system

Abstract

We provide the system. [Solution] A means of obtaining data from information sources, organizing and recording the obtained data, A means of analyzing organized data using generative models and inferring trends from the analysis results, A means for generating a policy based on inferences and displaying the generated policy, A means of acquiring and analyzing new data in real time and updating policies, A means of providing policies and update information through a user interface, To support negotiations in electronic payments, we provide means to present optimal policies regarding payment fees and the introduction of new technologies, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In business negotiations, it is required to quickly and accurately perform a large amount of processing and analysis of relevant information and formulate an effective strategy, but it has been difficult to achieve with conventional methods. There is a lack of means for accurately grasping market trends and competitive situations and timely and dynamically updating negotiation strategies, so it is an issue to efficiently achieve this. Furthermore, secure information processing that takes into account privacy protection is required, and technologies that satisfy this simultaneously are needed.

Means for Solving the Problems

[0005] This invention provides a means for efficiently crawling information from an internet database, performing a cleansing process, and storing it neatly in the database. Furthermore, it includes a means for analyzing this data using a generative model and predicting market trends. This makes it possible to generate and output an optimal negotiation strategy to the user based on the prediction results. By performing real-time data collection and analysis, it enables strategy proposals and updates that are always based on the latest information. In addition, by dynamically presenting strategies and updated information using a user interface and protecting communications with encryption protocols, information is provided to the user while ensuring privacy.

[0006] "Crawling" is the process of automatically retrieving data from the internet.

[0007] "Cleansing" is the process of removing unnecessary information and duplicates from collected data and organizing it into a usable format.

[0008] A "database" is a system configured to efficiently store and manage information, and to allow it to be searched and retrieved as needed.

[0009] A "generative model" is an algorithm or mathematical method used to analyze collected data and generate new insights or predictions.

[0010] "Analysis" is the process of evaluating collected data and deriving meaningful information and conclusions.

[0011] "Prediction" is the process of estimating future trends based on past and present data.

[0012] A "negotiation strategy" is a carefully planned set of negotiation tactics and approaches designed to achieve specific business objectives.

[0013] "Real-time" is a term that refers to the characteristic of data collection and processing occurring simultaneously without delay.

[0014] A "user interface" is a design and structure that allows users to interact with a system intuitively.

[0015] An "encryption protocol" is a technical specification used to conceal communication content from third parties and protect the confidentiality of information.

[0016] "Privacy" refers to the right or state of having one's personal information protected from being leaked to outsiders or used inappropriately. [Brief explanation of the drawing]

[0017] [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] 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.

[0021] 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.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] This invention is a system that supports effective strategy formulation in business negotiations and streamlines the entire process by utilizing advanced data analysis techniques and generative models. Specific embodiments are described below.

[0039] Data collection and cleansing

[0040] The server crawls business-related information from numerous data sources accessible via the internet. This process includes data from public databases, industry reports, and company press releases. The collected information is cleansed on the server, removing unnecessary and duplicate data, and organized into a format suitable for subsequent analysis.

[0041] Data analysis and strategy generation

[0042] Based on the cleansed data, the server uses a generative model to analyze market trends and competitive landscapes. The analysis reveals predictions of competitor behavior and market trends, and based on this information, multiple negotiation strategies are generated. Each strategy is evaluated for its expected success rate and potential risk level, and the strategy deemed most effective is proposed to the user.

[0043] Strategic presentation through user interface

[0044] The terminal presents the optimal strategy, transmitted from the server, to the user through a user interface. This interface is visually intuitive, allowing the user to quickly grasp the details of the proposed strategy. The information displayed here is highly reliable because it is based on crawled data.

[0045] Real-time advice and strategy updates

[0046] As users progress through negotiations, new data is collected, and the server analyzes this data, updating the strategy in real time. This strategy update takes into account new market trends and the latest information on the other company, and is immediately presented to the user. This allows users to flexibly respond to changing negotiation situations.

[0047] Implementation of specific examples

[0048] For example, suppose a user is negotiating a contract with a supplier for a new product. The server analyzes relevant market news and industry trends and provides an analysis showing that the new product is advantageous compared to competitors' products. Based on these results, the terminal recommends to the user a strategy that emphasizes the product's technical features rather than its price advantage. This strategy can be effectively used by the user during negotiations to lead to improved terms of the deal.

[0049] Thus, the present invention provides data-driven strategies for business negotiations and supports users in responding promptly to changing market environments.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The server crawls business-related information from public databases and news sites on the internet. A crawling algorithm is used to retrieve the information, and the scope of data collection is defined based on keywords or specific URLs.

[0053] Step 2:

[0054] The collected data is cleansed on the server. The server performs a process to detect and remove duplicate data, and further performs noise filtering to extract useful data. This results in data in a format suitable for analysis.

[0055] Step 3:

[0056] The server uses a generative model to analyze the cleansed data. This process employs data mining techniques to identify past trends and patterns and predict market movements. The analysis results provide predictions for the target company's actions and market changes.

[0057] Step 4:

[0058] Based on the analysis results, the server generates multiple negotiation strategies. The server evaluates the success rate and risk level of each generated strategy and selects the optimal strategy for the user.

[0059] Step 5:

[0060] The selected strategy is sent from the server to the terminal, which then presents the strategy to the user through a user interface. The presented strategy is visually organized for easy understanding, allowing the user to review the details of each strategy.

[0061] Step 6:

[0062] The user proceeds with actual negotiations based on the proposed strategy, and inputs the information obtained along the way into the system. This transmits on-site feedback to the server.

[0063] Step 7:

[0064] The server reanalyzes the strategy in real time based on user feedback and new data, and adjusts it if necessary. The adjusted strategy is then sent back to the terminal and presented to the user.

[0065] Step 8:

[0066] This process is repeated throughout the negotiation process and is designed to increase overall efficiency and improve the user's chances of negotiation success.

[0067] (Example 1)

[0068] 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."

[0069] In business negotiations, there is a need for systems that can quickly formulate efficient and effective strategies and flexibly respond to changing market environments. Furthermore, in today's information-saturated world, collecting and analyzing reliable information is becoming increasingly complex, and there is a lack of technology that automates this process in a user-friendly manner. Moreover, considerations for privacy and security are also crucial issues.

[0070] 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.

[0071] In this invention, the server includes means for automatically acquiring information from information sources, organizing and storing the acquired information, means for analyzing the organized information using learned techniques and predicting future trends as a result of the analysis, and means for generating action guidelines based on the predictions and outputting the generated guidelines. This makes it possible to efficiently collect information, quickly formulate strategies based on analysis results, and respond in real time.

[0072] A "source of information" is a collection of data, such as databases, reports, and releases, that are accessed to obtain the necessary information.

[0073] "Automatically acquiring information" refers to the process of collecting information using a program without manual intervention.

[0074] "Organizing and accumulating" means converting acquired information into a consistent format and structure, and saving it in a way that facilitates subsequent processing and retrieval.

[0075] "Pre-trained techniques" refer to methods that utilize models trained on existing datasets to analyze new data.

[0076] "Analysis" is the process of understanding the characteristics, trends, and relationships of collected information and data.

[0077] "Predicting future trends" means looking ahead to future developments and events based on current and past data.

[0078] "Generating action guidelines" means creating the optimal action strategy to take in a specific situation, based on the analyzed information.

[0079] "Outputting" means displaying or transmitting generated information or results in a format usable by humans or other systems.

[0080] This invention is a system for automating and streamlining strategy formulation in business negotiations. Specific embodiments of the invention are described below.

[0081] The server automatically retrieves information from its sources. In this process, the server collects information from databases, reports, and press releases on the internet via a program. This information retrieval is performed efficiently by using Python libraries for data crawling.

[0082] The collected information is organized on the server and converted into a format suitable for subsequent analysis. This involves using Pandas and NumPy for data frame manipulation and cleansing. The server then uses pre-trained techniques to perform detailed analysis based on this organized information. This analysis process utilizes generative AI models such as TENSORFLOW® and PyTorch.

[0083] Based on the analysis results, the server predicts future trends and generates multiple action plans. This allows users to select the optimal strategy based on different business scenarios. Specifically, the action plans are provided through a visual display on the user's terminal. This user interface presents information visually in an easy-to-understand manner, enabling users to make quick decisions.

[0084] As users progress through negotiations, the server analyzes the data in real time and updates its course of action as new information becomes available. This feature ensures users always have the latest information and can adapt to dynamically changing negotiation situations.

[0085] As a concrete example, consider a scenario where a user is exploring strategies for a new product in a highly competitive market. The server analyzes market data and suggests that highlighting the new product's technical features is an effective strategy for gaining a competitive advantage. This strategy is visualized on the user's terminal, enabling rapid strategic adjustments.

[0086] An example of a prompt message might be, "Re-evaluate the optimal negotiation strategy based on new market trends." This allows users to make effective decisions even in a changing business environment.

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] The server automatically retrieves business-related information from information sources. This information includes databases, reports, and press releases. A Python library is used to perform the crawling process, and the raw data is temporarily stored in storage. The input is the data retrieved from the information sources, and the output is the raw retrieved data.

[0090] Step 2:

[0091] The server organizes and cleanses the acquired data. It removes unnecessary information and duplicate data and converts it into a format suitable for analysis. Specifically, it uses the Pandas library to format the data and NumPy to correct for outliers. The input is the raw acquired data, and the output is cleansed, well-formed data.

[0092] Step 3:

[0093] The server analyzes cleansed data to predict future trends. Generative AI models are used to understand market trends and competitive landscapes within the data. Predictive data is generated as analysis results through model processing using TensorFlow and PyTorch. Input is well-formed data, and output is the prediction and analysis results.

[0094] Step 4:

[0095] The server generates strategies based on prediction results. It devises multiple negotiation strategies and evaluates the likelihood of success and potential risks of each. It analyzes the strategies using statistical models and simulations. The input is the analysis results, and the output is the set of generated strategies.

[0096] Step 5:

[0097] The terminal presents the strategy, transmitted from the server, to the user through a user interface. The strategy information is displayed visually and provided in a format that is easy for the user to quickly understand. For example, infographics and charts are used to represent the key points of the strategy. The input is the generated strategy, and the output is the visualized strategy information.

[0098] Step 6:

[0099] As new data is generated during the user's negotiation process, the server analyzes that data in real time and updates the strategy. The updated strategy is immediately presented to the user. The strategy is re-evaluated based on new market trends and competitive situations. The input is new negotiation data, and the output is updated strategy information.

[0100] (Application Example 1)

[0101] 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."

[0102] Business negotiations, particularly those concerning the introduction of new technologies and fees in electronic payments, require rapid and effective strategy development. In today's rapidly changing market environment, where information is vast and trends are constantly evolving, formulating and updating appropriate and flexible negotiation strategies in a timely manner is challenging. This can lead to inefficient business negotiations and missed opportunities.

[0103] 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.

[0104] In this invention, the server includes means for acquiring data from information sources, organizing and recording the acquired data, means for analyzing the organized data using a generative model and inferring trends as a result of the analysis, and means for generating policies based on the inferences and displaying the generated policies. This enables the provision of optimal negotiation policies in response to new market information in real time and allows for rapid response even when the business environment changes.

