The server selects an analysis model using a model selection mechanism based on preprocessed data. The input consists of a high-quality dataset and data tagged with sentiment. Using the scikit-learn library, it selects an appropriate model such as linear regression or clustering and performs data analysis. The analysis results are generated as output.

[0183] Step 5:

[0184] The server uses result generation tools to visualize analysis results and adjust them to the user's emotions. Analysis results are used as input, and the results are presented as visual graphs and charts. The content is adjusted to reflect the user's emotions and documented in natural language. The output consists of adjusted visual information and natural language advice.

[0185] Step 6:

[0186] The terminal receives advice generated by the server and notifies the user through a user interface. Input consists of natural language advice and visual information. The terminal displays the advice to the user via a smartphone or PC and provides instructions on how to proceed based on the results. Output is a user-accessible display of the advice.

[0187] Step 7:

[0188] The user receives advice through a device and considers its feasibility. The input is the advice information from the device. The user then considers improvement measures based on the advice received. The expected output is an action plan based on the advice.

[0189] Step 8:

[0190] Users provide feedback to the system via their devices. Input includes their experiences and opinions after receiving advice. The feedback is then analyzed again using sentiment analysis tools. The output, with newly assigned sentiment tags, is stored on the server.

[0191] Step 9:

[0192] The server uses feedback to improve the model. The input is feedback data tagged with sentiment. Based on the insights gained from the feedback, the parameters of the proposed model are adjusted, making the next advice more personalized. The output is the improved model settings.

[0193] (Application Example 2)

[0194] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0195] Traditional business consulting systems provide management improvement advice based on data analysis, but they have difficulty providing advice that takes into account the user's emotions. As a result, advice that is not sufficiently empathetic to the user is not provided, and effective management improvements are sometimes not implemented. Furthermore, in individual user experiences such as electronic payments, emotional feedback is not taken into consideration, leading to problems with decreased user satisfaction.

[0196] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0197] In this invention, the server includes data acquisition means, information processing means, and method selection means. This makes it possible to take user emotions into consideration and provide improvement suggestions that are optimal for the individual experience.

[0198] "Data acquisition means" refers to functions that collect information related to user behavior and transactions.

[0199] "Information processing means" refers to a function that integrates acquired information, performs preprocessing to improve data quality, and converts it into a format suitable for analysis.

[0200] The "method selection means" is a function that selects and applies the optimal analysis method based on pre-processed information.

[0201] A "result generation method" is a function that generates analysis results and visualizes them in a format that is easy for the user to understand.

[0202] An "emotional assessment tool" is a function that identifies and analyzes a user's emotional state.

[0203] The "proposal creation method" is a function that creates improvement suggestions tailored to user needs based on analysis results and sentiment evaluations.

[0204] A "dialogue mechanism" is a function that provides an interface for presenting suggestions to the user and collecting user responses and feedback.

[0205] A "response processing means" is a function that improves the analysis method based on responses and feedback from users.

[0206] This invention is a system that functions as a business consultant system and electronic payment advisor that takes user emotions into consideration, and is configured based on the roles of server, terminal, and user.

[0207] The server collects user transaction history and feedback data using data acquisition means. This information is integrated and preprocessed by information processing means. For example, using NLTK (Natural Language Toolkit) or other text processing libraries, sentiment evaluation means analyzes the user's emotions. Based on the analyzed emotions, method selection means selects the optimal analysis method and performs the analysis.

[0208] The analysis results are visualized by the results generation system, and the proposal creation system generates improvement suggestions based on these results. These suggestions are sent to the terminal via the dialogue system, allowing the user to review them directly.

[0209] Users accept suggestions and provide feedback using their devices. This feedback is then sent back to the server, and the response processing system uses the feedback to improve its analysis methods and algorithms. Through this process, the system can continuously provide optimal advice tailored to the user's needs.

[0210] As a concrete example, suppose a user is struggling with budget management. The server uses the user's emotional data to generate stress-reducing advice, which is then displayed on the device. By using prompts such as, "Generate emotionally reassuring payment advice based on recent purchase history and feedback," the AI ​​can generate more specific and personalized suggestions.

[0211] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0212] Step 1:

[0213] The server collects user transaction history and feedback data using data acquisition methods. In this process, transaction information and past feedback provided by the user are used as input, and the data is collected from necessary databases and output as organized information. Specifically, information is obtained through API calls and database queries.

[0214] Step 2:

[0215] The server integrates and preprocesses the collected data using information processing tools. In this step, the acquired raw data is taken as input, and after imputing missing values ​​and cleaning the data, it is output as data in an analyzable format. Data preprocessing includes, for example, using the Python Pandas library to imputate missing values ​​and remove outliers.

[0216] Step 3:

[0217] The server uses sentiment evaluation tools to analyze the user's emotions from pre-processed data. In this step, text data is used as input, and the result of the sentiment analysis is output as sentiment information such as positive, negative, or neutral. Specifically, the Natural Language Toolkit (NLTK) is used to score the sentiment of the text.

[0218] Step 4:

[0219] The server uses a method selection mechanism to choose the optimal analysis method based on the analyzed sentiment data and performs data analysis. Here, sentiment data and preprocessed data are input, and analysis results suitable for the business situation are output. Specifically, a machine learning model is selected and applied to the data to generate prediction and classification results.

[0220] Step 5:

[0221] The server uses a result generation mechanism to visualize the analysis results and convert them into advice in natural language. In this step, the analysis results are input, and the output is in the form of graphs, charts, and natural language advice. Specifically, the Matplotlib library is used to generate graphs, and a generative AI model is used to create natural language explanations.

[0222] Step 6:

[0223] The server sends the advice generated through the interaction to the terminal, and the user receives and confirms the advice. In this step, the generated advice becomes input and is displayed on the terminal in a user-friendly format. Specifically, data transmission is performed using HTTP communication.

[0224] Step 7:

[0225] Users receive advice using their devices and send their thoughts and feedback to the server. In this process, user feedback information is input and output as feedback data that is reflected in the system. Specifically, users fill out and submit a feedback form on their devices.

[0226] Step 8:

[0227] The server uses response processing to improve analysis methods and algorithms based on collected feedback. In this step, user feedback data is used as input, and optimized models and methods are output. Specifically, the feedback data is used to adjust model parameters and update algorithms.

[0228] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0229] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0230] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0231] [Second Embodiment]

[0232] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0233] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0234] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0235] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0236] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0237] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0238] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0239] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0240] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0241] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0242] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0243] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0244] The AI ​​business consultant system according to the present invention is designed to support corporate decision-making by automating the entire process from the collection and analysis of relevant data to the provision of results. The entire system operates between a server, a terminal, and a user.

[0245] The server first periodically accesses the company's data sources to collect necessary information. It retrieves data from various sources, such as ERP systems, CRM systems, and external market databases, and manages it centrally.

[0246] Next, the server uses data processing tools to integrate and preprocess the collected data. Since the collected data may contain missing or outlier values, the accuracy of the analysis is improved by appropriately imputing or correcting these.

[0247] Based on the processed data, the server uses a model selection mechanism to choose the optimal analysis model and applies that model. In this process, the server utilizes machine learning and statistical analysis algorithms to select the most suitable model according to the characteristics of the data.

[0248] Once the analysis is complete, the server visually represents the results through a results generation mechanism. These results are presented not only as numerical data but also in a graphical format, supporting corporate decision-making.

[0249] The terminal provides the user with the generated analysis results and advice. The advice generation mechanism presents these results to the user in an easy-to-understand report format using natural language processing technology.

[0250] At that time, the user reviews the advice provided via the terminal and provides feedback. This feedback includes the effectiveness of the suggested advice and the results of its application. Based on this, the server re-evaluates the model using the feedback processing mechanism and makes improvements.

[0251] For example, if a small or medium-sized enterprise is considering launching a new product, this system analyzes market data and historical sales data to suggest the optimal launch timing and target market. It can also evaluate the effectiveness of the suggestions after implementation, contributing to the development of future strategies.

[0252] Thus, the present invention provides data-driven analysis and advice, thereby helping to move away from conventional subjective decision-making and support the formulation of sophisticated business strategies.

[0253] The following describes the processing flow.

[0254] Step 1:

[0255] The server accesses various data sources within the company and periodically collects the necessary data using APIs and data import tools. This ensures that the system incorporates the latest information.

[0256] Step 2:

[0257] The server integrates the collected data using data processing tools and performs data cleansing. Missing values ​​are imputed based on past trends and averages, and outliers are identified and corrected. These processes are performed automatically to ensure data quality.

[0258] Step 3:

[0259] Based on the preprocessed data, the server uses a model selection mechanism to choose the optimal analysis model. For example, a time series forecasting model or a clustering algorithm may be selected, and the most suitable application is made according to the data characteristics.

[0260] Step 4:

[0261] The server applies the selected model to analyze the data. The analysis results are output as numerical data, which are then visualized in graph or dashboard format by a results generation tool.

[0262] Step 5:

[0263] Based on the analysis results, the server uses an advice generation system to create specific business improvement advice. This advice is documented using natural language processing technology and compiled into a report.

[0264] Step 6:

[0265] The terminal notifies the user of the generated report and displays the details through a dedicated interface. Based on this, the user makes decisions and develops actionable strategies.

[0266] Step 7:

[0267] The user provides feedback to the server via their terminal, showing the results after implementing the suggested advice. This feedback includes information about the effectiveness of the advice and the results of its application.

[0268] Step 8:

[0269] The server collects user feedback and uses feedback processing to evaluate the model. It adjusts the analysis model as needed to improve the accuracy of subsequent analyses.

[0270] (Example 1)

[0271] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0272] Businesses and organizations require vast amounts of diverse data to make informed business decisions. However, efficiently collecting this data, analyzing it consistently, and providing appropriate advice is challenging. Furthermore, data preprocessing to improve quality and adapting models to dynamic market environments are necessary, but performing these manually is time-consuming and costly. This invention aims to solve these problems and provide an automated, data-driven decision support system.

[0273] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0274] In this invention, the server includes means for accessing information sources and collecting relevant information, data processing means for integrating and preprocessing the collected information, including imputing missing values ​​and correcting outliers, and model selection means for selecting and applying the optimal analysis model based on the preprocessed information. This makes it possible to efficiently process diverse data and quickly provide accurate analysis results.

[0275] "Information source" refers to an external or internal data provider from which a system collects data, and the source from which information is provided.

[0276] "Data processing means" refers to the process of preparing collected data for analysis, and includes means that perform functions such as imputing missing values ​​and correcting outliers.

[0277] A "model selection means" is a function that selects and applies the optimal analysis model based on pre-processed information.

[0278] The "result generation means" is a function that generates analysis results in numerical and graphical formats and presents them in a visually easy-to-understand manner.

[0279] A "guideline creation tool" is a function that generates and provides policies for business improvement based on analysis results.

[0280] "Means of communication" refers to means of providing guidance to users and receiving their feedback.

[0281] A "feedback processing mechanism" is a function for re-evaluating and improving the analysis model based on the collected feedback.

[0282] A "generative AI model" is a component of artificial intelligence that generates appropriate output from given input data, enabling analysis and prompt generation for decision support.

[0283] A "prompt sentence" is a sentence that serves as an instruction or query for a generative AI model and is provided as a guideline for the model to perform specific tasks.