[0105] A "source of information" is a collection of data, such as public databases, industry reports, and company press releases, that are accessed to obtain data.

[0106] A "generative model" is a machine learning algorithm that analyzes large amounts of data to generate useful trends and insights.

[0107] "Organization" is the process of removing unnecessary information and duplicates from acquired data, and preparing the data to facilitate analysis.

[0108] "To infer" means to predict market trends and corporate behavior based on the results of an analysis.

[0109] "Generating a policy" means creating the optimal strategy or action plan based on inferred information.

[0110] "To provide support for negotiations" means to offer users useful information and strategies when conducting business negotiations regarding payments.

[0111] The system that implements this application consists of a server, a terminal, and a user interface. The server first automatically retrieves the necessary data from the information source and organizes it through a data cleansing process. Data cleansing removes duplicate data and noise, preparing it for analysis by a generative model. This analysis uses machine learning frameworks such as TensorFlow and PyTorch to accurately predict market trends and company behavior from the collected data.

[0112] Next, the server generates the optimal negotiation strategy based on the analyzed data. This process utilizes the Python programming language to set up an action plan suitable for the specific negotiation situation. The generated strategy is sent to the terminal via an intuitive user interface. This interface is developed using React Native and provides a visually appealing display that makes it easy for users to understand and act upon.

[0113] Users can always obtain the latest negotiation information through this interface. A key feature is its ability to update policies in real time in response to market changes, supporting negotiations in electronic payments. For example, when considering the introduction of a new QR code (registered trademark) payment function, the application analyzes competitor activities and market trends, and presents a marketing strategy for success.

[0114] A good example of a prompt would be: "Analyze the following data list regarding QR code payment functionality, identify the advantages compared to competitors, and create a detailed proposal."

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

[0116] Step 1:

[0117] The server retrieves business-related data from information sources. The input is websites or databases as information sources, and the output is the retrieved raw data. In this process, the server uses web crawlers and APIs to collect data in real time.

[0118] Step 2:

[0119] The server cleanses and organizes the acquired data. The input is the raw data obtained in step 1, and the output is a clean dataset. This process involves removing duplicate data and filtering out noise. Specifically, it standardizes the data using regular expressions and statistical tools.

[0120] Step 3:

[0121] The server analyzes cleansed data using a generative model. The input is a clean dataset, and the output is inferential information about market trends and competitor behavior. As part of the data processing, machine learning algorithms are applied to create a predictive model.

[0122] Step 4:

[0123] The server generates negotiation strategies based on the inferred information. The input is the inferred information from step 3, and the output is the optimal strategy specific to each negotiation. As a data calculation, the results of the predictive model are evaluated, and a concrete strategy is constructed using the policy decision logic.

[0124] Step 5:

[0125] The terminal visually presents the generated negotiation strategy to the user. The input is the optimal strategy from the server, and the output is the information displayed on the user interface. Specifically, a highly responsive user interface is used to visually decompose the strategy.

[0126] Step 6:

[0127] The user conducts business negotiations by referring to the provided negotiation strategies. Inputs are information displayed from the terminal, and outputs are the user's actions and negotiation results. In this step, the user uses the proposed strategies to conduct more effective negotiations.

[0128] Step 7:

[0129] The server acquires and analyzes new data in real time and updates its policies. The input is newly acquired market data, and the output is the updated negotiation policy. Specifically, it re-analyzes the acquired data and makes policy adjustments that take into account the latest market trends.

[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 is a system that combines an emotion engine with a conventional business negotiation support system to provide a flexible and effective negotiation strategy that takes into account the user's emotional state. The embodiments of this invention are described below.

[0132] Integration of data collection and emotion recognition

[0133] The server collects business-related information by crawling data sources on the internet. In addition, the emotion engine uses video, audio, and text data provided by the user through their device to recognize the user's emotional state in real time. This recognition is performed using a comprehensive approach that combines facial expression analysis, voice tone analysis, and text sentiment analysis.

[0134] Emotion-based strategy generation

[0135] In addition to normal data analysis, the server receives emotional information from the emotion engine as input. This allows it to generate negotiation strategies that include stress relief measures, words of encouragement, and tactical advice tailored to the user's emotional state. Machine learning algorithms are used in this process to improve the accuracy of emotion recognition.

[0136] Emotional feedback through user interface

[0137] The device not only presents the generated strategy to the user but also collects real-time responses to the user's emotional changes. This feedback is used in the next strategy generation process, facilitating system personalization. Through an intuitive and user-friendly interface, users can review their emotional state tracking results and receive stress management advice as needed.

[0138] Implementation of specific examples

[0139] For example, consider a situation where a user is feeling pressured while negotiating an important contract. The server analyzes the latest market trend data, and the device's emotion engine determines that the user's stress level is high. In this case, the server generates a strategy that includes encouraging words such as "Take a deep breath and stay calm," and the device presents this information to the user. By following the suggestion, the user can calm down and proceed with the negotiation calmly and effectively.

[0140] Thus, the system according to the present invention utilizes an emotion engine and advanced data analysis technology to provide individually optimized negotiation support to users.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] The server crawls business-related information from multiple data sources on the internet and stores it in a database. Furthermore, the server also receives private and sentiment data from users and prepares it for analysis.

[0144] Step 2:

[0145] The device acquires data on the user's facial expressions and voice in real time and analyzes the user's emotional state using an emotion engine. The results of this analysis are sent to the server as indicators such as stress levels and satisfaction levels.

[0146] Step 3:

[0147] The server integrates crawled business data with user sentiment data obtained from the sentiment engine and performs data analysis using a generative model. This analysis applies algorithms to generate negotiation strategies that take user sentiment into account.

[0148] Step 4:

[0149] Based on the analysis results, the server generates multiple negotiation strategy options. The strategies are tailored to the user's emotional state, and include advice to promote relaxation, especially if the user is experiencing high levels of stress.

[0150] Step 5:

[0151] The server sends the generated strategy proposals to the terminal, which then presents them to the user. Because they are displayed intuitively on the user interface, users can easily select strategies and respond to their emotions.

[0152] Step 6:

[0153] The user proceeds with the actual negotiation based on the presented strategy. The emotions and thoughts experienced during the negotiation are collected as feedback via the device and sent to the server for the purpose of formulating the next strategy.

[0154] Step 7:

[0155] The server analyzes new data in real time and continuously updates its strategies and emotional response approaches. This process continues until the negotiation is concluded, and the system is designed to provide optimal negotiation support throughout.

[0156] (Example 2)

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

[0158] Conventional negotiation support systems fail to consider the user's emotional state and struggle to perform real-time analysis of accumulated market information. Therefore, there is a need to provide negotiation strategies that are optimized for the user and tailored to their specific circumstances.

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

[0160] In this invention, the server includes means for collecting data from information sources, organizing and storing the collected data, means for analyzing the organized data using a generative model and making predictions as a result of the analysis, and means for generating negotiation methods based on the predictions and presenting the generated methods. This makes it possible to provide flexible and effective negotiation strategies that are tailored to the user's emotional state.

[0161] A "source of information" refers to the external or internal resources from which data is obtained.

[0162] "Collecting data" refers to the process of obtaining and storing necessary information from various sources.

[0163] "Organizing and memorizing" means classifying collected data according to its format and content, and then saving it.

[0164] A "generative model" is a mathematical or algorithmic method used to analyze data and generate predictions or insights.

[0165] "Analysis" is the process of evaluating data and extracting knowledge and information that is relevant to a specific purpose.

[0166] "Prediction" is the process of estimating future events based on currently available data.

[0167] "Negotiation methods" refer to the tactics and strategies that should be employed in negotiations.

[0168] "Presentation" refers to the act of informing the user about the method or information used to generate something.

[0169] "Emotion recognition" refers to a technology or method that identifies a user's emotional state and acquires that state as data.

[0170] "Adjusting" means changing the method or result based on the initial settings or conditions.

[0171] A "user interface" is a means or screen that allows a user to interact with a system and visually confirm information.

[0172] "Success rate" is an indicator that evaluates the probability that a proposed method will achieve its objective.

[0173] "Risk level" is an indicator that shows the degree of risk that may arise from implementing a method.

[0174] This invention is a system for providing flexible and effective strategies in business negotiations while considering the emotional state of the user. The server collects business-related data from information sources. This process involves running a wide range of programs for data acquisition, specifically crawling web information using common programming languages ​​and scripts. The collected data is stored in a database and used in subsequent processes.

[0175] The device receives video, audio, and text data provided by the user and analyzes it using an emotion engine. Specifically, a face detection algorithm is used for facial expression analysis, a voice waveform analysis tool for voice analysis, and a natural language processing tool for text sentiment analysis. This allows for real-time evaluation of the user's emotional state from their facial expressions, tone of voice, and messages.

[0176] The server uses a generative AI model to comprehensively analyze accumulated user sentiment information and business data to generate negotiation strategies based on the user's emotional state. Machine learning techniques are applied in this generation process. The strategies include specific word choices and responses for particular situations, which are then appropriately edited to communicate to the user.

[0177] For example, when a user is preparing for a meeting, the device might offer strategies that include advice such as, "It would be a good idea to practice your presentation and approach the meeting calmly." Such strategies are designed to alleviate user stress and anxiety.

[0178] An example of a prompt might be, "Generate appropriate advice based on the user's emotional state on how they should act to prepare for this meeting." This prompt allows the generative AI model to provide strategies to help the user achieve the best possible outcome.

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] The server collects business-related data from various sources. It uses publicly available information on the internet and data obtained from internal databases as input. Using this data, it employs web scraping techniques to acquire important market trends and company information, which is then stored in the database. This provides the material necessary for subsequent analysis.

[0182] Step 2:

[0183] The device acquires video, audio, and text data provided by the user. Inputs include, for example, audio and video data recorded by the user's camera and microphone, as well as manually entered text messages. Based on this, facial recognition software is used to analyze facial expressions, and a speech recognition algorithm is applied to analyze the tone of the voice. Furthermore, natural language processing tools are used to perform sentiment analysis of the text. This process allows for real-time analysis of the user's emotional state.

[0184] Step 3:

[0185] The server integrates emotional state data received from the terminal. The input includes emotional information from facial expressions, voice, and text obtained in the previous step. This information is input into a generating AI model, which performs analysis using machine learning techniques. As a result, insights based on the user's emotional state and business data are obtained.

[0186] Step 4:

[0187] The server generates negotiation strategies from integrated data. Inputs include user-specific data based on emotional states and business information. Using a generative model, it creates strategies that include action suggestions and emotional care methods tailored to specific situations. The output presents the user with effective strategic proposals.

[0188] Step 5:

[0189] The device presents strategies from the server through a user interface. Specifically, it visualizes strategies, including feedback based on emotional states, on the screen in a way that is easy for the user to understand. The user can then adjust their actions based on this information.

[0190] Step 6:

[0191] The user acts based on the strategy presented on the device and provides necessary feedback. The device returns changes in emotional state and the results of strategy execution as input. This allows the server to collect feedback data and use it to improve the system's accuracy in future strategy generation.

[0192] (Application Example 2)

[0193] 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".

[0194] Conventional negotiation support systems lack the ability to provide individualized support tailored to the user's emotional state, which prevents them from achieving maximum effectiveness in negotiations. Furthermore, they are insufficient in updating strategies to reflect real-time changes in the user's emotions, resulting in a lack of flexibility in adapting to changing situations.

[0195] 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.

[0196] In this invention, the server includes means for collecting information from a database, cleaning and storing the collected information, means for analyzing the cleansed information using a generative AI model and inferring trends from the analysis results, means for generating negotiation strategies based on the inferences and outputting the generated strategies, means for analyzing the user's facial expressions and voice and recognizing their emotional state, and means for generating personalized responses based on the recognized emotional state. This makes it possible to provide flexible and effective negotiation strategies that take the user's emotional state into consideration in real time.

[0197] "Methods for collecting, cleansing, and storing information" refers to the process of processing raw data obtained from a database, removing inaccurate or duplicate data, organizing it, and storing it in a format suitable for later analysis.

[0198] "Analysis using generative AI models" refers to a method that utilizes artificial intelligence models to analyze cleansed data and scientifically predict hidden patterns and trends.

[0199] "A means of generating and outputting negotiation strategies" refers to a technology that designs the best action plan for achieving negotiation objectives based on results obtained from data analysis and provides it to the user.

[0200] "Means for analyzing a user's facial expressions and voice to recognize their emotional state" refers to a process that processes the visual and auditory signals emitted by a user as data to identify their emotional responses and psychological state.

[0201] "Means for generating personalized responses" refers to methods for designing optimal responses and actions for a target individual based on their recognized emotional state and individual user information.

[0202] To realize this invention, a system is configured in which a server and a terminal work together. The server first collects business-related information from a database and cleanses the acquired information. Specifically, it removes noise and eliminates duplicate data, then organizes and stores the data. Next, it uses a generative AI model to analyze the cleansed data and predict trends. In the analysis, machine learning frameworks such as TensorFlow and PyTorch are used to extract useful insights from the data.

[0203] Meanwhile, the device acquires the user's facial expressions and voice data in real time to recognize their emotional state. This is achieved by collecting data through the camera and microphone and identifying emotions using machine learning algorithms. An automated analysis system evaluates the user's psychological state. This recognition result is sent to a server and input into the generated negotiation strategy.

[0204] Based on the user's emotional state, the server generates a user-optimized response and presents it to the user through the terminal. This process involves dynamically generated dialogue using Node.js and Dialogflow. The user interface also collects emotional feedback that helps in generating future strategies, thereby promoting system personalization.

[0205] As a concrete example, when a user returns home tired from work, the robot gently greets them with, "Welcome back. How was your day?" and suggests playing their preferred relaxing music. An example of a prompt message is, "Please recognize the user's emotions from their facial expression and tone of voice, and come up with a suggestion to help them relax." This system enables negotiation support that flexibly responds to the user's emotional changes.

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] The server collects business-related information from a database. It uses raw data crawled from the internet as input and produces cleaned data (de-noised and de-duplicated) as output. This data is then organized for later analysis. Specifically, a crawler program periodically collects new data from the web.

[0209] Step 2:

[0210] The server analyzes the cleansed data using a generative AI model. Using the cleansed data as input, it obtains analysis results for predicting trends as output. The generative AI model (e.g., using TensorFlow) executes a deep learning algorithm on the dataset to extract patterns and latent trends. In its specific operation, the model activates a neural network using trained weights to perform inference.

[0211] Step 3:

[0212] The device collects the user's facial expressions and voice data to recognize their emotional state in real time. It uses visual and audio data acquired through the camera and microphone as input, and outputs a report of the recognized emotional state. Data processing involves analyzing facial expressions with image processing algorithms and evaluating tone with a voice analysis program. Specifically, this analysis is performed using machine learning models.

[0213] Step 4:

[0214] The server generates the next negotiation strategy based on the user's emotional state. Using analysis results and emotional state reports as input, the optimized negotiation strategy is presented as output. Data processing involves inputting analysis results into a support system and executing a strategy generation algorithm tailored to the conditions. Specifically, Node.js and Dialogflow are used to dynamically construct the dialogue strategy.

[0215] Step 5:

[0216] The terminal presents the generated negotiation strategy to the user and collects emotional feedback in real time. It uses strategies sent from the server as input and collects user feedback information as output. Operationally, it provides visual and auditory feedback functions on the interface and continuously monitors the user's evolving emotional state. Specifically, it sends the collected feedback information to the server for continuous strategy improvement.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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".

[0233] This invention is a system that supports effective strategy formulation in business negotiations and streamlines the entire process by utilizing advanced data analysis techniques and generative models. Specific embodiments are described below.

[0234] Data collection and cleansing

[0235] The server crawls business-related information from numerous data sources accessible via the internet. This process includes data from public databases, industry reports, and company press releases. The collected information is cleansed on the server, removing unnecessary and duplicate data, and organized into a format suitable for subsequent analysis.

[0236] Data analysis and strategy generation

[0237] Based on the cleansed data, the server uses a generative model to analyze market trends and competitive landscapes. The analysis reveals predictions of competitor behavior and market trends, and based on this information, multiple negotiation strategies are generated. Each strategy is evaluated for its expected success rate and potential risk level, and the strategy deemed most effective is proposed to the user.

[0238] Strategic presentation through user interface

[0239] The terminal presents the optimal strategy, transmitted from the server, to the user through a user interface. This interface is visually intuitive, allowing the user to quickly grasp the details of the proposed strategy. The information displayed here is highly reliable because it is based on crawled data.

[0240] Real-time advice and strategy updates

[0241] As users progress through negotiations, new data is collected, and the server analyzes this data, updating the strategy in real time. This strategy update takes into account new market trends and the latest information on the other company, and is immediately presented to the user. This allows users to flexibly respond to changing negotiation situations.

[0242] Implementation of specific examples

[0243] For example, suppose a user is negotiating a contract with a supplier for a new product. The server analyzes relevant market news and industry trends and provides an analysis showing that the new product is advantageous compared to competitors' products. Based on these results, the terminal recommends to the user a strategy that emphasizes the product's technical features rather than its price advantage. This strategy can be effectively used by the user during negotiations to lead to improved terms of the deal.

[0244] Thus, the present invention provides data-driven strategies for business negotiations and supports users in responding promptly to changing market environments.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] The server crawls business-related information from public databases and news sites on the internet. A crawling algorithm is used to retrieve the information, and the scope of data collection is defined based on keywords or specific URLs.

[0248] Step 2:

[0249] The collected data is cleansed on the server. The server performs a process to detect and remove duplicate data, and further performs noise filtering to extract useful data. This results in data in a format suitable for analysis.

[0250] Step 3:

[0251] The server uses a generative model to analyze the cleansed data. This process employs data mining techniques to identify past trends and patterns and predict market movements. The analysis results provide predictions for the target company's actions and market changes.

[0252] Step 4:

[0253] Based on the analysis results, the server generates multiple negotiation strategies. The server evaluates the success rate and risk level of each generated strategy and selects the optimal strategy for the user.

[0254] Step 5:

[0255] The selected strategy is sent from the server to the terminal, which then presents the strategy to the user through a user interface. The presented strategy is visually organized for easy understanding, allowing the user to review the details of each strategy.

[0256] Step 6:

[0257] The user proceeds with actual negotiations based on the proposed strategy, and inputs the information obtained along the way into the system. This transmits on-site feedback to the server.

[0258] Step 7:

[0259] The server reanalyzes the strategy in real time based on user feedback and new data, and adjusts it if necessary. The adjusted strategy is then sent back to the terminal and presented to the user.

[0260] Step 8:

[0261] This process is repeated throughout the negotiation process and is designed to increase overall efficiency and improve the user's chances of negotiation success.

[0262] (Example 1)

[0263] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0264] In business negotiations, there is a need for systems that can quickly formulate efficient and effective strategies and flexibly respond to changing market environments. Furthermore, in today's information-saturated world, collecting and analyzing reliable information is becoming increasingly complex, and there is a lack of technology that automates this process in a user-friendly manner. Moreover, considerations for privacy and security are also crucial issues.

[0265] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0266] In this invention, the server includes means for automatically acquiring information from information sources, organizing and storing the acquired information, means for analyzing the organized information using learned techniques and predicting future trends as a result of the analysis, and means for generating action guidelines based on the predictions and outputting the generated guidelines. This makes it possible to efficiently collect information, quickly formulate strategies based on analysis results, and respond in real time.

[0267] A "source of information" is a collection of data, such as databases, reports, and releases, that are accessed to obtain the necessary information.

[0268] "Automatically acquiring information" refers to the process of collecting information using a program without manual intervention.

[0269] "Organizing and accumulating" means converting acquired information into a consistent format and structure, and saving it in a way that facilitates subsequent processing and retrieval.

[0270] "Pre-trained techniques" refer to methods that utilize models trained on existing datasets to analyze new data.

[0271] "Analysis" is the process of understanding the characteristics, trends, and relationships of collected information and data.

[0272] "Predicting future trends" means looking ahead to future developments and events based on current and past data.

[0273] "Generating action guidelines" means creating the optimal action strategy to take in a specific situation, based on the analyzed information.

[0274] "Outputting" means displaying or transmitting generated information or results in a format usable by humans or other systems.

[0275] This invention is a system for automating and streamlining strategy formulation in business negotiations. Specific embodiments of the invention are described below.

[0276] The server automatically retrieves information from its sources. In this process, the server collects information from databases, reports, and press releases on the internet via a program. This information retrieval is performed efficiently by using Python libraries for data crawling.

[0277] The collected information is organized on the server and converted into a format suitable for subsequent analysis. This involves using Pandas and NumPy for data frame manipulation and cleansing. The server then uses pre-trained techniques to perform detailed analysis based on this organized information. Generative AI models such as TensorFlow and PyTorch are used for this analysis process.

[0278] Based on the analysis results, the server predicts future trends and generates multiple action plans. This allows users to select the optimal strategy based on different business scenarios. Specifically, the action plans are provided through a visual display on the user's terminal. This user interface presents information visually in an easy-to-understand manner, enabling users to make quick decisions.

[0279] When new information is obtained while the user is progressing with the negotiation, the server analyzes the data in real time and updates the action guidelines. With this function, the user always has the latest information and can adapt to the dynamically changing negotiation situation.

[0280] As a specific example, consider the case where a user is exploring a strategy in a highly competitive market for a new product. The server analyzes the market data and proposes that highlighting the technical features of the new product is an effective strategy for gaining a competitive advantage. This strategy is visualized on the user's terminal, enabling rapid strategic adjustments.

[0281] As an example of a prompt sentence, an instruction such as "Re-evaluate the optimal negotiation strategy based on the new market trends" can be considered. This enables the user to make effective decisions even in a changing business environment.

[0282] The flow of the specific process in Example 1 will be described using FIG. 11.

[0283] Step 1:

[0284] The server automatically acquires business-related information from information sources. The information to be acquired includes databases, reports, press releases, etc. Crawling processing is performed using Python libraries and temporarily stored in storage as raw data. The input is the data acquired from the information source, and the output is the raw acquired data.