[0284] Mode for Carrying Out the Invention

[0285] The AI business consultant system of the present invention supports business decision-making by automating the collection, processing, analysis of relevant information, and provision of feedback to users. The main components in this system are realized by the interaction of servers, terminals, and users.

[0286] Data Collection and Processing

[0287] The server regularly accesses the information sources of enterprises and automatically collects information from ERP systems, CRM, external market databases, etc. This information may be obtained through various APIs or aggregated in one place by being downloaded in file format. The server then integrates this collected information using data processing means and performs preprocessing including the complementation of missing values and the correction of outliers. Specific data processing software such as the Pandas and NumPy libraries on Python is utilized.

[0288] Model Selection and Result Generation

[0289] The server selects the most appropriate analysis model using the preprocessed information. Here, machine learning libraries such as TensorFlow and Scikit-learn are utilized to perform the modeling required for sales forecasting, market analysis, etc. The modeled results are visualized using Matplotlib and Tableau and generated in the form of graphs and dashboards.

[0290] Provision of Advice and Feedback

[0291] The terminal receives analysis results generated from the server and uses natural language processing technology to create reports that are easy for the user to understand. This allows the user to receive detailed guidance on future market trend forecasts and product launch strategies. For example, based on the scenario "What is the optimal marketing strategy for the next quarter?", the system inputs the prompt "Predict market trends for the next quarter and indicate which product categories should be focused on" into the AI ​​model and proposes the optimal strategy.

[0292] Feedback and model improvement

[0293] Users make decisions based on guidelines received via their devices and provide feedback on the results. This feedback information is analyzed by the server and used for re-evaluation during model selection and data processing. This allows the system to continuously learn and improve, enabling it to continue providing highly accurate consulting tailored to user needs.

[0294] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0295] Step 1:

[0296] The server accesses sources such as ERP systems, CRMs, and external market databases to collect data. Inputs are provided in the form of APIs or data files. In this process, the server retrieves relevant information periodically as a scheduled task and integrates it into a centralized dataset. Output is the collected raw data, which is stored in a database.

[0297] Step 2:

[0298] The server preprocesses the collected data using data processing tools. The input is the raw data collected in step 1. Specifically, it uses the Python library Pandas to computationally impute missing values ​​and detect and remove outliers. This data processing results in a clean and consistent dataset.

[0299] Step 3:

[0300] The server selects and applies the optimal analysis model based on pre-processed data as input. It uses a machine learning library (e.g., Scikit-learn) to select a model based on data trends. In this case, models for sales forecasting and market trend analysis are selected and applied. The output consists of predicted data and trend visualizations as analysis results.

[0301] Step 4:

[0302] The server visualizes the analysis results and expresses them as numerical data and diagrams. The input is the analysis results generated in step 3. Specific operations include generating graphs using Matplotlib and creating dashboards using Tableau. The output is a report in a format that facilitates visual understanding.

[0303] Step 5:

[0304] The terminal uses the visualized results received from the server to generate a report using natural language processing technology. The input is the visualized data from step 4. Specifically, it uses a natural language generation library to output text that is easy for the AI ​​model to understand. The output is a guideline report to support user decision-making.

[0305] Step 6:

[0306] The user receives the pointers provided by the terminal and makes decisions based on them. The input is the report in step 5. As a specific operation, the user inputs feedback to the terminal and evaluates the effects and the effectiveness of the proposals. The output is sent back to the system as feedback information and is used by the server to improve the model and advice generation process.

[0307] (Application Example 1)

[0308] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0309] In the handling plan of items in the logistics center, inventory management and optimization of the shipping schedule are important. However, with conventional methods, it is difficult to effectively analyze a large amount of data, and there is a possibility of inefficient planning and incorrect judgments. There is a need for a system to solve such problems and improve the operational efficiency of the logistics center.

[0310] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0311] In this invention, the server includes data collection means, data processing means for integrating the collected data and performing preprocessing, model selection means for selecting and applying an analysis model based on the preprocessed data, plan optimization means for assisting in the handling plan of items in the warehouse, and anomaly detection means for detecting anomalies using the information and sending warnings. Thereby, it becomes possible to optimize the business plan in the logistics center and respond quickly to anomalies.

[0312] The "data collection means" is a function of regularly acquiring necessary information from information sources inside and outside the company and storing it in a database.

[0313] The "data processing means" is a function of integrating the collected information, performing missing value supplementation and outlier correction, and shaping it into an analyzable state.

[0314] A "model selection means" is a function that includes an algorithm for selecting and applying the optimal analysis model based on preprocessed information.

[0315] A "result generation means" is a function for visually representing the results of the analysis as text or graphs.

[0316] A "proposal generation tool" is a function that generates proposals for business improvement based on analysis results.

[0317] An "interface means" is a function that provides suggestions to users and collects feedback from them.

[0318] A "response processing means" is a function that improves the analysis model based on feedback from the user.

[0319] "Planning optimization means" refers to functions that support the improvement of efficiency in goods management and shipping planning at logistics facilities.

[0320] An "anomaly detection method" is a function that identifies anomalies based on analysis results and real-time data, and issues warnings in a timely manner.

[0321] The server periodically collects necessary information from internal and external sources, such as ERP systems and market databases, using data aggregation tools. This information is stored in a database and used for subsequent processing. The collected information is integrated by data processing tools, and missing values ​​are imputed and outliers are corrected. This creates a dataset suitable for analysis.

[0322] Next, the server analyzes this preprocessed data by using a model selection mechanism to determine and apply the optimal analysis model. By utilizing machine learning algorithms and statistical analysis, advanced analysis tailored to the data characteristics is achieved. The analysis results are visualized as graphs and charts by a results generation mechanism. This provides information in a way that users can intuitively understand.

[0323] Furthermore, the server uses a proposal generation mechanism to generate business improvement proposals based on the analysis results. These proposals are expressed in an easy-to-understand format using natural language processing technology and provided to the user via a terminal. The user reviews the proposals via the terminal and provides a response, which the response processing mechanism then uses to improve the model.

[0324] As a concrete example, in inventory management at a logistics center, this system combines real-time inventory data with market demand forecast data to propose optimal replenishment plans and shipping strategies. Furthermore, if the anomaly detection mechanism detects an anomaly, it immediately sends a warning to the user, prompting quick action. An example of a prompt for the generated AI model is: "Select an analytical model for inventory optimization based on the following two data sets, and report the results in natural language. Inventory data: {inventory_data} Market demand data: {demand_data}".

[0325] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0326] Step 1:

[0327] The server uses data aggregation tools to periodically collect necessary data from sources such as ERP systems and market databases. In this step, the inputs include company inventory data and market demand data, and the output is the collected raw data stored in the database. The data collection process is periodically triggered by automated scripts to maintain data integrity.

[0328] Step 2:

[0329] The server uses data processing tools to integrate the collected raw data, imputing missing values ​​and correcting outliers. In this step, the raw data collected in step 1 is taken as input, and formatted data suitable for analysis is generated as output. Specifically, the data is cleansed to extract only the information necessary for analysis.

[0330] Step 3:

[0331] The server uses a model selection mechanism to select and apply the optimal analysis model based on the pre-processed data. In this step, the input is pre-processed data, and the output is the analysis results generated by the model. Machine learning algorithms are applied to perform predictions and clustering according to the data characteristics.

[0332] Step 4:

[0333] The server uses a results generation mechanism to visualize the analysis results in graphs and charts. In this step, the analysis results from step 3 are taken as input, and a visualized report is generated as output. The visualization tool organizes the information in an intuitively easy-to-understand format.

[0334] Step 5:

[0335] The server uses a proposal generation tool to generate proposals for business improvement based on visualized analysis results. In this step, visualized information is taken as input, and a proposal document expressed in natural language is generated as output. Natural language processing technology is used to convert complex data into concise sentences.

[0336] Step 6:

[0337] The terminal uses an interface to provide suggestions to the user. It then receives responses from the user. In this step, the input is a proposal document, and the output is the collection of user feedback. The user reviews the proposal on the terminal screen and inputs their own opinions and suggestions for improvement.

[0338] Step 7:

[0339] The server uses a response processing mechanism to improve the analysis model based on user feedback. In this step, user feedback is the input, and the improved analysis model is the output. The feedback information is used to adjust model parameters and train new data.

[0340] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0341] This invention incorporates an emotion engine into an AI business consultant system, making it possible to provide business improvement advice that takes into account the user's emotional state. This system employs a more human-centered approach based on the interaction between the server, terminal, and user.

[0342] The server first automatically collects various types of corporate data and performs preprocessing of the integrated data. In addition to conventional data processing functions, it utilizes an emotion engine to analyze user emotion data collected during feedback. After data processing, the server selects an appropriate analysis model, analyzes the data, and generates results.

[0343] The generated analysis results are not simply presented as numerical data or graphical visual information, but are also adjusted to align with the user's emotions as analyzed by the emotion engine. This allows the server to create advice that takes the user's emotional state into account through an advice generation mechanism, and then compile it into a report format in natural language.

[0344] The terminal notifies the user of the generated report and allows the user to review the advice through the interface. The user receives the advice via the terminal, reviews its contents, and then considers its feasibility.

[0345] Furthermore, when users provide feedback on the effects after implementation, the emotion engine recognizes and classifies emotions from the user's text data. This feedback process allows the server to improve the model and adjust it so that future suggestions are more relatable and provide more effective advice to the user.

[0346] For example, in the case of a company considering new business development, this system utilizes historical market data and user feedback to not only analyze points of differentiation from competitors and market needs in detail, but also provides an approach that emphasizes risk mitigation measures if the user is feeling anxious. As a result, it can realize a next-generation consulting service that is more user-centric than traditional business advice.

[0347] The following describes the processing flow.

[0348] Step 1:

[0349] The server accesses various data sources within the company and automatically collects the necessary data via APIs. Furthermore, it also incorporates data related to user sentiment during feedback.

[0350] Step 2:

[0351] The server integrates the collected data and performs preprocessing using data processing tools. Missing values ​​are imputed using mean values ​​or modes, and outliers are detected and corrected using a rule-based approach.

[0352] Step 3:

[0353] The server activates the emotion engine and analyzes the user's emotions from the collected feedback data. It then classifies these emotions into categories (e.g., positive, negative, neutral) using natural language processing.

[0354] Step 4:

[0355] The server selects the optimal analysis model based on the data and analyzed sentiment information. For example, it uses the ARIMA model for sales forecasting and a clustering algorithm for user interest analysis.

[0356] Step 5:

[0357] The server applies the selected analytical model and performs data analysis. The generated analysis results are visualized in the form of graphs and dashboards.

[0358] Step 6:

[0359] The server interprets the analysis results based on the user's emotions obtained from the emotion engine and generates advice. If the user expresses anxiety, the advice will emphasize risk avoidance measures.

[0360] Step 7:

[0361] The terminal notifies the user of the generated advice and displays a report. The user reviews the details of the advice through the interface.

[0362] Step 8:

[0363] Users follow the advice and provide feedback on the results. This feedback, including emotional input, is sent to the server via the device.

[0364] Step 9:

[0365] The server receives feedback data and uses feedback processing mechanisms to improve the model. User sentiment is reconsidered, and adjustments are made to reflect it in future advice.

[0366] (Example 2)

[0367] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0368] Traditional business consulting systems provide advice based on data analysis, but they have difficulty considering the user's emotional state. This has resulted in a lack of optimal advice tailored to the user's emotions, leading to problems with its feasibility and acceptability.

[0369] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0370] In this invention, the server includes data collection means, data processing means for integrating and pre-processing the collected data, and sentiment analysis means for analyzing the pre-processed data together with sentiment data. This makes it possible to provide business improvement advice that takes into account the user's emotional state, thereby improving feasibility and acceptability.

[0371] "Data collection means" refers to functions for automatically collecting various types of information related to a company, and it is possible to obtain necessary data from database connections and online information sources.

[0372] "Data processing means" refers to a process that integrates collected raw data, performs functions such as imputing missing values ​​and correcting outliers, and extracts sentiment data.

[0373] "Emotional analysis means" refers to a processing function that analyzes emotional states from user feedback and text data and assigns specific emotional tags to them.

[0374] "Model selection means" refers to a function that selects the optimal analytical model according to the analyzed data and applies it to the data to extract business insights.

[0375] "Result generation means" refers to a function that visualizes the results of data analysis as numbers and graphs, and further adjusts the expression of advice according to the user's emotional state.

[0376] "Advice generation method" refers to a function that uses a generative AI model and prompt text to document management improvement advice for users in natural language based on the analysis results obtained.

[0377] "Interface means" refers to an interactive platform that provides generated advice to the user and effectively collects feedback from the user.

[0378] "Feedback processing means" refers to a function that analyzes feedback collected from users, performs sentiment analysis, and improves the suggestion model based on the results to enhance the quality of advice for future use.

[0379] The embodiment of this invention is a system that is made possible by the collaboration of a server, a terminal, and a user.

[0380] The server uses a database connection to automatically collect various types of company information. This allows for the acquisition of diverse data such as sales data, customer feedback, and market research results. Data processing involves manipulating dataframes using the Python Pandas library, including imputing missing values ​​and correcting outliers. Furthermore, text analysis libraries such as Natural Language Toolkit are used to extract sentiment data from user feedback. The sentiment analysis system analyzes the user's emotional state based on this data and assigns sentiment tags. The analyzed data is then analyzed using machine learning models such as scikit-learn. The result generation system visualizes the data analysis results and adjusts them to take user emotions into consideration. Using a generative AI model, prompt sentences are used, and advice is documented using natural language processing techniques. This process ensures that the generated advice is easy for users to understand and leads to actual action.

[0381] The terminal notifies the user of advice generated by the server and provides a platform for the user to review the advice through an interface. Since this utilizes applications on smartphones and PCs, users can receive advice regardless of their location.

[0382] Users review the advice provided through their device and consider its feasibility. They then return feedback to the system, including the results of implementing the advice and their opinions. This feedback is then analyzed again by sentiment analysis tools and assigned sentiment tags. Using these results, the server can improve its next suggestion model and provide more personalized advice.

[0383] As a concrete example, a company considering a new business venture would utilize past market data and user feedback to analyze in detail its points of differentiation from competitors and market needs. In this case, an example of a prompt given to the AI ​​model would be: "For companies considering a new business venture, please analyze specific points of differentiation and market needs based on past market data and feedback, and propose measures to alleviate user concerns." This allows users to receive emotionally resonant and more actionable advice.

[0384] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0385] Step 1:

[0386] The server collects data related to the company. Input for data collection includes data from databases and external APIs. It uses SQL queries and API requests to retrieve sales data and customer feedback, and stores them in local storage. The output is an integrated dataset.

[0387] Step 2:

[0388] The server preprocesses the collected data. The input for this step is the integrated dataset obtained in step 1. Specifically, it uses the Python Pandas library to impute missing values ​​and correct outliers. The output is an improved dataset.

[0389] Step 3:

[0390] The server analyzes user feedback using sentiment analysis tools. The input is user feedback in text format. Using the Natural Language Toolkit, sentiment data is extracted from the feedback text, and specific sentiment tags are assigned to classify the emotional state. The output is feedback data with sentiment tags.

[0391] Step 4:

[0392] The server selects an analysis model using a model selection mechanism based on preprocessed data. The input consists of a high-quality dataset and data tagged with sentiment. Using the scikit-learn library, it selects an appropriate model such as linear regression or clustering and performs data analysis. The analysis results are generated as output.

[0393] Step 5:

[0394] The server uses result generation tools to visualize analysis results and adjust them to the user's emotions. Analysis results are used as input, and the results are presented as visual graphs and charts. The content is adjusted to reflect the user's emotions and documented in natural language. The output consists of adjusted visual information and natural language advice.

[0395] Step 6:

[0396] The terminal receives advice generated by the server and notifies the user through a user interface. Input consists of natural language advice and visual information. The terminal displays the advice to the user via a smartphone or PC and provides instructions on how to proceed based on the results. Output is a user-accessible display of the advice.

[0397] Step 7:

[0398] The user receives advice through a device and considers its feasibility. The input is the advice information from the device. The user then considers improvement measures based on the advice received. The expected output is an action plan based on the advice.

[0399] Step 8:

[0400] Users provide feedback to the system via their devices. Input includes their experiences and opinions after receiving advice. The feedback is then analyzed again using sentiment analysis tools. The output, with newly assigned sentiment tags, is stored on the server.

[0401] Step 9:

[0402] The server uses feedback to improve the model. The input is feedback data tagged with sentiment. Based on the insights gained from the feedback, the parameters of the proposed model are adjusted, making the next advice more personalized. The output is the improved model settings.

[0403] (Application Example 2)

[0404] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0405] Traditional business consulting systems provide management improvement advice based on data analysis, but they have difficulty providing advice that takes into account the user's emotions. As a result, advice that is not sufficiently empathetic to the user is not provided, and effective management improvements are sometimes not implemented. Furthermore, in individual user experiences such as electronic payments, emotional feedback is not taken into consideration, leading to problems with decreased user satisfaction.

[0406] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0407] In this invention, the server includes data acquisition means, information processing means, and method selection means. This makes it possible to take user emotions into consideration and provide improvement suggestions that are optimal for the individual experience.

[0408] "Data acquisition means" refers to functions that collect information related to user behavior and transactions.

[0409] "Information processing means" refers to a function that integrates acquired information, performs preprocessing to improve data quality, and converts it into a format suitable for analysis.

[0410] The "method selection means" is a function that selects and applies the optimal analysis method based on pre-processed information.

[0411] A "result generation method" is a function that generates analysis results and visualizes them in a format that is easy for the user to understand.

[0412] An "emotional assessment tool" is a function that identifies and analyzes a user's emotional state.

[0413] The "proposal creation method" is a function that creates improvement suggestions tailored to user needs based on analysis results and sentiment evaluations.

[0414] A "dialogue mechanism" is a function that provides an interface for presenting suggestions to the user and collecting user responses and feedback.

[0415] A "response processing means" is a function that improves the analysis method based on responses and feedback from users.

[0416] This invention is a system that functions as a business consultant system and electronic payment advisor that takes user emotions into consideration, and is configured based on the roles of server, terminal, and user.

[0417] The server collects user transaction history and feedback data using data acquisition means. This information is integrated and preprocessed by information processing means. For example, using NLTK (Natural Language Toolkit) or other text processing libraries, sentiment evaluation means analyzes the user's emotions. Based on the analyzed emotions, method selection means selects the optimal analysis method and performs the analysis.

[0418] The analysis results are visualized by the results generation system, and the proposal creation system generates improvement suggestions based on these results. These suggestions are sent to the terminal via the dialogue system, allowing the user to review them directly.

[0419] Users accept suggestions and provide feedback using their devices. This feedback is then sent back to the server, and the response processing system uses the feedback to improve its analysis methods and algorithms. Through this process, the system can continuously provide optimal advice tailored to the user's needs.

[0420] As a concrete example, suppose a user is struggling with budget management. The server uses the user's emotional data to generate stress-reducing advice, which is then displayed on the device. By using prompts such as, "Generate emotionally reassuring payment advice based on recent purchase history and feedback," the AI ​​can generate more specific and personalized suggestions.

[0421] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0422] Step 1:

[0423] The server collects user transaction history and feedback data using data acquisition methods. In this process, transaction information and past feedback provided by the user are used as input, and the data is collected from necessary databases and output as organized information. Specifically, information is obtained through API calls and database queries.

[0424] Step 2:

[0425] The server integrates and preprocesses the collected data using information processing tools. In this step, the acquired raw data is taken as input, and after imputing missing values ​​and cleaning the data, it is output as data in an analyzable format. Data preprocessing includes, for example, using the Python Pandas library to imputate missing values ​​and remove outliers.

[0426] Step 3:

[0427] The server uses sentiment evaluation tools to analyze the user's emotions from pre-processed data. In this step, text data is used as input, and the result of the sentiment analysis is output as sentiment information such as positive, negative, or neutral. Specifically, the Natural Language Toolkit (NLTK) is used to score the sentiment of the text.

[0428] Step 4:

[0429] The server uses a method selection mechanism to choose the optimal analysis method based on the analyzed sentiment data and performs data analysis. Here, sentiment data and preprocessed data are input, and analysis results suitable for the business situation are output. Specifically, a machine learning model is selected and applied to the data to generate prediction and classification results.

[0430] Step 5:

[0431] The server uses a result generation mechanism to visualize the analysis results and convert them into advice in natural language. In this step, the analysis results are input, and the output is in the form of graphs, charts, and natural language advice. Specifically, the Matplotlib library is used to generate graphs, and a generative AI model is used to create natural language explanations.

[0432] Step 6:

[0433] The server sends the advice generated through the interaction to the terminal, and the user receives and confirms the advice. In this step, the generated advice becomes input and is displayed on the terminal in a user-friendly format. Specifically, data transmission is performed using HTTP communication.

[0434] Step 7:

[0435] Users receive advice using their devices and send their thoughts and feedback to the server. In this process, user feedback information is input and output as feedback data that is reflected in the system. Specifically, users fill out and submit a feedback form on their devices.

[0436] Step 8:

[0437] The server uses response processing to improve analysis methods and algorithms based on collected feedback. In this step, user feedback data is used as input, and optimized models and methods are output. Specifically, the feedback data is used to adjust model parameters and update algorithms.

[0438] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0439] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0440] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0441] [Third Embodiment]

[0442] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0443] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0444] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0445] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0446] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0447] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0448] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0449] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0450] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0451] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0452] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0453] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0454] The AI ​​business consultant system according to the present invention is designed to support corporate decision-making by automating the entire process from the collection and analysis of relevant data to the provision of results. The entire system operates between a server, a terminal, and a user.

[0455] The server first periodically accesses the company's data sources to collect necessary information. It retrieves data from various sources, such as ERP systems, CRM systems, and external market databases, and manages it centrally.

[0456] Next, the server uses data processing tools to integrate and preprocess the collected data. Since the collected data may contain missing or outlier values, the accuracy of the analysis is improved by appropriately imputing or correcting these.

[0457] Based on the processed data, the server uses a model selection mechanism to choose the optimal analysis model and applies that model. In this process, the server utilizes machine learning and statistical analysis algorithms to select the most suitable model according to the characteristics of the data.

[0458] Once the analysis is complete, the server visually represents the results through a results generation mechanism. These results are presented not only as numerical data but also in a graphical format, supporting corporate decision-making.

[0459] The terminal provides the user with the generated analysis results and advice. The advice generation mechanism presents these results to the user in an easy-to-understand report format using natural language processing technology.