[0285] Step 2:

[0286] The server sorts and cleans the acquired data. Unnecessary information and duplicate data in the data are removed and converted into a format suitable for analysis. Specifically, the data is formatted using the Pandas library, and outlier correction is performed using NumPy. The input is the raw acquired data, and the output is the cleansed and formatted data.

[0287] Step 3:

[0288] The server analyzes cleansed data to predict future trends. Generative AI models are used to understand market trends and competitive landscapes within the data. Predictive data is generated as analysis results through model processing using TensorFlow and PyTorch. Input is well-formed data, and output is the prediction and analysis results.

[0289] Step 4:

[0290] The server generates strategies based on prediction results. It devises multiple negotiation strategies and evaluates the likelihood of success and potential risks of each. It analyzes the strategies using statistical models and simulations. The input is the analysis results, and the output is the set of generated strategies.

[0291] Step 5:

[0292] The terminal presents the strategy, transmitted from the server, to the user through a user interface. The strategy information is displayed visually and provided in a format that is easy for the user to quickly understand. For example, infographics and charts are used to represent the key points of the strategy. The input is the generated strategy, and the output is the visualized strategy information.

[0293] Step 6:

[0294] As new data is generated during the user's negotiation process, the server analyzes that data in real time and updates the strategy. The updated strategy is immediately presented to the user. The strategy is re-evaluated based on new market trends and competitive situations. The input is new negotiation data, and the output is updated strategy information.

[0295] (Application Example 1)

[0296] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0297] Business negotiations, particularly those concerning the introduction of new technologies and fees in electronic payments, require rapid and effective strategy development. In today's rapidly changing market environment, where information is vast and trends are constantly evolving, formulating and updating appropriate and flexible negotiation strategies in a timely manner is challenging. This can lead to inefficient business negotiations and missed opportunities.

[0298] 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.

[0299] In this invention, the server includes means for acquiring data from information sources, organizing and recording the acquired data, means for analyzing the organized data using a generative model and inferring trends as a result of the analysis, and means for generating policies based on the inferences and displaying the generated policies. This enables the provision of optimal negotiation policies in response to new market information in real time and allows for rapid response even when the business environment changes.

[0300] A "source of information" is a collection of data, such as public databases, industry reports, and company press releases, that are accessed to obtain data.

[0301] A "generative model" is a machine learning algorithm that analyzes large amounts of data to generate useful trends and insights.

[0302] "Organization" is the process of removing unnecessary information and duplicates from acquired data, and preparing the data to facilitate analysis.

[0303] "To infer" means to predict market trends and corporate behavior based on the results of an analysis.

[0304] "Generating a policy" means creating the optimal strategy or action plan based on inferred information.

[0305] "To present for negotiation support" means to provide information and strategies useful for users when conducting business negotiations regarding payments.

[0306] The system that realizes this application example is composed of a server, a terminal, and a user interface. First, the server automatically acquires the necessary data from the information source and makes it in an organized state through the data cleansing process. In data cleansing, duplicate data and noise are removed, and preparations for analysis using a generative model are made. For this analysis, machine learning frameworks such as TensorFlow and PyTorch are used to accurately infer market trends and corporate behaviors from the collected data.

[0307] Next, based on the analyzed data, the server generates an optimal negotiation policy. In this process, the Python programming language is used to set an action plan suitable for a specific negotiation situation. The generated policy is sent to the terminal via an intuitive user interface. This interface is developed using React Native and provides a visually excellent display that allows users to easily understand and take action.

[0308] Users can always obtain the latest negotiation information through this interface. For negotiation support in electronic payments, it is characterized by the ability to update the policy in real time in response to market changes. As a specific example, when considering the introduction of a new QR code payment function, the application analyzes the trends of competing companies and market trends and presents a marketing strategy for success.

[0309] As an example of the prompt sentence, it is advisable to use "Analyze the following data list regarding the QR code payment function, identify the advantages compared to competing companies, and create a specific proposal."

[0310] The flow of the specific process in Application Example 1 will be described using Figure 12.

[0311] Step 1:

[0312] The server retrieves business-related data from information sources. The input is websites or databases as information sources, and the output is the retrieved raw data. In this process, the server uses web crawlers and APIs to collect data in real time.

[0313] Step 2:

[0314] The server cleanses and organizes the acquired data. The input is the raw data obtained in step 1, and the output is a clean dataset. This process involves removing duplicate data and filtering out noise. Specifically, it standardizes the data using regular expressions and statistical tools.

[0315] Step 3:

[0316] The server analyzes cleansed data using a generative model. The input is a clean dataset, and the output is inferential information about market trends and competitor behavior. As part of the data processing, machine learning algorithms are applied to create a predictive model.

[0317] Step 4:

[0318] The server generates negotiation strategies based on the inferred information. The input is the inferred information from step 3, and the output is the optimal strategy specific to each negotiation. As a data calculation, the results of the predictive model are evaluated, and a concrete strategy is constructed using the policy decision logic.

[0319] Step 5:

[0320] The terminal visually presents the generated negotiation strategy to the user. The input is the optimal strategy from the server, and the output is the information displayed on the user interface. Specifically, a highly responsive user interface is used to visually decompose the strategy.

[0321] Step 6:

[0322] The user conducts business negotiations by referring to the provided negotiation strategies. Inputs are information displayed from the terminal, and outputs are the user's actions and negotiation results. In this step, the user uses the proposed strategies to conduct more effective negotiations.

[0323] Step 7:

[0324] The server acquires and analyzes new data in real time and updates its policies. The input is newly acquired market data, and the output is the updated negotiation policy. Specifically, it re-analyzes the acquired data and makes policy adjustments that take into account the latest market trends.

[0325] 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.

[0326] This invention is a system that combines an emotion engine with a conventional business negotiation support system to provide a flexible and effective negotiation strategy that takes into account the user's emotional state. The embodiments of this invention are described below.

[0327] Integration of data collection and emotion recognition

[0328] The server collects business-related information by crawling data sources on the internet. In addition, the emotion engine uses video, audio, and text data provided by the user through their device to recognize the user's emotional state in real time. This recognition is performed using a comprehensive approach that combines facial expression analysis, voice tone analysis, and text sentiment analysis.

[0329] Emotion-based strategy generation

[0330] In addition to normal data analysis, the server receives emotional information from the emotion engine as input. This allows it to generate negotiation strategies that include stress relief measures, words of encouragement, and tactical advice tailored to the user's emotional state. Machine learning algorithms are used in this process to improve the accuracy of emotion recognition.

[0331] Emotional feedback through user interface

[0332] The device not only presents the generated strategy to the user but also collects real-time responses to the user's emotional changes. This feedback is used in the next strategy generation process, facilitating system personalization. Through an intuitive and user-friendly interface, users can review their emotional state tracking results and receive stress management advice as needed.

[0333] Implementation of specific examples

[0334] For example, consider a situation where a user is feeling pressured while negotiating an important contract. The server analyzes the latest market trend data, and the device's emotion engine determines that the user's stress level is high. In this case, the server generates a strategy that includes encouraging words such as "Take a deep breath and stay calm," and the device presents this information to the user. By following the suggestion, the user can calm down and proceed with the negotiation calmly and effectively.

[0335] Thus, the system according to the present invention utilizes an emotion engine and advanced data analysis technology to provide individually optimized negotiation support to users.

[0336] The following describes the processing flow.

[0337] Step 1:

[0338] The server crawls business-related information from multiple data sources on the internet and stores it in a database. Furthermore, the server also receives private and sentiment data from users and prepares it for analysis.

[0339] Step 2:

[0340] The device acquires data on the user's facial expressions and voice in real time and analyzes the user's emotional state using an emotion engine. The results of this analysis are sent to the server as indicators such as stress levels and satisfaction levels.

[0341] Step 3:

[0342] The server integrates crawled business data with user sentiment data obtained from the sentiment engine and performs data analysis using a generative model. This analysis applies algorithms to generate negotiation strategies that take user sentiment into account.

[0343] Step 4:

[0344] Based on the analysis results, the server generates multiple negotiation strategy options. The strategies are tailored to the user's emotional state, and include advice to promote relaxation, especially if the user is experiencing high levels of stress.

[0345] Step 5:

[0346] The server sends the generated strategy proposals to the terminal, which then presents them to the user. Because they are displayed intuitively on the user interface, users can easily select strategies and respond to their emotions.

[0347] Step 6:

[0348] The user proceeds with the actual negotiation based on the presented strategy. The emotions and thoughts experienced during the negotiation are collected as feedback via the device and sent to the server for the purpose of formulating the next strategy.

[0349] Step 7:

[0350] The server analyzes new data in real time and continuously updates its strategies and emotional response approaches. This process continues until the negotiation is concluded, and the system is designed to provide optimal negotiation support throughout.

[0351] (Example 2)

[0352] 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".

[0353] Conventional negotiation support systems fail to consider the user's emotional state and struggle to perform real-time analysis of accumulated market information. Therefore, there is a need to provide negotiation strategies that are optimized for the user and tailored to their specific circumstances.

[0354] 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.

[0355] In this invention, the server includes means for collecting data from information sources, organizing and storing the collected data, means for analyzing the organized data using a generative model and making predictions as a result of the analysis, and means for generating negotiation methods based on the predictions and presenting the generated methods. This makes it possible to provide flexible and effective negotiation strategies that are tailored to the user's emotional state.

[0356] A "source of information" refers to the external or internal resources from which data is obtained.

[0357] "Collecting data" refers to the process of obtaining and storing necessary information from various sources.

[0358] "Organizing and memorizing" means classifying collected data according to its format and content, and then saving it.

[0359] A "generative model" is a mathematical or algorithmic method used to analyze data and generate predictions or insights.

[0360] "Analysis" is the process of evaluating data and extracting knowledge and information that is relevant to a specific purpose.

[0361] "Prediction" is the process of estimating future events based on currently available data.

[0362] "Negotiation methods" refer to the tactics and strategies that should be employed in negotiations.

[0363] "Presentation" refers to the act of informing the user about the method or information used to generate something.

[0364] "Emotion recognition" refers to a technology or method that identifies a user's emotional state and acquires that state as data.

[0365] "Adjusting" means changing the method or result based on the initial settings or conditions.

[0366] A "user interface" is a means or screen that allows a user to interact with a system and visually confirm information.

[0367] "Success rate" is an indicator that evaluates the probability that a proposed method will achieve its objective.

[0368] "Risk level" is an indicator that shows the degree of risk that may arise from implementing a method.

[0369] This invention is a system for providing flexible and effective strategies in business negotiations while considering the emotional state of the user. The server collects business-related data from information sources. This process involves running a wide range of programs for data acquisition, specifically crawling web information using common programming languages ​​and scripts. The collected data is stored in a database and used in subsequent processes.

[0370] The device receives video, audio, and text data provided by the user and analyzes it using an emotion engine. Specifically, a face detection algorithm is used for facial expression analysis, a voice waveform analysis tool for voice analysis, and a natural language processing tool for text sentiment analysis. This allows for real-time evaluation of the user's emotional state from their facial expressions, tone of voice, and messages.

[0371] The server uses a generative AI model to comprehensively analyze accumulated user sentiment information and business data to generate negotiation strategies based on the user's emotional state. Machine learning techniques are applied in this generation process. The strategies include specific word choices and responses for particular situations, which are then appropriately edited to communicate to the user.

[0372] For example, when a user is preparing for a meeting, the device might offer strategies that include advice such as, "It would be a good idea to practice your presentation and approach the meeting calmly." Such strategies are designed to alleviate user stress and anxiety.

[0373] An example of a prompt might be, "Generate appropriate advice based on the user's emotional state on how they should act to prepare for this meeting." This prompt allows the generative AI model to provide strategies to help the user achieve the best possible outcome.

[0374] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0375] Step 1:

[0376] The server collects business-related data from various sources. It uses publicly available information on the internet and data obtained from internal databases as input. Using this data, it employs web scraping techniques to acquire important market trends and company information, which is then stored in the database. This provides the material necessary for subsequent analysis.

[0377] Step 2:

[0378] The device acquires video, audio, and text data provided by the user. Inputs include, for example, audio and video data recorded by the user's camera and microphone, as well as manually entered text messages. Based on this, facial recognition software is used to analyze facial expressions, and a speech recognition algorithm is applied to analyze the tone of the voice. Furthermore, natural language processing tools are used to perform sentiment analysis of the text. This process allows for real-time analysis of the user's emotional state.

[0379] Step 3:

[0380] The server integrates emotional state data received from the terminal. The input includes emotional information from facial expressions, voice, and text obtained in the previous step. This information is input into a generating AI model, which performs analysis using machine learning techniques. As a result, insights based on the user's emotional state and business data are obtained.

[0381] Step 4:

[0382] The server generates negotiation strategies from integrated data. Inputs include user-specific data based on emotional states and business information. Using a generative model, it creates strategies that include action suggestions and emotional care methods tailored to specific situations. The output presents the user with effective strategic proposals.

[0383] Step 5:

[0384] The device presents strategies from the server through a user interface. Specifically, it visualizes strategies, including feedback based on emotional states, on the screen in a way that is easy for the user to understand. The user can then adjust their actions based on this information.

[0385] Step 6:

[0386] The user acts based on the strategy presented on the device and provides necessary feedback. The device returns changes in emotional state and the results of strategy execution as input. This allows the server to collect feedback data and use it to improve the system's accuracy in future strategy generation.

[0387] (Application Example 2)

[0388] 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."

[0389] Conventional negotiation support systems lack the ability to provide individualized support tailored to the user's emotional state, which prevents them from achieving maximum effectiveness in negotiations. Furthermore, they are insufficient in updating strategies to reflect real-time changes in the user's emotions, resulting in a lack of flexibility in adapting to changing situations.

[0390] 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.

[0391] In this invention, the server includes means for collecting information from a database, cleaning and storing the collected information, means for analyzing the cleansed information using a generative AI model and inferring trends from the analysis results, means for generating negotiation strategies based on the inferences and outputting the generated strategies, means for analyzing the user's facial expressions and voice and recognizing their emotional state, and means for generating personalized responses based on the recognized emotional state. This makes it possible to provide flexible and effective negotiation strategies that take the user's emotional state into consideration in real time.

[0392] "Methods for collecting, cleansing, and storing information" refers to the process of processing raw data obtained from a database, removing inaccurate or duplicate data, organizing it, and storing it in a format suitable for later analysis.

[0393] "Analysis using generative AI models" refers to a method that utilizes artificial intelligence models to analyze cleansed data and scientifically predict hidden patterns and trends.

[0394] "A means of generating and outputting negotiation strategies" refers to a technology that designs the best action plan for achieving negotiation objectives based on results obtained from data analysis and provides it to the user.

[0395] "Means for analyzing a user's facial expressions and voice to recognize their emotional state" refers to a process that processes the visual and auditory signals emitted by a user as data to identify their emotional responses and psychological state.

[0396] "Means for generating personalized responses" refers to methods for designing optimal responses and actions for a target individual based on their recognized emotional state and individual user information.

[0397] To realize this invention, a system is configured in which a server and a terminal work together. The server first collects business-related information from a database and cleanses the acquired information. Specifically, it removes noise and eliminates duplicate data, then organizes and stores the data. Next, it uses a generative AI model to analyze the cleansed data and predict trends. In the analysis, machine learning frameworks such as TensorFlow and PyTorch are used to extract useful insights from the data.

[0398] Meanwhile, the device acquires the user's facial expressions and voice data in real time to recognize their emotional state. This is achieved by collecting data through the camera and microphone and identifying emotions using machine learning algorithms. An automated analysis system evaluates the user's psychological state. This recognition result is sent to a server and input into the generated negotiation strategy.

[0399] Based on the user's emotional state, the server generates a user-optimized response and presents it to the user through the terminal. This process involves dynamically generated dialogue using Node.js and Dialogflow. The user interface also collects emotional feedback that helps in generating future strategies, thereby promoting system personalization.

[0400] As a concrete example, when a user returns home tired from work, the robot gently greets them with, "Welcome back. How was your day?" and suggests playing their preferred relaxing music. An example of a prompt message is, "Please recognize the user's emotions from their facial expression and tone of voice, and come up with a suggestion to help them relax." This system enables negotiation support that flexibly responds to the user's emotional changes.

[0401] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0402] Step 1:

[0403] The server collects business-related information from a database. It uses raw data crawled from the internet as input and produces cleaned data (de-noised and de-duplicated) as output. This data is then organized for later analysis. Specifically, a crawler program periodically collects new data from the web.

[0404] Step 2:

[0405] The server analyzes the cleansed data using a generative AI model. Using the cleansed data as input, it obtains analysis results for predicting trends as output. The generative AI model (e.g., using TensorFlow) executes a deep learning algorithm on the dataset to extract patterns and latent trends. In its specific operation, the model activates a neural network using trained weights to perform inference.

[0406] Step 3:

[0407] The device collects the user's facial expressions and voice data to recognize their emotional state in real time. It uses visual and audio data acquired through the camera and microphone as input, and outputs a report of the recognized emotional state. Data processing involves analyzing facial expressions with image processing algorithms and evaluating tone with a voice analysis program. Specifically, this analysis is performed using machine learning models.

[0408] Step 4:

[0409] The server generates the next negotiation strategy based on the user's emotional state. Using analysis results and emotional state reports as input, the optimized negotiation strategy is presented as output. Data processing involves inputting analysis results into a support system and executing a strategy generation algorithm tailored to the conditions. Specifically, Node.js and Dialogflow are used to dynamically construct the dialogue strategy.

[0410] Step 5:

[0411] The terminal presents the generated negotiation strategy to the user and collects emotional feedback in real time. It uses strategies sent from the server as input and collects user feedback information as output. Operationally, it provides visual and auditory feedback functions on the interface and continuously monitors the user's evolving emotional state. Specifically, it sends the collected feedback information to the server for continuous strategy improvement.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] [Third Embodiment]

[0416] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0417] 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.

[0418] 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).

[0419] 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.

[0420] 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.

[0421] 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).

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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".

[0428] This invention is a system that supports effective strategy formulation in business negotiations and streamlines the entire process by utilizing advanced data analysis techniques and generative models. Specific embodiments are described below.

[0429] Data collection and cleansing

[0430] The server crawls business-related information from numerous data sources accessible via the internet. This process includes data from public databases, industry reports, and company press releases. The collected information is cleansed on the server, removing unnecessary and duplicate data, and organized into a format suitable for subsequent analysis.

[0431] Data analysis and strategy generation

[0432] Based on the cleansed data, the server uses a generative model to analyze market trends and competitive landscapes. The analysis reveals predictions of competitor behavior and market trends, and based on this information, multiple negotiation strategies are generated. Each strategy is evaluated for its expected success rate and potential risk level, and the strategy deemed most effective is proposed to the user.

[0433] Strategic presentation through user interface

[0434] The terminal presents the optimal strategy, transmitted from the server, to the user through a user interface. This interface is visually intuitive, allowing the user to quickly grasp the details of the proposed strategy. The information displayed here is highly reliable because it is based on crawled data.

[0435] Real-time advice and strategy updates

[0436] As users progress through negotiations, new data is collected, and the server analyzes this data, updating the strategy in real time. This strategy update takes into account new market trends and the latest information on the other company, and is immediately presented to the user. This allows users to flexibly respond to changing negotiation situations.

[0437] Implementation of specific examples

[0438] For example, suppose a user is negotiating a contract with a supplier for a new product. The server analyzes relevant market news and industry trends and provides an analysis showing that the new product is advantageous compared to competitors' products. Based on these results, the terminal recommends to the user a strategy that emphasizes the product's technical features rather than its price advantage. This strategy can be effectively used by the user during negotiations to lead to improved terms of the deal.

[0439] Thus, the present invention provides data-driven strategies for business negotiations and supports users in responding promptly to changing market environments.

[0440] The following describes the processing flow.

[0441] Step 1:

[0442] The server crawls business-related information from public databases and news sites on the internet. A crawling algorithm is used to retrieve the information, and the scope of data collection is defined based on keywords or specific URLs.

[0443] Step 2:

[0444] The collected data is cleansed on the server. The server performs a process to detect and remove duplicate data, and further performs noise filtering to extract useful data. This results in data in a format suitable for analysis.

[0445] Step 3:

[0446] The server uses a generative model to analyze the cleansed data. This process employs data mining techniques to identify past trends and patterns and predict market movements. The analysis results provide predictions for the target company's actions and market changes.

[0447] Step 4:

[0448] Based on the analysis results, the server generates multiple negotiation strategies. The server evaluates the success rate and risk level of each generated strategy and selects the optimal strategy for the user.

[0449] Step 5:

[0450] The selected strategy is sent from the server to the terminal, which then presents the strategy to the user through a user interface. The presented strategy is visually organized for easy understanding, allowing the user to review the details of each strategy.

[0451] Step 6:

[0452] The user proceeds with actual negotiations based on the proposed strategy, and inputs the information obtained along the way into the system. This transmits on-site feedback to the server.

[0453] Step 7:

[0454] The server reanalyzes the strategy in real time based on user feedback and new data, and adjusts it if necessary. The adjusted strategy is then sent back to the terminal and presented to the user.

[0455] Step 8:

[0456] This process is repeated throughout the negotiation process and is designed to increase overall efficiency and improve the user's chances of negotiation success.

[0457] (Example 1)

[0458] 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."

[0459] In business negotiations, there is a need for systems that can quickly formulate efficient and effective strategies and flexibly respond to changing market environments. Furthermore, in today's information-saturated world, collecting and analyzing reliable information is becoming increasingly complex, and there is a lack of technology that automates this process in a user-friendly manner. Moreover, considerations for privacy and security are also crucial issues.

[0460] 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.

[0461] In this invention, the server includes means for automatically acquiring information from information sources, organizing and storing the acquired information, means for analyzing the organized information using learned techniques and predicting future trends as a result of the analysis, and means for generating action guidelines based on the predictions and outputting the generated guidelines. This makes it possible to efficiently collect information, quickly formulate strategies based on analysis results, and respond in real time.