[0460] At that time, the user reviews the advice provided via the terminal and provides feedback. This feedback includes the effectiveness of the suggested advice and the results of its application. Based on this, the server re-evaluates the model using the feedback processing mechanism and makes improvements.

[0461] For example, if a small or medium-sized enterprise is considering launching a new product, this system analyzes market data and historical sales data to suggest the optimal launch timing and target market. It can also evaluate the effectiveness of the suggestions after implementation, contributing to the development of future strategies.

[0462] Thus, the present invention provides data-driven analysis and advice, thereby helping to move away from conventional subjective decision-making and support the formulation of sophisticated business strategies.

[0463] The following describes the processing flow.

[0464] Step 1:

[0465] The server accesses various data sources within the company and periodically collects the necessary data using APIs and data import tools. This ensures that the system incorporates the latest information.

[0466] Step 2:

[0467] The server integrates the collected data using data processing tools and performs data cleansing. Missing values ​​are imputed based on past trends and averages, and outliers are identified and corrected. These processes are performed automatically to ensure data quality.

[0468] Step 3:

[0469] Based on the preprocessed data, the server uses a model selection mechanism to choose the optimal analysis model. For example, a time series forecasting model or a clustering algorithm may be selected, and the most suitable application is made according to the data characteristics.

[0470] Step 4:

[0471] The server applies the selected model to analyze the data. The analysis results are output as numerical data, which are then visualized in graph or dashboard format by a results generation tool.

[0472] Step 5:

[0473] Based on the analysis results, the server uses an advice generation system to create specific business improvement advice. This advice is documented using natural language processing technology and compiled into a report.

[0474] Step 6:

[0475] The terminal notifies the user of the generated report and displays the details through a dedicated interface. Based on this, the user makes decisions and develops actionable strategies.

[0476] Step 7:

[0477] The user provides feedback to the server via their terminal, showing the results after implementing the suggested advice. This feedback includes information about the effectiveness of the advice and the results of its application.

[0478] Step 8:

[0479] The server collects user feedback and uses feedback processing to evaluate the model. It adjusts the analysis model as needed to improve the accuracy of subsequent analyses.

[0480] (Example 1)

[0481] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0482] Businesses and organizations require vast amounts of diverse data to make informed business decisions. However, efficiently collecting this data, analyzing it consistently, and providing appropriate advice is challenging. Furthermore, data preprocessing to improve quality and adapting models to dynamic market environments are necessary, but performing these manually is time-consuming and costly. This invention aims to solve these problems and provide an automated, data-driven decision support system.

[0483] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0484] In this invention, the server includes means for accessing information sources and collecting relevant information, data processing means for integrating and preprocessing the collected information, including imputing missing values ​​and correcting outliers, and model selection means for selecting and applying the optimal analysis model based on the preprocessed information. This makes it possible to efficiently process diverse data and quickly provide accurate analysis results.

[0485] "Information source" refers to an external or internal data provider from which a system collects data, and the source from which information is provided.

[0486] "Data processing means" refers to the process of preparing collected data for analysis, and includes means that perform functions such as imputing missing values ​​and correcting outliers.

[0487] A "model selection means" is a function that selects and applies the optimal analysis model based on pre-processed information.

[0488] The "result generation means" is a function that generates analysis results in numerical and graphical formats and presents them in a visually easy-to-understand manner.

[0489] A "guideline creation tool" is a function that generates and provides policies for business improvement based on analysis results.

[0490] "Means of communication" refers to means of providing guidance to users and receiving their feedback.

[0491] A "feedback processing mechanism" is a function for re-evaluating and improving the analysis model based on the collected feedback.

[0492] A "generative AI model" is a component of artificial intelligence that generates appropriate output from given input data, enabling analysis and prompt generation for decision support.

[0493] A "prompt" is a sentence that serves as an instruction or question to a generative AI model, providing guidance for the model to perform a specific task.

[0494] Modes for carrying out the invention

[0495] The AI ​​business consultant system of the present invention supports management decision-making by automating the collection, processing, and analysis of relevant information and the provision of feedback to the user. The main components of this system are realized through the interaction of a server, a terminal, and the user.

[0496] Data collection and processing

[0497] The server periodically accesses corporate data sources and automatically collects information from ERP systems, CRMs, external market databases, and other sources. This information may be obtained through various APIs or downloaded in file format and aggregated in one location. The server then integrates this collected information using data processing tools and performs preprocessing, including imputing missing values ​​and correcting outliers. Specific data processing software used includes Python libraries such as Pandas and NumPy.

[0498] Model selection and result generation

[0499] The server uses pre-processed information to select the most appropriate analysis model. Here, machine learning libraries such as TensorFlow and Scikit-learn are utilized to perform modeling necessary for sales forecasting, market analysis, and other applications. The modeled results are visualized using Matplotlib and Tableau, and generated as graphs and dashboards.

[0500] Providing advice and feedback

[0501] The terminal receives analysis results generated from the server and uses natural language processing technology to create reports that are easy for the user to understand. This allows the user to receive detailed guidance on future market trend forecasts and product launch strategies. For example, based on the scenario "What is the optimal marketing strategy for the next quarter?", the system inputs the prompt "Predict market trends for the next quarter and indicate which product categories should be focused on" into the AI ​​model and proposes the optimal strategy.

[0502] Feedback and model improvement

[0503] Users make decisions based on guidelines received via their devices and provide feedback on the results. This feedback information is analyzed by the server and used for re-evaluation during model selection and data processing. This allows the system to continuously learn and improve, enabling it to continue providing highly accurate consulting tailored to user needs.

[0504] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0505] Step 1:

[0506] The server accesses sources such as ERP systems, CRMs, and external market databases to collect data. Inputs are provided in the form of APIs or data files. In this process, the server retrieves relevant information periodically as a scheduled task and integrates it into a centralized dataset. Output is the collected raw data, which is stored in a database.

[0507] Step 2:

[0508] The server preprocesses the collected data using data processing tools. The input is the raw data collected in step 1. Specifically, it uses the Python library Pandas to computationally impute missing values ​​and detect and remove outliers. This data processing results in a clean and consistent dataset.

[0509] Step 3:

[0510] The server selects and applies the optimal analysis model based on pre-processed data as input. It uses a machine learning library (e.g., Scikit-learn) to select a model based on data trends. In this case, models for sales forecasting and market trend analysis are selected and applied. The output consists of predicted data and trend visualizations as analysis results.

[0511] Step 4:

[0512] The server visualizes the analysis results and expresses them as numerical data and diagrams. The input is the analysis results generated in step 3. Specific operations include generating graphs using Matplotlib and creating dashboards using Tableau. The output is a report in a format that facilitates visual understanding.

[0513] Step 5:

[0514] The terminal uses the visualized results received from the server to generate a report using natural language processing technology. The input is the visualized data from step 4. Specifically, it uses a natural language generation library to output text that is easy for the AI ​​model to understand. The output is a guideline report to support user decision-making.

[0515] Step 6:

[0516] The user receives guidance from the terminal and makes decisions based on it. The input is the report from step 5. Specifically, the user inputs feedback into the terminal and evaluates its effectiveness and the validity of the suggestions. The output is sent back to the system as feedback information and used by the server to improve the model and advice generation process.

[0517] (Application Example 1)

[0518] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0519] Planning the handling of goods in a logistics center requires careful inventory management and optimization of shipping schedules. However, traditional methods make it difficult to effectively analyze large amounts of data, potentially leading to inefficient planning and incorrect decisions. A system is needed to solve these problems and improve the operational efficiency of logistics centers.

[0520] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0521] In this invention, the server includes data aggregation means, data processing means for integrating and pre-processing the collected data, model selection means for selecting and applying an analysis model based on the pre-processed data, planning optimization means for supporting the planning of goods handling in a warehouse, and anomaly detection means for detecting anomalies using the information and sending warnings. This enables optimization of operational plans and rapid response to anomalies in a logistics center.

[0522] A "data aggregation method" is a function that periodically acquires necessary information from internal and external sources within a company and stores it in a database.

[0523] "Data processing means" refers to a function that integrates collected information and formats it into an analyzable state by imputing missing values ​​and correcting outliers.

[0524] A "model selection means" is a function that includes an algorithm for selecting and applying the optimal analysis model based on preprocessed information.

[0525] A "result generation means" is a function for visually representing the results of the analysis as text or graphs.

[0526] A "proposal generation tool" is a function that generates proposals for business improvement based on analysis results.

[0527] An "interface means" is a function that provides suggestions to users and collects feedback from them.

[0528] A "response processing means" is a function that improves the analysis model based on feedback from the user.

[0529] "Planning optimization means" refers to functions that support the improvement of efficiency in goods management and shipping planning at logistics facilities.

[0530] An "anomaly detection method" is a function that identifies anomalies based on analysis results and real-time data, and issues warnings in a timely manner.

[0531] The server periodically collects necessary information from internal and external sources, such as ERP systems and market databases, using data aggregation tools. This information is stored in a database and used for subsequent processing. The collected information is integrated by data processing tools, and missing values ​​are imputed and outliers are corrected. This creates a dataset suitable for analysis.

[0532] Next, the server analyzes this preprocessed data by using a model selection mechanism to determine and apply the optimal analysis model. By utilizing machine learning algorithms and statistical analysis, advanced analysis tailored to the data characteristics is achieved. The analysis results are visualized as graphs and charts by a results generation mechanism. This provides information in a way that users can intuitively understand.

[0533] Furthermore, the server uses a proposal generation mechanism to generate business improvement proposals based on the analysis results. These proposals are expressed in an easy-to-understand format using natural language processing technology and provided to the user via a terminal. The user reviews the proposals via the terminal and provides a response, which the response processing mechanism then uses to improve the model.

[0534] As a concrete example, in inventory management at a logistics center, this system combines real-time inventory data with market demand forecast data to propose optimal replenishment plans and shipping strategies. Furthermore, if the anomaly detection mechanism detects an anomaly, it immediately sends a warning to the user, prompting quick action. An example of a prompt for the generated AI model is: "Select an analytical model for inventory optimization based on the following two data sets, and report the results in natural language. Inventory data: {inventory_data} Market demand data: {demand_data}".

[0535] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0536] Step 1:

[0537] The server uses data aggregation tools to periodically collect necessary data from sources such as ERP systems and market databases. In this step, the inputs include company inventory data and market demand data, and the output is the collected raw data stored in the database. The data collection process is periodically triggered by automated scripts to maintain data integrity.

[0538] Step 2:

[0539] The server uses data processing tools to integrate the collected raw data, imputing missing values ​​and correcting outliers. In this step, the raw data collected in step 1 is taken as input, and formatted data suitable for analysis is generated as output. Specifically, the data is cleansed to extract only the information necessary for analysis.

[0540] Step 3:

[0541] The server uses a model selection mechanism to select and apply the optimal analysis model based on the pre-processed data. In this step, the input is pre-processed data, and the output is the analysis results generated by the model. Machine learning algorithms are applied to perform predictions and clustering according to the data characteristics.

[0542] Step 4:

[0543] The server uses a results generation mechanism to visualize the analysis results in graphs and charts. In this step, the analysis results from step 3 are taken as input, and a visualized report is generated as output. The visualization tool organizes the information in an intuitively easy-to-understand format.

[0544] Step 5:

[0545] The server uses a proposal generation tool to generate proposals for business improvement based on visualized analysis results. In this step, visualized information is taken as input, and a proposal document expressed in natural language is generated as output. Natural language processing technology is used to convert complex data into concise sentences.