[0462] A "source of information" is a collection of data, such as databases, reports, and releases, that are accessed to obtain the necessary information.

[0463] "Automatically acquiring information" refers to the process of collecting information using a program without manual intervention.

[0464] "Organizing and accumulating" means converting acquired information into a consistent format and structure, and saving it in a way that facilitates subsequent processing and retrieval.

[0465] "Pre-trained techniques" refer to methods that utilize models trained on existing datasets to analyze new data.

[0466] "Analysis" is the process of understanding the characteristics, trends, and relationships of collected information and data.

[0467] "Predicting future trends" means looking ahead to future developments and events based on current and past data.

[0468] "Generating action guidelines" means creating the optimal action strategy to take in a specific situation, based on the analyzed information.

[0469] "Outputting" means displaying or transmitting generated information or results in a format usable by humans or other systems.

[0470] This invention is a system for automating and streamlining strategy formulation in business negotiations. Specific embodiments of the invention are described below.

[0471] The server automatically retrieves information from its sources. In this process, the server collects information from databases, reports, and press releases on the internet via a program. This information retrieval is performed efficiently by using Python libraries for data crawling.

[0472] The collected information is organized on the server and converted into a format suitable for subsequent analysis. This involves using Pandas and NumPy for data frame manipulation and cleansing. The server then uses pre-trained techniques to perform detailed analysis based on this organized information. Generative AI models such as TensorFlow and PyTorch are used for this analysis process.

[0473] Based on the analysis results, the server predicts future trends and generates multiple action plans. This allows users to select the optimal strategy based on different business scenarios. Specifically, the action plans are provided through a visual display on the user's terminal. This user interface presents information visually in an easy-to-understand manner, enabling users to make quick decisions.

[0474] As users progress through negotiations, the server analyzes the data in real time and updates its course of action as new information becomes available. This feature ensures users always have the latest information and can adapt to dynamically changing negotiation situations.

[0475] As a concrete example, consider a scenario where a user is exploring strategies for a new product in a highly competitive market. The server analyzes market data and suggests that highlighting the new product's technical features is an effective strategy for gaining a competitive advantage. This strategy is visualized on the user's terminal, enabling rapid strategic adjustments.

[0476] An example of a prompt message might be, "Re-evaluate the optimal negotiation strategy based on new market trends." This allows users to make effective decisions even in a changing business environment.

[0477] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0478] Step 1:

[0479] The server automatically retrieves business-related information from information sources. This information includes databases, reports, and press releases. A Python library is used to perform the crawling process, and the raw data is temporarily stored in storage. The input is the data retrieved from the information sources, and the output is the raw retrieved data.

[0480] Step 2:

[0481] The server organizes and cleanses the acquired data. It removes unnecessary information and duplicate data and converts it into a format suitable for analysis. Specifically, it uses the Pandas library to format the data and NumPy to correct for outliers. The input is the raw acquired data, and the output is cleansed, well-formed data.

[0482] Step 3:

[0483] The server analyzes cleansed data to predict future trends. Generative AI models are used to understand market trends and competitive landscapes within the data. Predictive data is generated as analysis results through model processing using TensorFlow and PyTorch. Input is well-formed data, and output is the prediction and analysis results.

[0484] Step 4:

[0485] The server generates strategies based on prediction results. It devises multiple negotiation strategies and evaluates the likelihood of success and potential risks of each. It analyzes the strategies using statistical models and simulations. The input is the analysis results, and the output is the set of generated strategies.

[0486] Step 5:

[0487] The terminal presents the strategy, transmitted from the server, to the user through a user interface. The strategy information is displayed visually and provided in a format that is easy for the user to quickly understand. For example, infographics and charts are used to represent the key points of the strategy. The input is the generated strategy, and the output is the visualized strategy information.

[0488] Step 6:

[0489] As new data is generated during the user's negotiation process, the server analyzes that data in real time and updates the strategy. The updated strategy is immediately presented to the user. The strategy is re-evaluated based on new market trends and competitive situations. The input is new negotiation data, and the output is updated strategy information.

[0490] (Application Example 1)

[0491] 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."

[0492] Business negotiations, particularly those concerning the introduction of new technologies and fees in electronic payments, require rapid and effective strategy development. In today's rapidly changing market environment, where information is vast and trends are constantly evolving, formulating and updating appropriate and flexible negotiation strategies in a timely manner is challenging. This can lead to inefficient business negotiations and missed opportunities.

[0493] 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.

[0494] In this invention, the server includes means for acquiring data from information sources, organizing and recording the acquired data, means for analyzing the organized data using a generative model and inferring trends as a result of the analysis, and means for generating policies based on the inferences and displaying the generated policies. This enables the provision of optimal negotiation policies in response to new market information in real time and allows for rapid response even when the business environment changes.

[0495] A "source of information" is a collection of data, such as public databases, industry reports, and company press releases, that are accessed to obtain data.

[0496] A "generative model" is a machine learning algorithm that analyzes large amounts of data to generate useful trends and insights.

[0497] "Organization" is the process of removing unnecessary information and duplicates from acquired data, and preparing the data to facilitate analysis.

[0498] "To infer" means to predict market trends and corporate behavior based on the results of an analysis.

[0499] "Generating a policy" means creating the optimal strategy or action plan based on inferred information.

[0500] "To provide support for negotiations" means to offer users useful information and strategies when conducting business negotiations regarding payments.

[0501] The system that implements this application consists of a server, a terminal, and a user interface. The server first automatically retrieves the necessary data from the information source and organizes it through a data cleansing process. Data cleansing removes duplicate data and noise, preparing it for analysis by a generative model. This analysis uses machine learning frameworks such as TensorFlow and PyTorch to accurately predict market trends and company behavior from the collected data.

[0502] Next, the server generates the optimal negotiation strategy based on the analyzed data. This process utilizes the Python programming language to set up an action plan suitable for the specific negotiation situation. The generated strategy is sent to the terminal via an intuitive user interface. This interface is developed using React Native and provides a visually appealing display that makes it easy for users to understand and act upon.

[0503] Users can always obtain the latest negotiation information through this interface. A key feature is its ability to update policies in real time in response to market changes, supporting negotiations in electronic payments. For example, when considering the introduction of a new QR code payment function, the application analyzes competitor activities and market trends, and presents a marketing strategy for success.

[0504] A good example of a prompt would be: "Analyze the following data list regarding QR code payment functionality, identify the advantages compared to competitors, and create a detailed proposal."

[0505] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0506] Step 1:

[0507] The server retrieves business-related data from information sources. The input is websites or databases as information sources, and the output is the retrieved raw data. In this process, the server uses web crawlers and APIs to collect data in real time.

[0508] Step 2:

[0509] The server cleanses and organizes the acquired data. The input is the raw data obtained in step 1, and the output is a clean dataset. This process involves removing duplicate data and filtering out noise. Specifically, it standardizes the data using regular expressions and statistical tools.

[0510] Step 3:

[0511] The server analyzes cleansed data using a generative model. The input is a clean dataset, and the output is inferential information about market trends and competitor behavior. As part of the data processing, machine learning algorithms are applied to create a predictive model.

[0512] Step 4:

[0513] The server generates negotiation strategies based on the inferred information. The input is the inferred information from step 3, and the output is the optimal strategy specific to each negotiation. As a data calculation, the results of the predictive model are evaluated, and a concrete strategy is constructed using the policy decision logic.

[0514] Step 5:

[0515] The terminal visually presents the generated negotiation strategy to the user. The input is the optimal strategy from the server, and the output is the information displayed on the user interface. Specifically, a highly responsive user interface is used to visually decompose the strategy.

[0516] Step 6:

[0517] The user conducts business negotiations by referring to the provided negotiation strategies. Inputs are information displayed from the terminal, and outputs are the user's actions and negotiation results. In this step, the user uses the proposed strategies to conduct more effective negotiations.

[0518] Step 7:

[0519] The server acquires and analyzes new data in real time and updates its policies. The input is newly acquired market data, and the output is the updated negotiation policy. Specifically, it re-analyzes the acquired data and makes policy adjustments that take into account the latest market trends.

[0520] 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.

[0521] This invention is a system that combines an emotion engine with a conventional business negotiation support system to provide a flexible and effective negotiation strategy that takes into account the user's emotional state. The embodiments of this invention are described below.

[0522] Integration of data collection and emotion recognition

[0523] The server collects business-related information by crawling data sources on the internet. In addition, the emotion engine uses video, audio, and text data provided by the user through their device to recognize the user's emotional state in real time. This recognition is performed using a comprehensive approach that combines facial expression analysis, voice tone analysis, and text sentiment analysis.

[0524] Emotion-based strategy generation

[0525] In addition to normal data analysis, the server receives emotional information from the emotion engine as input. This allows it to generate negotiation strategies that include stress relief measures, words of encouragement, and tactical advice tailored to the user's emotional state. Machine learning algorithms are used in this process to improve the accuracy of emotion recognition.

[0526] Emotional feedback through user interface

[0527] The device not only presents the generated strategy to the user but also collects real-time responses to the user's emotional changes. This feedback is used in the next strategy generation process, facilitating system personalization. Through an intuitive and user-friendly interface, users can review their emotional state tracking results and receive stress management advice as needed.

[0528] Implementation of specific examples

[0529] For example, consider a situation where a user is feeling pressured while negotiating an important contract. The server analyzes the latest market trend data, and the device's emotion engine determines that the user's stress level is high. In this case, the server generates a strategy that includes encouraging words such as "Take a deep breath and stay calm," and the device presents this information to the user. By following the suggestion, the user can calm down and proceed with the negotiation calmly and effectively.

[0530] Thus, the system according to the present invention utilizes an emotion engine and advanced data analysis technology to provide individually optimized negotiation support to users.

[0531] The following describes the processing flow.

[0532] Step 1:

[0533] The server crawls business-related information from multiple data sources on the internet and stores it in a database. Furthermore, the server also receives private and sentiment data from users and prepares it for analysis.

[0534] Step 2:

[0535] The device acquires data on the user's facial expressions and voice in real time and analyzes the user's emotional state using an emotion engine. The results of this analysis are sent to the server as indicators such as stress levels and satisfaction levels.

[0536] Step 3:

[0537] The server integrates crawled business data with user sentiment data obtained from the sentiment engine and performs data analysis using a generative model. This analysis applies algorithms to generate negotiation strategies that take user sentiment into account.

[0538] Step 4:

[0539] Based on the analysis results, the server generates multiple negotiation strategy options. The strategies are tailored to the user's emotional state, and include advice to promote relaxation, especially if the user is experiencing high levels of stress.

[0540] Step 5:

[0541] The server sends the generated strategy proposals to the terminal, which then presents them to the user. Because they are displayed intuitively on the user interface, users can easily select strategies and respond to their emotions.

[0542] Step 6:

[0543] The user proceeds with the actual negotiation based on the presented strategy. The emotions and thoughts experienced during the negotiation are collected as feedback via the device and sent to the server for the purpose of formulating the next strategy.

[0544] Step 7:

[0545] The server analyzes new data in real time and continuously updates its strategies and emotional response approaches. This process continues until the negotiation is concluded, and the system is designed to provide optimal negotiation support throughout.