[0546] Step 6:

[0547] The terminal uses an interface to provide suggestions to the user. It then receives responses from the user. In this step, the input is a proposal document, and the output is the collection of user feedback. The user reviews the proposal on the terminal screen and inputs their own opinions and suggestions for improvement.

[0548] Step 7:

[0549] The server uses a response processing mechanism to improve the analysis model based on user feedback. In this step, user feedback is the input, and the improved analysis model is the output. The feedback information is used to adjust model parameters and train new data.

[0550] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0551] This invention incorporates an emotion engine into an AI business consultant system, making it possible to provide business improvement advice that takes into account the user's emotional state. This system employs a more human-centered approach based on the interaction between the server, terminal, and user.

[0552] The server first automatically collects various types of corporate data and performs preprocessing of the integrated data. In addition to conventional data processing functions, it utilizes an emotion engine to analyze user emotion data collected during feedback. After data processing, the server selects an appropriate analysis model, analyzes the data, and generates results.

[0553] The generated analysis results are not simply presented as numerical data or graphical visual information, but are also adjusted to align with the user's emotions as analyzed by the emotion engine. This allows the server to create advice that takes the user's emotional state into account through an advice generation mechanism, and then compile it into a report format in natural language.

[0554] The terminal notifies the user of the generated report and allows the user to review the advice through the interface. The user receives the advice via the terminal, reviews its contents, and then considers its feasibility.

[0555] Furthermore, when users provide feedback on the effects after implementation, the emotion engine recognizes and classifies emotions from the user's text data. This feedback process allows the server to improve the model and adjust it so that future suggestions are more relatable and provide more effective advice to the user.

[0556] For example, in the case of a company considering new business development, this system utilizes historical market data and user feedback to not only analyze points of differentiation from competitors and market needs in detail, but also provides an approach that emphasizes risk mitigation measures if the user is feeling anxious. As a result, it can realize a next-generation consulting service that is more user-centric than traditional business advice.

[0557] The following describes the processing flow.

[0558] Step 1:

[0559] The server accesses various data sources within the company and automatically collects the necessary data via APIs. Furthermore, it also incorporates data related to user sentiment during feedback.

[0560] Step 2:

[0561] The server integrates the collected data and performs preprocessing using data processing tools. Missing values ​​are imputed using mean values ​​or modes, and outliers are detected and corrected using a rule-based approach.

[0562] Step 3:

[0563] The server activates the emotion engine and analyzes the user's emotions from the collected feedback data. It then classifies these emotions into categories (e.g., positive, negative, neutral) using natural language processing.

[0564] Step 4:

[0565] The server selects the optimal analysis model based on the data and analyzed sentiment information. For example, it uses the ARIMA model for sales forecasting and a clustering algorithm for user interest analysis.

[0566] Step 5:

[0567] The server applies the selected analytical model and performs data analysis. The generated analysis results are visualized in the form of graphs and dashboards.

[0568] Step 6:

[0569] The server interprets the analysis results based on the user's emotions obtained from the emotion engine and generates advice. If the user expresses anxiety, the advice will emphasize risk avoidance measures.

[0570] Step 7:

[0571] The terminal notifies the user of the generated advice and displays a report. The user reviews the details of the advice through the interface.

[0572] Step 8:

[0573] Users follow the advice and provide feedback on the results. This feedback, including emotional input, is sent to the server via the device.

[0574] Step 9:

[0575] The server receives feedback data and uses feedback processing mechanisms to improve the model. User sentiment is reconsidered, and adjustments are made to reflect it in future advice.

[0576] (Example 2)

[0577] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0578] Traditional business consulting systems provide advice based on data analysis, but they have difficulty considering the user's emotional state. This has resulted in a lack of optimal advice tailored to the user's emotions, leading to problems with its feasibility and acceptability.

[0579] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0580] In this invention, the server includes data collection means, data processing means for integrating and pre-processing the collected data, and sentiment analysis means for analyzing the pre-processed data together with sentiment data. This makes it possible to provide business improvement advice that takes into account the user's emotional state, thereby improving feasibility and acceptability.

[0581] "Data collection means" refers to functions for automatically collecting various types of information related to a company, and it is possible to obtain necessary data from database connections and online information sources.

[0582] "Data processing means" refers to a process that integrates collected raw data, performs functions such as imputing missing values ​​and correcting outliers, and extracts sentiment data.

[0583] "Emotional analysis means" refers to a processing function that analyzes emotional states from user feedback and text data and assigns specific emotional tags to them.

[0584] "Model selection means" refers to a function that selects the optimal analytical model according to the analyzed data and applies it to the data to extract business insights.

[0585] "Result generation means" refers to a function that visualizes the results of data analysis as numbers and graphs, and further adjusts the expression of advice according to the user's emotional state.

[0586] "Advice generation method" refers to a function that uses a generative AI model and prompt text to document management improvement advice for users in natural language based on the analysis results obtained.

[0587] "Interface means" refers to an interactive platform that provides generated advice to the user and effectively collects feedback from the user.

[0588] "Feedback processing means" refers to a function that analyzes feedback collected from users, performs sentiment analysis, and improves the suggestion model based on the results to enhance the quality of advice for future use.

[0589] The embodiment of this invention is a system that is made possible by the collaboration of a server, a terminal, and a user.

[0590] The server uses a database connection to automatically collect various types of company information. This allows for the acquisition of diverse data such as sales data, customer feedback, and market research results. Data processing involves manipulating dataframes using the Python Pandas library, including imputing missing values ​​and correcting outliers. Furthermore, text analysis libraries such as Natural Language Toolkit are used to extract sentiment data from user feedback. The sentiment analysis system analyzes the user's emotional state based on this data and assigns sentiment tags. The analyzed data is then analyzed using machine learning models such as scikit-learn. The result generation system visualizes the data analysis results and adjusts them to take user emotions into consideration. Using a generative AI model, prompt sentences are used, and advice is documented using natural language processing techniques. This process ensures that the generated advice is easy for users to understand and leads to actual action.

[0591] The terminal notifies the user of advice generated by the server and provides a platform for the user to review the advice through an interface. Since this utilizes applications on smartphones and PCs, users can receive advice regardless of their location.

[0592] Users review the advice provided through their device and consider its feasibility. They then return feedback to the system, including the results of implementing the advice and their opinions. This feedback is then analyzed again by sentiment analysis tools and assigned sentiment tags. Using these results, the server can improve its next suggestion model and provide more personalized advice.

[0593] As a concrete example, a company considering a new business venture would utilize past market data and user feedback to analyze in detail its points of differentiation from competitors and market needs. In this case, an example of a prompt given to the AI ​​model would be: "For companies considering a new business venture, please analyze specific points of differentiation and market needs based on past market data and feedback, and propose measures to alleviate user concerns." This allows users to receive emotionally resonant and more actionable advice.

[0594] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0595] Step 1:

[0596] The server collects data related to the company. Input for data collection includes data from databases and external APIs. It uses SQL queries and API requests to retrieve sales data and customer feedback, and stores them in local storage. The output is an integrated dataset.

[0597] Step 2:

[0598] The server preprocesses the collected data. The input for this step is the integrated dataset obtained in step 1. Specifically, it uses the Python Pandas library to impute missing values ​​and correct outliers. The output is an improved dataset.

[0599] Step 3:

[0600] The server analyzes user feedback using sentiment analysis tools. The input is user feedback in text format. Using the Natural Language Toolkit, sentiment data is extracted from the feedback text, and specific sentiment tags are assigned to classify the emotional state. The output is feedback data with sentiment tags.

[0601] Step 4:

[0602] The server selects an analysis model using a model selection mechanism based on preprocessed data. The input consists of a high-quality dataset and data tagged with sentiment. Using the scikit-learn library, it selects an appropriate model such as linear regression or clustering and performs data analysis. The analysis results are generated as output.

[0603] Step 5:

[0604] The server uses result generation tools to visualize analysis results and adjust them to the user's emotions. Analysis results are used as input, and the results are presented as visual graphs and charts. The content is adjusted to reflect the user's emotions and documented in natural language. The output consists of adjusted visual information and natural language advice.

[0605] Step 6:

[0606] The terminal receives advice generated by the server and notifies the user through a user interface. Input consists of natural language advice and visual information. The terminal displays the advice to the user via a smartphone or PC and provides instructions on how to proceed based on the results. Output is a user-accessible display of the advice.

[0607] Step 7:

[0608] The user receives advice through a device and considers its feasibility. The input is the advice information from the device. The user then considers improvement measures based on the advice received. The expected output is an action plan based on the advice.

[0609] Step 8:

[0610] Users provide feedback to the system via their devices. Input includes their experiences and opinions after receiving advice. The feedback is then analyzed again using sentiment analysis tools. The output, with newly assigned sentiment tags, is stored on the server.

[0611] Step 9:

[0612] The server uses feedback to improve the model. The input is feedback data tagged with sentiment. Based on the insights gained from the feedback, the parameters of the proposed model are adjusted, making the next advice more personalized. The output is the improved model settings.

[0613] (Application Example 2)

[0614] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0615] Traditional business consulting systems provide management improvement advice based on data analysis, but they have difficulty providing advice that takes into account the user's emotions. As a result, advice that is not sufficiently empathetic to the user is not provided, and effective management improvements are sometimes not implemented. Furthermore, in individual user experiences such as electronic payments, emotional feedback is not taken into consideration, leading to problems with decreased user satisfaction.

[0616] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0617] In this invention, the server includes data acquisition means, information processing means, and method selection means. This makes it possible to take user emotions into consideration and provide improvement suggestions that are optimal for the individual experience.

[0618] "Data acquisition means" refers to functions that collect information related to user behavior and transactions.

[0619] "Information processing means" refers to a function that integrates acquired information, performs preprocessing to improve data quality, and converts it into a format suitable for analysis.

[0620] The "method selection means" is a function that selects and applies the optimal analysis method based on pre-processed information.

[0621] A "result generation method" is a function that generates analysis results and visualizes them in a format that is easy for the user to understand.

[0622] An "emotional assessment tool" is a function that identifies and analyzes a user's emotional state.

[0623] The "proposal creation method" is a function that creates improvement suggestions tailored to user needs based on analysis results and sentiment evaluations.

[0624] A "dialogue mechanism" is a function that provides an interface for presenting suggestions to the user and collecting user responses and feedback.

[0625] A "response processing means" is a function that improves the analysis method based on responses and feedback from users.

[0626] This invention is a system that functions as a business consultant system and electronic payment advisor that takes user emotions into consideration, and is configured based on the roles of server, terminal, and user.

[0627] The server collects user transaction history and feedback data using data acquisition means. This information is integrated and preprocessed by information processing means. For example, using NLTK (Natural Language Toolkit) or other text processing libraries, sentiment evaluation means analyzes the user's emotions. Based on the analyzed emotions, method selection means selects the optimal analysis method and performs the analysis.

[0628] The analysis results are visualized by the results generation system, and the proposal creation system generates improvement suggestions based on these results. These suggestions are sent to the terminal via the dialogue system, allowing the user to review them directly.

[0629] Users accept suggestions and provide feedback using their devices. This feedback is then sent back to the server, and the response processing system uses the feedback to improve its analysis methods and algorithms. Through this process, the system can continuously provide optimal advice tailored to the user's needs.

[0630] As a concrete example, suppose a user is struggling with budget management. The server uses the user's emotional data to generate stress-reducing advice, which is then displayed on the device. By using prompts such as, "Generate emotionally reassuring payment advice based on recent purchase history and feedback," the AI ​​can generate more specific and personalized suggestions.

[0631] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0632] Step 1:

[0633] The server collects user transaction history and feedback data using data acquisition methods. In this process, transaction information and past feedback provided by the user are used as input, and the data is collected from necessary databases and output as organized information. Specifically, information is obtained through API calls and database queries.

[0634] Step 2:

[0635] The server integrates and preprocesses the collected data using information processing tools. In this step, the acquired raw data is taken as input, and after imputing missing values ​​and cleaning the data, it is output as data in an analyzable format. Data preprocessing includes, for example, using the Python Pandas library to imputate missing values ​​and remove outliers.

[0636] Step 3:

[0637] The server uses sentiment evaluation tools to analyze the user's emotions from pre-processed data. In this step, text data is used as input, and the result of the sentiment analysis is output as sentiment information such as positive, negative, or neutral. Specifically, the Natural Language Toolkit (NLTK) is used to score the sentiment of the text.

[0638] Step 4:

[0639] The server uses a method selection mechanism to choose the optimal analysis method based on the analyzed sentiment data and performs data analysis. Here, sentiment data and preprocessed data are input, and analysis results suitable for the business situation are output. Specifically, a machine learning model is selected and applied to the data to generate prediction and classification results.

[0640] Step 5:

[0641] The server uses a result generation mechanism to visualize the analysis results and convert them into advice in natural language. In this step, the analysis results are input, and the output is in the form of graphs, charts, and natural language advice. Specifically, the Matplotlib library is used to generate graphs, and a generative AI model is used to create natural language explanations.

[0642] Step 6:

[0643] The server sends the advice generated through the interaction to the terminal, and the user receives and confirms the advice. In this step, the generated advice becomes input and is displayed on the terminal in a user-friendly format. Specifically, data transmission is performed using HTTP communication.

[0644] Step 7:

[0645] Users receive advice using their devices and send their thoughts and feedback to the server. In this process, user feedback information is input and output as feedback data that is reflected in the system. Specifically, users fill out and submit a feedback form on their devices.

[0646] Step 8:

[0647] The server uses response processing to improve analysis methods and algorithms based on collected feedback. In this step, user feedback data is used as input, and optimized models and methods are output. Specifically, the feedback data is used to adjust model parameters and update algorithms.

[0648] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0649] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0650] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0651] [Fourth Embodiment]

[0652] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0653] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0654] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0655] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0656] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0657] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0658] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0659] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0660] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0661] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0662] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0663] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0664] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0665] The AI ​​business consultant system according to the present invention is designed to support corporate decision-making by automating the entire process from the collection and analysis of relevant data to the provision of results. The entire system operates between a server, a terminal, and a user.

[0666] The server first periodically accesses the company's data sources to collect necessary information. It retrieves data from various sources, such as ERP systems, CRM systems, and external market databases, and manages it centrally.

[0667] Next, the server uses data processing tools to integrate and preprocess the collected data. Since the collected data may contain missing or outlier values, the accuracy of the analysis is improved by appropriately imputing or correcting these.

[0668] Based on the processed data, the server uses a model selection mechanism to choose the optimal analysis model and applies that model. In this process, the server utilizes machine learning and statistical analysis algorithms to select the most suitable model according to the characteristics of the data.

[0669] Once the analysis is complete, the server visually represents the results through a results generation mechanism. These results are presented not only as numerical data but also in a graphical format, supporting corporate decision-making.

[0670] The terminal provides the user with the generated analysis results and advice. The advice generation mechanism presents these results to the user in an easy-to-understand report format using natural language processing technology.

[0671] At that time, the user reviews the advice provided via the terminal and provides feedback. This feedback includes the effectiveness of the suggested advice and the results of its application. Based on this, the server re-evaluates the model using the feedback processing mechanism and makes improvements.

[0672] For example, if a small or medium-sized enterprise is considering launching a new product, this system analyzes market data and historical sales data to suggest the optimal launch timing and target market. It can also evaluate the effectiveness of the suggestions after implementation, contributing to the development of future strategies.

[0673] Thus, the present invention provides data-driven analysis and advice, thereby helping to move away from conventional subjective decision-making and support the formulation of sophisticated business strategies.

[0674] The following describes the processing flow.

[0675] Step 1:

[0676] The server accesses various data sources within the company and periodically collects the necessary data using APIs and data import tools. This ensures that the system incorporates the latest information.

[0677] Step 2:

[0678] The server integrates the collected data using data processing tools and performs data cleansing. Missing values ​​are imputed based on past trends and averages, and outliers are identified and corrected. These processes are performed automatically to ensure data quality.

[0679] Step 3:

[0680] Based on the preprocessed data, the server uses a model selection mechanism to choose the optimal analysis model. For example, a time series forecasting model or a clustering algorithm may be selected, and the most suitable application is made according to the data characteristics.

[0681] Step 4:

[0682] The server applies the selected model to analyze the data. The analysis results are output as numerical data, which are then visualized in graph or dashboard format by a results generation tool.

[0683] Step 5:

[0684] Based on the analysis results, the server uses an advice generation system to create specific business improvement advice. This advice is documented using natural language processing technology and compiled into a report.

[0685] Step 6:

[0686] The terminal notifies the user of the generated report and displays the details through a dedicated interface. Based on this, the user makes decisions and develops actionable strategies.

[0687] Step 7:

[0688] The user provides feedback to the server via their terminal, showing the results after implementing the suggested advice. This feedback includes information about the effectiveness of the advice and the results of its application.

[0689] Step 8:

[0690] The server collects user feedback and uses feedback processing to evaluate the model. It adjusts the analysis model as needed to improve the accuracy of subsequent analyses.

[0691] (Example 1)

[0692] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0693] Businesses and organizations require vast amounts of diverse data to make informed business decisions. However, efficiently collecting this data, analyzing it consistently, and providing appropriate advice is challenging. Furthermore, data preprocessing to improve quality and adapting models to dynamic market environments are necessary, but performing these manually is time-consuming and costly. This invention aims to solve these problems and provide an automated, data-driven decision support system.

[0694] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0695] In this invention, the server includes means for accessing information sources and collecting relevant information, data processing means for integrating and preprocessing the collected information, including imputing missing values ​​and correcting outliers, and model selection means for selecting and applying the optimal analysis model based on the preprocessed information. This makes it possible to efficiently process diverse data and quickly provide accurate analysis results.

[0696] "Information source" refers to an external or internal data provider from which a system collects data, and the source from which information is provided.

[0697] "Data processing means" refers to the process of preparing collected data for analysis, and includes means that perform functions such as imputing missing values ​​and correcting outliers.

[0698] A "model selection means" is a function that selects and applies the optimal analysis model based on pre-processed information.

[0699] The "result generation means" is a function that generates analysis results in numerical and graphical formats and presents them in a visually easy-to-understand manner.

[0700] A "guideline creation tool" is a function that generates and provides policies for business improvement based on analysis results.

[0701] "Means of communication" refers to means of providing guidance to users and receiving their feedback.

[0702] A "feedback processing mechanism" is a function for re-evaluating and improving the analysis model based on the collected feedback.

[0703] A "generative AI model" is a component of artificial intelligence that generates appropriate output from given input data, enabling analysis and prompt generation for decision support.

[0704] A "prompt" is a sentence that serves as an instruction or question to a generative AI model, providing guidance for the model to perform a specific task.

[0705] Modes for carrying out the invention

[0706] The AI ​​business consultant system of the present invention supports management decision-making by automating the collection, processing, and analysis of relevant information and the provision of feedback to the user. The main components of this system are realized through the interaction of a server, a terminal, and the user.

[0707] Data collection and processing

[0708] The server periodically accesses corporate data sources and automatically collects information from ERP systems, CRMs, external market databases, and other sources. This information may be obtained through various APIs or downloaded in file format and aggregated in one location. The server then integrates this collected information using data processing tools and performs preprocessing, including imputing missing values ​​and correcting outliers. Specific data processing software used includes Python libraries such as Pandas and NumPy.

[0709] Model selection and result generation

[0710] The server uses pre-processed information to select the most appropriate analysis model. Here, machine learning libraries such as TensorFlow and Scikit-learn are utilized to perform modeling necessary for sales forecasting, market analysis, and other applications. The modeled results are visualized using Matplotlib and Tableau, and generated as graphs and dashboards.

[0711] Providing advice and feedback

[0712] The terminal receives analysis results generated from the server and uses natural language processing technology to create reports that are easy for the user to understand. This allows the user to receive detailed guidance on future market trend forecasts and product launch strategies. For example, based on the scenario "What is the optimal marketing strategy for the next quarter?", the system inputs the prompt "Predict market trends for the next quarter and indicate which product categories should be focused on" into the AI ​​model and proposes the optimal strategy.

[0713] Feedback and model improvement

[0714] Users make decisions based on guidelines received via their devices and provide feedback on the results. This feedback information is analyzed by the server and used for re-evaluation during model selection and data processing. This allows the system to continuously learn and improve, enabling it to continue providing highly accurate consulting tailored to user needs.

[0715] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0716] Step 1:

[0717] The server accesses sources such as ERP systems, CRMs, and external market databases to collect data. Inputs are provided in the form of APIs or data files. In this process, the server retrieves relevant information periodically as a scheduled task and integrates it into a centralized dataset. Output is the collected raw data, which is stored in a database.

[0718] Step 2:

[0719] The server preprocesses the collected data using data processing tools. The input is the raw data collected in step 1. Specifically, it uses the Python library Pandas to computationally impute missing values ​​and detect and remove outliers. This data processing results in a clean and consistent dataset.

[0720] Step 3:

[0721] The server selects and applies the optimal analysis model based on pre-processed data as input. It uses a machine learning library (e.g., Scikit-learn) to select a model based on data trends. In this case, models for sales forecasting and market trend analysis are selected and applied. The output consists of predicted data and trend visualizations as analysis results.

[0722] Step 4:

[0723] The server visualizes the analysis results and expresses them as numerical data and diagrams. The input is the analysis results generated in step 3. Specific operations include generating graphs using Matplotlib and creating dashboards using Tableau. The output is a report in a format that facilitates visual understanding.

[0724] Step 5:

[0725] The terminal uses the visualized results received from the server to generate a report using natural language processing technology. The input is the visualized data from step 4. Specifically, it uses a natural language generation library to output text that is easy for the AI ​​model to understand. The output is a guideline report to support user decision-making.

[0726] Step 6:

[0727] The user receives guidance from the terminal and makes decisions based on it. The input is the report from step 5. Specifically, the user inputs feedback into the terminal and evaluates its effectiveness and the validity of the suggestions. The output is sent back to the system as feedback information and used by the server to improve the model and advice generation process.

[0728] (Application Example 1)

[0729] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0730] Planning the handling of goods in a logistics center requires careful inventory management and optimization of shipping schedules. However, traditional methods make it difficult to effectively analyze large amounts of data, potentially leading to inefficient planning and incorrect decisions. A system is needed to solve these problems and improve the operational efficiency of logistics centers.

[0731] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0732] In this invention, the server includes data aggregation means, data processing means for integrating and pre-processing the collected data, model selection means for selecting and applying an analysis model based on the pre-processed data, planning optimization means for supporting the planning of goods handling in a warehouse, and anomaly detection means for detecting anomalies using the information and sending warnings. This enables optimization of operational plans and rapid response to anomalies in a logistics center.