[0546] (Example 2)

[0547] 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."

[0548] Conventional negotiation support systems fail to consider the user's emotional state and struggle to perform real-time analysis of accumulated market information. Therefore, there is a need to provide negotiation strategies that are optimized for the user and tailored to their specific circumstances.

[0549] 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.

[0550] In this invention, the server includes means for collecting data from information sources, organizing and storing the collected data, means for analyzing the organized data using a generative model and making predictions as a result of the analysis, and means for generating negotiation methods based on the predictions and presenting the generated methods. This makes it possible to provide flexible and effective negotiation strategies that are tailored to the user's emotional state.

[0551] A "source of information" refers to the external or internal resources from which data is obtained.

[0552] "Collecting data" refers to the process of obtaining and storing necessary information from various sources.

[0553] "Organizing and memorizing" means classifying collected data according to its format and content, and then saving it.

[0554] A "generative model" is a mathematical or algorithmic method used to analyze data and generate predictions or insights.

[0555] "Analysis" is the process of evaluating data and extracting knowledge and information that is relevant to a specific purpose.

[0556] "Prediction" is the process of estimating future events based on currently available data.

[0557] "Negotiation methods" refer to the tactics and strategies that should be employed in negotiations.

[0558] "Presentation" refers to the act of informing the user about the method or information used to generate something.

[0559] "Emotion recognition" refers to a technology or method that identifies a user's emotional state and acquires that state as data.

[0560] "Adjusting" means changing the method or result based on the initial settings or conditions.

[0561] A "user interface" is a means or screen through which a user interacts with a system and visually confirms information.

[0562] "Success rate" is an indicator that evaluates the probability that a proposed method will achieve its objective.

[0563] "Risk level" is an indicator that shows the degree of risk that may arise from implementing a method.

[0564] This invention is a system for providing flexible and effective strategies in business negotiations while considering the emotional state of the user. The server collects business-related data from information sources. This process involves running a wide range of programs for data acquisition, specifically crawling web information using common programming languages ​​and scripts. The collected data is stored in a database and used in subsequent processes.

[0565] The device receives video, audio, and text data provided by the user and analyzes it using an emotion engine. Specifically, a face detection algorithm is used for facial expression analysis, a voice waveform analysis tool for voice analysis, and a natural language processing tool for text sentiment analysis. This allows for real-time evaluation of the user's emotional state from their facial expressions, tone of voice, and messages.

[0566] The server uses a generative AI model to comprehensively analyze accumulated user sentiment information and business data to generate negotiation strategies based on the user's emotional state. Machine learning techniques are applied in this generation process. The strategies include specific word choices and responses for particular situations, which are then appropriately edited to communicate to the user.

[0567] For example, when a user is preparing for a meeting, the device might offer strategies that include advice such as, "It would be a good idea to practice your presentation and approach the meeting calmly." Such strategies are designed to alleviate user stress and anxiety.

[0568] An example of a prompt might be, "Generate appropriate advice based on the user's emotional state on how they should act to prepare for this meeting." This prompt allows the generative AI model to provide strategies to help the user achieve the best possible outcome.

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

[0570] Step 1:

[0571] The server collects business-related data from various sources. It uses publicly available information on the internet and data obtained from internal databases as input. Using this data, it employs web scraping techniques to acquire important market trends and company information, which is then stored in the database. This provides the material necessary for subsequent analysis.

[0572] Step 2:

[0573] The device acquires video, audio, and text data provided by the user. Inputs include, for example, audio and video data recorded by the user's camera and microphone, as well as manually entered text messages. Based on this, facial recognition software is used to analyze facial expressions, and a speech recognition algorithm is applied to analyze the tone of the voice. Furthermore, natural language processing tools are used to perform sentiment analysis of the text. This process allows for real-time analysis of the user's emotional state.

[0574] Step 3:

[0575] The server integrates emotional state data received from the terminal. The input includes emotional information from facial expressions, voice, and text obtained in the previous step. This information is input into a generating AI model, which performs analysis using machine learning techniques. As a result, insights based on the user's emotional state and business data are obtained.

[0576] Step 4:

[0577] The server generates negotiation strategies from integrated data. Inputs include user-specific data based on emotional states and business information. Using a generative model, it creates strategies that include action suggestions and emotional care methods tailored to specific situations. The output presents the user with effective strategic proposals.

[0578] Step 5:

[0579] The device presents strategies from the server through a user interface. Specifically, it visualizes strategies, including feedback based on emotional states, on the screen in a way that is easy for the user to understand. The user can then adjust their actions based on this information.

[0580] Step 6:

[0581] The user acts based on the strategy presented on the device and provides necessary feedback. The device returns changes in emotional state and the results of strategy execution as input. This allows the server to collect feedback data and use it to improve the system's accuracy in future strategy generation.

[0582] (Application Example 2)

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

[0584] Conventional negotiation support systems lack the ability to provide individualized support tailored to the user's emotional state, which prevents them from achieving maximum effectiveness in negotiations. Furthermore, they are insufficient in updating strategies to reflect real-time changes in the user's emotions, resulting in a lack of flexibility in adapting to changing situations.

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

[0586] In this invention, the server includes means for collecting information from a database, cleaning and storing the collected information, means for analyzing the cleansed information using a generative AI model and inferring trends from the analysis results, means for generating negotiation strategies based on the inferences and outputting the generated strategies, means for analyzing the user's facial expressions and voice and recognizing their emotional state, and means for generating personalized responses based on the recognized emotional state. This makes it possible to provide flexible and effective negotiation strategies that take the user's emotional state into consideration in real time.

[0587] "Methods for collecting, cleansing, and storing information" refers to the process of processing raw data obtained from a database, removing inaccurate or duplicate data, organizing it, and storing it in a format suitable for later analysis.

[0588] "Analysis using generative AI models" refers to a method that utilizes artificial intelligence models to analyze cleansed data and scientifically predict hidden patterns and trends.

[0589] "A means of generating and outputting negotiation strategies" refers to a technology that designs the best action plan for achieving negotiation objectives based on results obtained from data analysis and provides it to the user.

[0590] "Means for analyzing a user's facial expressions and voice to recognize their emotional state" refers to a process that processes the visual and auditory signals emitted by a user as data to identify their emotional responses and psychological state.

[0591] "Means for generating personalized responses" refers to methods for designing optimal responses and actions for a target individual based on their recognized emotional state and individual user information.

[0592] To realize this invention, a system is configured in which a server and a terminal work together. The server first collects business-related information from a database and cleanses the acquired information. Specifically, it removes noise and eliminates duplicate data, then organizes and stores the data. Next, it uses a generative AI model to analyze the cleansed data and predict trends. In the analysis, machine learning frameworks such as TensorFlow and PyTorch are used to extract useful insights from the data.

[0593] Meanwhile, the device acquires the user's facial expressions and voice data in real time to recognize their emotional state. This is achieved by collecting data through the camera and microphone and identifying emotions using machine learning algorithms. An automated analysis system evaluates the user's psychological state. This recognition result is sent to a server and input into the generated negotiation strategy.

[0594] Based on the user's emotional state, the server generates a user-optimized response and presents it to the user through the terminal. This process involves dynamically generated dialogue using Node.js and Dialogflow. The user interface also collects emotional feedback that helps in generating future strategies, thereby promoting system personalization.

[0595] As a concrete example, when a user returns home tired from work, the robot gently greets them with, "Welcome back. How was your day?" and suggests playing their preferred relaxing music. An example of a prompt message is, "Please recognize the user's emotions from their facial expression and tone of voice, and come up with a suggestion to help them relax." This system enables negotiation support that flexibly responds to the user's emotional changes.

[0596] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0597] Step 1:

[0598] The server collects business-related information from a database. It uses raw data crawled from the internet as input and produces cleaned data (de-noised and de-duplicated) as output. This data is then organized for later analysis. Specifically, a crawler program periodically collects new data from the web.

[0599] Step 2:

[0600] The server analyzes the cleansed data using a generative AI model. Using the cleansed data as input, it obtains analysis results for predicting trends as output. The generative AI model (e.g., using TensorFlow) executes a deep learning algorithm on the dataset to extract patterns and latent trends. In its specific operation, the model activates a neural network using trained weights to perform inference.

[0601] Step 3:

[0602] The device collects the user's facial expressions and voice data to recognize their emotional state in real time. It uses visual and audio data acquired through the camera and microphone as input, and outputs a report of the recognized emotional state. Data processing involves analyzing facial expressions with image processing algorithms and evaluating tone with a voice analysis program. Specifically, this analysis is performed using machine learning models.

[0603] Step 4:

[0604] The server generates the next negotiation strategy based on the user's emotional state. Using analysis results and emotional state reports as input, the optimized negotiation strategy is presented as output. Data processing involves inputting analysis results into a support system and executing a strategy generation algorithm tailored to the conditions. Specifically, Node.js and Dialogflow are used to dynamically construct the dialogue strategy.

[0605] Step 5:

[0606] The terminal presents the generated negotiation strategy to the user and collects emotional feedback in real time. It uses strategies sent from the server as input and collects user feedback information as output. Operationally, it provides visual and auditory feedback functions on the interface and continuously monitors the user's evolving emotional state. Specifically, it sends the collected feedback information to the server for continuous strategy improvement.

[0607] 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.

[0608] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0609] 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.

[0610] [Fourth Embodiment]

[0611] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0612] 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.

[0613] 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).

[0614] 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.

[0615] 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.

[0616] 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).

[0617] 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.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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".

[0624] This invention is a system that supports effective strategy formulation in business negotiations and streamlines the entire process by utilizing advanced data analysis techniques and generative models. Specific embodiments are described below.

[0625] Data collection and cleansing

[0626] The server crawls business-related information from numerous data sources accessible via the internet. This process includes data from public databases, industry reports, and company press releases. The collected information is cleansed on the server, removing unnecessary and duplicate data, and organized into a format suitable for subsequent analysis.

[0627] Data analysis and strategy generation

[0628] Based on the cleansed data, the server uses a generative model to analyze market trends and competitive landscapes. The analysis reveals predictions of competitor behavior and market trends, and based on this information, multiple negotiation strategies are generated. Each strategy is evaluated for its expected success rate and potential risk level, and the strategy deemed most effective is proposed to the user.

[0629] Strategic presentation through user interface

[0630] The terminal presents the optimal strategy, transmitted from the server, to the user through a user interface. This interface is visually intuitive, allowing the user to quickly grasp the details of the proposed strategy. The information displayed here is highly reliable because it is based on crawled data.

[0631] Real-time advice and strategy updates

[0632] As users progress through negotiations, new data is collected, and the server analyzes this data, updating the strategy in real time. This strategy update takes into account new market trends and the latest information on the other company, and is immediately presented to the user. This allows users to flexibly respond to changing negotiation situations.

[0633] Implementation of specific examples

[0634] For example, suppose a user is negotiating a contract with a supplier for a new product. The server analyzes relevant market news and industry trends and provides an analysis showing that the new product is advantageous compared to competitors' products. Based on these results, the terminal recommends to the user a strategy that emphasizes the product's technical features rather than its price advantage. This strategy can be effectively used by the user during negotiations to lead to improved terms of the deal.