[0733] A "data aggregation method" is a function that periodically acquires necessary information from internal and external sources within a company and stores it in a database.

[0734] "Data processing means" refers to a function that integrates collected information and formats it into an analyzable state by imputing missing values ​​and correcting outliers.

[0735] A "model selection means" is a function that includes an algorithm for selecting and applying the optimal analysis model based on preprocessed information.

[0736] A "result generation means" is a function for visually representing the results of the analysis as text or graphs.

[0737] A "proposal generation tool" is a function that generates proposals for business improvement based on analysis results.

[0738] An "interface means" is a function that provides suggestions to users and collects feedback from them.

[0739] A "response processing means" is a function that improves the analysis model based on feedback from the user.

[0740] "Planning optimization means" refers to functions that support the improvement of efficiency in goods management and shipping planning at logistics facilities.

[0741] An "anomaly detection method" is a function that identifies anomalies based on analysis results and real-time data, and issues warnings in a timely manner.

[0742] The server periodically collects necessary information from internal and external sources, such as ERP systems and market databases, using data aggregation tools. This information is stored in a database and used for subsequent processing. The collected information is integrated by data processing tools, and missing values ​​are imputed and outliers are corrected. This creates a dataset suitable for analysis.

[0743] Next, the server analyzes this preprocessed data by using a model selection mechanism to determine and apply the optimal analysis model. By utilizing machine learning algorithms and statistical analysis, advanced analysis tailored to the data characteristics is achieved. The analysis results are visualized as graphs and charts by a results generation mechanism. This provides information in a way that users can intuitively understand.

[0744] Furthermore, the server uses a proposal generation mechanism to generate business improvement proposals based on the analysis results. These proposals are expressed in an easy-to-understand format using natural language processing technology and provided to the user via a terminal. The user reviews the proposals via the terminal and provides a response, which the response processing mechanism then uses to improve the model.

[0745] As a concrete example, in inventory management at a logistics center, this system combines real-time inventory data with market demand forecast data to propose optimal replenishment plans and shipping strategies. Furthermore, if the anomaly detection mechanism detects an anomaly, it immediately sends a warning to the user, prompting quick action. An example of a prompt for the generated AI model is: "Select an analytical model for inventory optimization based on the following two data sets, and report the results in natural language. Inventory data: {inventory_data} Market demand data: {demand_data}".

[0746] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0747] Step 1:

[0748] The server uses data aggregation tools to periodically collect necessary data from sources such as ERP systems and market databases. In this step, the inputs include company inventory data and market demand data, and the output is the collected raw data stored in the database. The data collection process is periodically triggered by automated scripts to maintain data integrity.

[0749] Step 2:

[0750] The server uses data processing tools to integrate the collected raw data, imputing missing values ​​and correcting outliers. In this step, the raw data collected in step 1 is taken as input, and formatted data suitable for analysis is generated as output. Specifically, the data is cleansed to extract only the information necessary for analysis.

[0751] Step 3:

[0752] The server uses a model selection mechanism to select and apply the optimal analysis model based on the pre-processed data. In this step, the input is pre-processed data, and the output is the analysis results generated by the model. Machine learning algorithms are applied to perform predictions and clustering according to the data characteristics.

[0753] Step 4:

[0754] The server uses a results generation mechanism to visualize the analysis results in graphs and charts. In this step, the analysis results from step 3 are taken as input, and a visualized report is generated as output. The visualization tool organizes the information in an intuitively easy-to-understand format.

[0755] Step 5:

[0756] The server uses a proposal generation tool to generate proposals for business improvement based on visualized analysis results. In this step, visualized information is taken as input, and a proposal document expressed in natural language is generated as output. Natural language processing technology is used to convert complex data into concise sentences.

[0757] Step 6:

[0758] The terminal uses an interface to provide suggestions to the user. It then receives responses from the user. In this step, the input is a proposal document, and the output is the collection of user feedback. The user reviews the proposal on the terminal screen and inputs their own opinions and suggestions for improvement.

[0759] Step 7:

[0760] The server uses a response processing mechanism to improve the analysis model based on user feedback. In this step, user feedback is the input, and the improved analysis model is the output. The feedback information is used to adjust model parameters and train new data.

[0761] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0762] This invention incorporates an emotion engine into an AI business consultant system, making it possible to provide business improvement advice that takes into account the user's emotional state. This system employs a more human-centered approach based on the interaction between the server, terminal, and user.

[0763] The server first automatically collects various types of corporate data and performs preprocessing of the integrated data. In addition to conventional data processing functions, it utilizes an emotion engine to analyze user emotion data collected during feedback. After data processing, the server selects an appropriate analysis model, analyzes the data, and generates results.

[0764] The generated analysis results are not simply presented as numerical data or graphical visual information, but are also adjusted to align with the user's emotions as analyzed by the emotion engine. This allows the server to create advice that takes the user's emotional state into account through an advice generation mechanism, and then compile it into a report format in natural language.

[0765] The terminal notifies the user of the generated report and allows the user to review the advice through the interface. The user receives the advice via the terminal, reviews its contents, and then considers its feasibility.

[0766] Furthermore, when users provide feedback on the effects after implementation, the emotion engine recognizes and classifies emotions from the user's text data. This feedback process allows the server to improve the model and adjust it so that future suggestions are more relatable and provide more effective advice to the user.

[0767] For example, in the case of a company considering new business development, this system utilizes historical market data and user feedback to not only analyze points of differentiation from competitors and market needs in detail, but also provides an approach that emphasizes risk mitigation measures if the user is feeling anxious. As a result, it can realize a next-generation consulting service that is more user-centric than traditional business advice.

[0768] The following describes the processing flow.

[0769] Step 1:

[0770] The server accesses various data sources within the company and automatically collects the necessary data via APIs. Furthermore, it also incorporates data related to user sentiment during feedback.

[0771] Step 2:

[0772] The server integrates the collected data and performs preprocessing using data processing tools. Missing values ​​are imputed using mean values ​​or modes, and outliers are detected and corrected using a rule-based approach.

[0773] Step 3:

[0774] The server activates the emotion engine and analyzes the user's emotions from the collected feedback data. It then classifies these emotions into categories (e.g., positive, negative, neutral) using natural language processing.

[0775] Step 4:

[0776] The server selects the optimal analysis model based on the data and analyzed sentiment information. For example, it uses the ARIMA model for sales forecasting and a clustering algorithm for user interest analysis.

[0777] Step 5:

[0778] The server applies the selected analytical model and performs data analysis. The generated analysis results are visualized in the form of graphs and dashboards.

[0779] Step 6:

[0780] The server interprets the analysis results based on the user's emotions obtained from the emotion engine and generates advice. If the user expresses anxiety, the advice will emphasize risk avoidance measures.

[0781] Step 7:

[0782] The terminal notifies the user of the generated advice and displays a report. The user reviews the details of the advice through the interface.

[0783] Step 8:

[0784] Users follow the advice and provide feedback on the results. This feedback, including emotional input, is sent to the server via the device.

[0785] Step 9:

[0786] The server receives feedback data and uses feedback processing mechanisms to improve the model. User sentiment is reconsidered, and adjustments are made to reflect it in future advice.

[0787] (Example 2)

[0788] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0789] Traditional business consulting systems provide advice based on data analysis, but they have difficulty considering the user's emotional state. This has resulted in a lack of optimal advice tailored to the user's emotions, leading to problems with its feasibility and acceptability.

[0790] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0791] In this invention, the server includes data collection means, data processing means for integrating and pre-processing the collected data, and sentiment analysis means for analyzing the pre-processed data together with sentiment data. This makes it possible to provide business improvement advice that takes into account the user's emotional state, thereby improving feasibility and acceptability.

[0792] "Data collection means" refers to functions for automatically collecting various types of information related to a company, and it is possible to obtain necessary data from database connections and online information sources.

[0793] "Data processing means" refers to a process that integrates collected raw data, performs functions such as imputing missing values ​​and correcting outliers, and extracts sentiment data.

[0794] "Emotional analysis means" refers to a processing function that analyzes emotional states from user feedback and text data and assigns specific emotional tags to them.

[0795] "Model selection means" refers to a function that selects the optimal analytical model according to the analyzed data and applies it to the data to extract business insights.

[0796] "Result generation means" refers to a function that visualizes the results of data analysis as numbers and graphs, and further adjusts the expression of advice according to the user's emotional state.

[0797] "Advice generation method" refers to a function that uses a generative AI model and prompt text to document management improvement advice for users in natural language based on the analysis results obtained.

[0798] "Interface means" refers to an interactive platform that provides generated advice to the user and effectively collects feedback from the user.

[0799] "Feedback processing means" refers to a function that analyzes feedback collected from users, performs sentiment analysis, and improves the suggestion model based on the results to enhance the quality of advice for future use.

[0800] The embodiment of this invention is a system that is made possible by the collaboration of a server, a terminal, and a user.

[0801] The server uses a database connection to automatically collect various types of company information. This allows for the acquisition of diverse data such as sales data, customer feedback, and market research results. Data processing involves manipulating dataframes using the Python Pandas library, including imputing missing values ​​and correcting outliers. Furthermore, text analysis libraries such as Natural Language Toolkit are used to extract sentiment data from user feedback. The sentiment analysis system analyzes the user's emotional state based on this data and assigns sentiment tags. The analyzed data is then analyzed using machine learning models such as scikit-learn. The result generation system visualizes the data analysis results and adjusts them to take user emotions into consideration. Using a generative AI model, prompt sentences are used, and advice is documented using natural language processing techniques. This process ensures that the generated advice is easy for users to understand and leads to actual action.

[0802] The terminal notifies the user of advice generated by the server and provides a platform for the user to review the advice through an interface. Since this utilizes applications on smartphones and PCs, users can receive advice regardless of their location.

[0803] Users review the advice provided through their device and consider its feasibility. They then return feedback to the system, including the results of implementing the advice and their opinions. This feedback is then analyzed again by sentiment analysis tools and assigned sentiment tags. Using these results, the server can improve its next suggestion model and provide more personalized advice.

[0804] As a concrete example, a company considering a new business venture would utilize past market data and user feedback to analyze in detail its points of differentiation from competitors and market needs. In this case, an example of a prompt given to the AI ​​model would be: "For companies considering a new business venture, please analyze specific points of differentiation and market needs based on past market data and feedback, and propose measures to alleviate user concerns." This allows users to receive emotionally resonant and more actionable advice.

[0805] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0806] Step 1:

[0807] The server collects data related to the company. Input for data collection includes data from databases and external APIs. It uses SQL queries and API requests to retrieve sales data and customer feedback, and stores them in local storage. The output is an integrated dataset.

[0808] Step 2:

[0809] The server preprocesses the collected data. The input for this step is the integrated dataset obtained in step 1. Specifically, it uses the Python Pandas library to impute missing values ​​and correct outliers. The output is an improved dataset.

[0810] Step 3:

[0811] The server analyzes user feedback using sentiment analysis tools. The input is user feedback in text format. Using the Natural Language Toolkit, sentiment data is extracted from the feedback text, and specific sentiment tags are assigned to classify the emotional state. The output is feedback data with sentiment tags.

[0812] Step 4:

[0813] The server selects an analysis model using a model selection mechanism based on preprocessed data. The input consists of a high-quality dataset and data tagged with sentiment. Using the scikit-learn library, it selects an appropriate model such as linear regression or clustering and performs data analysis. The analysis results are generated as output.

[0814] Step 5:

[0815] The server uses result generation tools to visualize analysis results and adjust them to the user's emotions. Analysis results are used as input, and the results are presented as visual graphs and charts. The content is adjusted to reflect the user's emotions and documented in natural language. The output consists of adjusted visual information and natural language advice.

[0816] Step 6:

[0817] The terminal receives advice generated by the server and notifies the user through a user interface. Input consists of natural language advice and visual information. The terminal displays the advice to the user via a smartphone or PC and provides instructions on how to proceed based on the results. Output is a user-accessible display of the advice.

[0818] Step 7:

[0819] The user receives advice through a device and considers its feasibility. The input is the advice information from the device. The user then considers improvement measures based on the advice received. The expected output is an action plan based on the advice.

[0820] Step 8:

[0821] Users provide feedback to the system via their devices. Input includes their experiences and opinions after receiving advice. The feedback is then analyzed again using sentiment analysis tools. The output, with newly assigned sentiment tags, is stored on the server.

[0822] Step 9:

[0823] The server uses feedback to improve the model. The input is feedback data tagged with sentiment. Based on the insights gained from the feedback, the parameters of the proposed model are adjusted, making the next advice more personalized. The output is the improved model settings.

[0824] (Application Example 2)

[0825] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0826] Traditional business consulting systems provide management improvement advice based on data analysis, but they have difficulty providing advice that takes into account the user's emotions. As a result, advice that is not sufficiently empathetic to the user is not provided, and effective management improvements are sometimes not implemented. Furthermore, in individual user experiences such as electronic payments, emotional feedback is not taken into consideration, leading to problems with decreased user satisfaction.

[0827] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0828] In this invention, the server includes data acquisition means, information processing means, and method selection means. This makes it possible to take user emotions into consideration and provide improvement suggestions that are optimal for the individual experience.

[0829] "Data acquisition means" refers to functions that collect information related to user behavior and transactions.

[0830] "Information processing means" refers to a function that integrates acquired information, performs preprocessing to improve data quality, and converts it into a format suitable for analysis.

[0831] The "method selection means" is a function that selects and applies the optimal analysis method based on pre-processed information.

[0832] A "result generation method" is a function that generates analysis results and visualizes them in a format that is easy for the user to understand.

[0833] An "emotional assessment tool" is a function that identifies and analyzes a user's emotional state.

[0834] The "proposal creation method" is a function that creates improvement suggestions tailored to user needs based on analysis results and sentiment evaluations.

[0835] A "dialogue mechanism" is a function that provides an interface for presenting suggestions to the user and collecting user responses and feedback.

[0836] A "response processing means" is a function that improves the analysis method based on responses and feedback from users.

[0837] This invention is a system that functions as a business consultant system and electronic payment advisor that takes user emotions into consideration, and is configured based on the roles of server, terminal, and user.

[0838] The server collects user transaction history and feedback data using data acquisition means. This information is integrated and preprocessed by information processing means. For example, using NLTK (Natural Language Toolkit) or other text processing libraries, sentiment evaluation means analyzes the user's emotions. Based on the analyzed emotions, method selection means selects the optimal analysis method and performs the analysis.

[0839] The analysis results are visualized by the results generation system, and the proposal creation system generates improvement suggestions based on these results. These suggestions are sent to the terminal via the dialogue system, allowing the user to review them directly.

[0840] Users accept suggestions and provide feedback using their devices. This feedback is then sent back to the server, and the response processing system uses the feedback to improve its analysis methods and algorithms. Through this process, the system can continuously provide optimal advice tailored to the user's needs.

[0841] As a concrete example, suppose a user is struggling with budget management. The server uses the user's emotional data to generate stress-reducing advice, which is then displayed on the device. By using prompts such as, "Generate emotionally reassuring payment advice based on recent purchase history and feedback," the AI ​​can generate more specific and personalized suggestions.

[0842] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0843] Step 1:

[0844] The server collects user transaction history and feedback data using data acquisition methods. In this process, transaction information and past feedback provided by the user are used as input, and the data is collected from necessary databases and output as organized information. Specifically, information is obtained through API calls and database queries.

[0845] Step 2:

[0846] The server integrates and preprocesses the collected data using information processing tools. In this step, the acquired raw data is taken as input, and after imputing missing values ​​and cleaning the data, it is output as data in an analyzable format. Data preprocessing includes, for example, using the Python Pandas library to imputate missing values ​​and remove outliers.

[0847] Step 3:

[0848] The server uses sentiment evaluation tools to analyze the user's emotions from pre-processed data. In this step, text data is used as input, and the result of the sentiment analysis is output as sentiment information such as positive, negative, or neutral. Specifically, the Natural Language Toolkit (NLTK) is used to score the sentiment of the text.

[0849] Step 4:

[0850] The server uses a method selection mechanism to choose the optimal analysis method based on the analyzed sentiment data and performs data analysis. Here, sentiment data and preprocessed data are input, and analysis results suitable for the business situation are output. Specifically, a machine learning model is selected and applied to the data to generate prediction and classification results.

[0851] Step 5:

[0852] The server uses a result generation mechanism to visualize the analysis results and convert them into advice in natural language. In this step, the analysis results are input, and the output is in the form of graphs, charts, and natural language advice. Specifically, the Matplotlib library is used to generate graphs, and a generative AI model is used to create natural language explanations.

[0853] Step 6:

[0854] The server sends the advice generated through the interaction to the terminal, and the user receives and confirms the advice. In this step, the generated advice becomes input and is displayed on the terminal in a user-friendly format. Specifically, data transmission is performed using HTTP communication.

[0855] Step 7:

[0856] Users receive advice using their devices and send their thoughts and feedback to the server. In this process, user feedback information is input and output as feedback data that is reflected in the system. Specifically, users fill out and submit a feedback form on their devices.

[0857] Step 8:

[0858] The server uses response processing to improve analysis methods and algorithms based on collected feedback. In this step, user feedback data is used as input, and optimized models and methods are output. Specifically, the feedback data is used to adjust model parameters and update algorithms.

[0859] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0860] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0861] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0862] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0863] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0864] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0865] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0866] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0867] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0868] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0869] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0870] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0871] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0872] 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.

[0873] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0874] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0875] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0876] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0877] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0878] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0879] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0880] The following is further disclosed regarding the embodiments described above.

[0881] (Claim 1)

[0882] Data collection means,

[0883] A data processing means that integrates and preprocesses the collected data,

[0884] A model selection means for selecting and applying an analysis model based on preprocessed data,

[0885] A result generation means for generating and visualizing analysis results,

[0886] An advice generation tool that generates advice for business improvement based on analysis results,

[0887] An interface means for providing advice to users and collecting feedback,

[0888] A feedback processing means for improving the model based on feedback,

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, wherein the data processing means performs imputation of missing values ​​and correction of abnormal values.

[0892] (Claim 3)

[0893] The system according to claim 1, wherein the advice generation means documents the advice using natural language processing technology.

[0894] "Example 1"

[0895] (Claim 1)

[0896] Means of accessing information sources and collecting relevant information,

[0897] A data processing means that integrates and preprocesses the collected information, including imputing missing values ​​and correcting outliers,

[0898] A model selection means that selects and applies the optimal analysis model based on preprocessed information,

[0899] A result generation means that generates analysis results in numerical and graphical formats,

[0900] A guideline creation method that generates guidelines for business improvement based on analysis results,

[0901] A means of communication to provide guidelines and collect feedback from users,

[0902] A means for processing feedback to re-evaluate and improve the model based on the collected opinions,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, wherein the guideline creation means documents the guideline using natural language processing technology.

[0906] (Claim 3)

[0907] The system according to claim 1, wherein the communication means includes a function to generate prompt sentences that support the understanding of guidelines using a generative AI model.

[0908] "Application Example 1"

[0909] (Claim 1)

[0910] Data collection means,

[0911] A data processing means for integrating and pre-processing the collected data,

[0912] A model selection means for selecting and applying an analysis model based on preprocessed data,

[0913] A result generation means for generating and visualizing analysis results,

[0914] A proposal creation method that generates proposals for business improvement based on analysis results,

[0915] An interface means for providing suggestions to users and collecting responses,

[0916] A response processing means that improves the model based on the response,

[0917] A planning optimization means to support the planning of handling goods in a warehouse,

[0918] An anomaly detection means that uses information to detect anomalies and transmit warnings,

[0919] A system that includes this.

[0920] (Claim 2)

[0921] The system according to claim 1, wherein the data processing means performs imputation of missing values ​​and correction of abnormal values.

[0922] (Claim 3)

[0923] The system according to claim 1, wherein the proposal creation means documents the proposal using natural language processing technology.

[0924] "Example 2 of combining an emotion engine"

[0925] (Claim 1)

[0926] Data collection means,

[0927] A data processing means that integrates and preprocesses the collected data,

[0928] A sentiment analysis means for analyzing preprocessed data together with sentiment data,

[0929] A model selection means for selecting and applying an analysis model based on the analyzed data,

[0930] A result generation means that generates and visualizes analysis results and adjusts them based on the user's emotional state,

[0931] An advice generation tool that generates advice for business improvement based on analysis results,

[0932] An interface for documenting advice in natural language and providing it to the user,

[0933] A feedback processing method that collects user feedback, analyzes emotions, and improves the model,

[0934] A system that includes this.

[0935] (Claim 2)

[0936] The system according to claim 1, wherein the data processing means performs imputation of missing values ​​and correction of outliers, and extracts sentiment data from the collected feedback text.

[0937] (Claim 3)

[0938] The system according to claim 1, wherein the advice generation means documents the advice using a generated AI model and prompt sentences and makes adjustments in line with the user's emotional state.

[0939] "Application example 2 when combining with an emotional engine"

[0940] (Claim 1)

[0941] Data acquisition method,

[0942] Information processing means for integrating acquired information and performing preprocessing,

[0943] A method selection means that selects and applies an analysis method based on preprocessed information,

[0944] A result generation means for generating and visualizing analysis results,

[0945] A proposal creation method that generates improvement suggestions based on analysis results and sentiment evaluation,

[0946] A dialogue means that provides suggestions to the user and obtains responses,

[0947] A response processing means that improves the method based on the response,

[0948] A system that includes a means for evaluating emotions.

[0949] (Claim 2)

[0950] The system according to claim 1, wherein the information processing means performs the supplementation of missing information and the correction of abnormal information.

[0951] (Claim 3)

[0952] The system according to claim 1, wherein the proposal creation means documents the proposal using natural language processing technology. [Explanation of Symbols]

[0953] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Data collection means, A data processing means for integrating and pre-processing the collected data, A model selection means for selecting and applying an analysis model based on preprocessed data, A result generation means for generating and visualizing analysis results, A proposal creation method that generates proposals for business improvement based on analysis results, An interface means for providing suggestions to users and collecting responses, A response processing means that improves the model based on the response, A planning optimization means to support the planning of handling goods in a warehouse, An anomaly detection means that uses information to detect anomalies and transmit warnings, A system that includes this.

2. The system according to claim 1, wherein the data processing means performs imputation of missing values ​​and correction of abnormal values.

3. The system according to claim 1, wherein the proposal creation means documents the proposal using natural language processing technology.

Images