[0635] Thus, the present invention provides data-driven strategies for business negotiations and supports users in responding promptly to changing market environments.

[0636] The following describes the processing flow.

[0637] Step 1:

[0638] The server crawls business-related information from public databases and news sites on the internet. A crawling algorithm is used to retrieve the information, and the scope of data collection is defined based on keywords or specific URLs.

[0639] Step 2:

[0640] The collected data is cleansed on the server. The server performs a process to detect and remove duplicate data, and further performs noise filtering to extract useful data. This results in data in a format suitable for analysis.

[0641] Step 3:

[0642] The server uses a generative model to analyze the cleansed data. This process employs data mining techniques to identify past trends and patterns and predict market movements. The analysis results provide predictions for the target company's actions and market changes.

[0643] Step 4:

[0644] Based on the analysis results, the server generates multiple negotiation strategies. The server evaluates the success rate and risk level of each generated strategy and selects the optimal strategy for the user.

[0645] Step 5:

[0646] The selected strategy is sent from the server to the terminal, which then presents the strategy to the user through a user interface. The presented strategy is visually organized for easy understanding, allowing the user to review the details of each strategy.

[0647] Step 6:

[0648] The user proceeds with actual negotiations based on the proposed strategy, and inputs the information obtained along the way into the system. This transmits on-site feedback to the server.

[0649] Step 7:

[0650] The server reanalyzes the strategy in real time based on user feedback and new data, and adjusts it if necessary. The adjusted strategy is then sent back to the terminal and presented to the user.

[0651] Step 8:

[0652] This process is repeated throughout the negotiation process and is designed to increase overall efficiency and improve the user's chances of negotiation success.

[0653] (Example 1)

[0654] 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".

[0655] In business negotiations, there is a need for systems that can quickly formulate efficient and effective strategies and flexibly respond to changing market environments. Furthermore, in today's information-saturated world, collecting and analyzing reliable information is becoming increasingly complex, and there is a lack of technology that automates this process in a user-friendly manner. Moreover, considerations for privacy and security are also crucial issues.

[0656] 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.

[0657] In this invention, the server includes means for automatically acquiring information from information sources, organizing and storing the acquired information, means for analyzing the organized information using learned techniques and predicting future trends as a result of the analysis, and means for generating action guidelines based on the predictions and outputting the generated guidelines. This makes it possible to efficiently collect information, quickly formulate strategies based on analysis results, and respond in real time.

[0658] A "source of information" is a collection of data, such as databases, reports, and releases, that are accessed to obtain the necessary information.

[0659] "Automatically acquiring information" refers to the process of collecting information using a program without manual intervention.

[0660] "Organizing and accumulating" means converting acquired information into a consistent format and structure, and saving it in a way that facilitates subsequent processing and retrieval.

[0661] "Pre-trained techniques" refer to methods that utilize models trained on existing datasets to analyze new data.

[0662] "Analysis" is the process of understanding the characteristics, trends, and relationships of collected information and data.

[0663] "Predicting future trends" means looking ahead to future developments and events based on current and past data.

[0664] "Generating action guidelines" means creating the optimal action strategy to take in a specific situation, based on the analyzed information.

[0665] "Outputting" means displaying or transmitting generated information or results in a format usable by humans or other systems.

[0666] This invention is a system for automating and streamlining strategy formulation in business negotiations. Specific embodiments of the invention are described below.

[0667] The server automatically retrieves information from its sources. In this process, the server collects information from databases, reports, and press releases on the internet via a program. This information retrieval is performed efficiently by using Python libraries for data crawling.

[0668] The collected information is organized on the server and converted into a format suitable for subsequent analysis. This involves using Pandas and NumPy for data frame manipulation and cleansing. The server then uses pre-trained techniques to perform detailed analysis based on this organized information. Generative AI models such as TensorFlow and PyTorch are used for this analysis process.

[0669] Based on the analysis results, the server predicts future trends and generates multiple action plans. This allows users to select the optimal strategy based on different business scenarios. Specifically, the action plans are provided through a visual display on the user's terminal. This user interface presents information visually in an easy-to-understand manner, enabling users to make quick decisions.

[0670] As users progress through negotiations, the server analyzes the data in real time and updates its course of action as new information becomes available. This feature ensures users always have the latest information and can adapt to dynamically changing negotiation situations.

[0671] As a concrete example, consider a scenario where a user is exploring strategies for a new product in a highly competitive market. The server analyzes market data and suggests that highlighting the new product's technical features is an effective strategy for gaining a competitive advantage. This strategy is visualized on the user's terminal, enabling rapid strategic adjustments.

[0672] An example of a prompt message might be, "Re-evaluate the optimal negotiation strategy based on new market trends." This allows users to make effective decisions even in a changing business environment.

[0673] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0674] Step 1:

[0675] The server automatically retrieves business-related information from information sources. This information includes databases, reports, and press releases. A Python library is used to perform the crawling process, and the raw data is temporarily stored in storage. The input is the data retrieved from the information sources, and the output is the raw retrieved data.

[0676] Step 2:

[0677] The server organizes and cleanses the acquired data. It removes unnecessary information and duplicate data and converts it into a format suitable for analysis. Specifically, it uses the Pandas library to format the data and NumPy to correct for outliers. The input is the raw acquired data, and the output is cleansed, well-formed data.

[0678] Step 3:

[0679] The server analyzes cleansed data to predict future trends. Generative AI models are used to understand market trends and competitive landscapes within the data. Predictive data is generated as analysis results through model processing using TensorFlow and PyTorch. Input is well-formed data, and output is the prediction and analysis results.

[0680] Step 4:

[0681] The server generates strategies based on prediction results. It devises multiple negotiation strategies and evaluates the likelihood of success and potential risks of each. It analyzes the strategies using statistical models and simulations. The input is the analysis results, and the output is the set of generated strategies.

[0682] Step 5:

[0683] The terminal presents the strategy, transmitted from the server, to the user through a user interface. The strategy information is displayed visually and provided in a format that is easy for the user to quickly understand. For example, infographics and charts are used to represent the key points of the strategy. The input is the generated strategy, and the output is the visualized strategy information.

[0684] Step 6:

[0685] As new data is generated during the user's negotiation process, the server analyzes that data in real time and updates the strategy. The updated strategy is immediately presented to the user. The strategy is re-evaluated based on new market trends and competitive situations. The input is new negotiation data, and the output is updated strategy information.

[0686] (Application Example 1)

[0687] 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".

[0688] Business negotiations, particularly those concerning the introduction of new technologies and fees in electronic payments, require rapid and effective strategy development. In today's rapidly changing market environment, where information is vast and trends are constantly evolving, formulating and updating appropriate and flexible negotiation strategies in a timely manner is challenging. This can lead to inefficient business negotiations and missed opportunities.

[0689] 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.

[0690] In this invention, the server includes means for acquiring data from information sources, organizing and recording the acquired data, means for analyzing the organized data using a generative model and inferring trends as a result of the analysis, and means for generating policies based on the inferences and displaying the generated policies. This enables the provision of optimal negotiation policies in response to new market information in real time and allows for rapid response even when the business environment changes.

[0691] A "source of information" is a collection of data, such as public databases, industry reports, and company press releases, that are accessed to obtain data.

[0692] A "generative model" is a machine learning algorithm that analyzes large amounts of data to generate useful trends and insights.

[0693] "Organization" is the process of removing unnecessary information and duplicates from acquired data, and preparing the data to facilitate analysis.

[0694] "To infer" means to predict market trends and corporate behavior based on the results of an analysis.

[0695] "Generating a policy" means creating the optimal strategy or action plan based on inferred information.

[0696] "To provide support for negotiations" means to offer users useful information and strategies when conducting business negotiations regarding payments.

[0697] The system that implements this application consists of a server, a terminal, and a user interface. The server first automatically retrieves the necessary data from the information source and organizes it through a data cleansing process. Data cleansing removes duplicate data and noise, preparing it for analysis by a generative model. This analysis uses machine learning frameworks such as TensorFlow and PyTorch to accurately predict market trends and company behavior from the collected data.

[0698] Next, the server generates the optimal negotiation strategy based on the analyzed data. This process utilizes the Python programming language to set up an action plan suitable for the specific negotiation situation. The generated strategy is sent to the terminal via an intuitive user interface. This interface is developed using React Native and provides a visually appealing display that makes it easy for users to understand and act upon.

[0699] Users can always obtain the latest negotiation information through this interface. A key feature is its ability to update policies in real time in response to market changes, supporting negotiations in electronic payments. For example, when considering the introduction of a new QR code payment function, the application analyzes competitor activities and market trends, and presents a marketing strategy for success.

[0700] A good example of a prompt would be: "Analyze the following data list regarding QR code payment functionality, identify the advantages compared to competitors, and create a detailed proposal."

[0701] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0702] Step 1:

[0703] The server retrieves business-related data from information sources. The input is websites or databases as information sources, and the output is the retrieved raw data. In this process, the server uses web crawlers and APIs to collect data in real time.

[0704] Step 2:

[0705] The server cleanses and organizes the acquired data. The input is the raw data obtained in step 1, and the output is a clean dataset. This process involves removing duplicate data and filtering out noise. Specifically, it standardizes the data using regular expressions and statistical tools.

[0706] Step 3:

[0707] The server analyzes cleansed data using a generative model. The input is a clean dataset, and the output is inferential information about market trends and competitor behavior. As part of the data processing, machine learning algorithms are applied to create a predictive model.

[0708] Step 4:

[0709] The server generates negotiation strategies based on the inferred information. The input is the inferred information from step 3, and the output is the optimal strategy specific to each negotiation. As a data calculation, the results of the predictive model are evaluated, and a concrete strategy is constructed using the policy decision logic.

[0710] Step 5:

[0711] The terminal visually presents the generated negotiation strategy to the user. The input is the optimal strategy from the server, and the output is the information displayed on the user interface. Specifically, a highly responsive user interface is used to visually decompose the strategy.

[0712] Step 6:

[0713] The user conducts business negotiations by referring to the provided negotiation strategies. Inputs are information displayed from the terminal, and outputs are the user's actions and negotiation results. In this step, the user uses the proposed strategies to conduct more effective negotiations.

[0714] Step 7:

[0715] The server acquires and analyzes new data in real time and updates its policies. The input is newly acquired market data, and the output is the updated negotiation policy. Specifically, it re-analyzes the acquired data and makes policy adjustments that take into account the latest market trends.

[0716] 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.

[0717] This invention is a system that combines an emotion engine with a conventional business negotiation support system to provide a flexible and effective negotiation strategy that takes into account the user's emotional state. The embodiments of this invention are described below.

[0718] Integration of data collection and emotion recognition

[0719] The server collects business-related information by crawling data sources on the internet. In addition, the emotion engine uses video, audio, and text data provided by the user through their device to recognize the user's emotional state in real time. This recognition is performed using a comprehensive approach that combines facial expression analysis, voice tone analysis, and text sentiment analysis.

[0720] Emotion-based strategy generation

[0721] In addition to normal data analysis, the server receives emotional information from the emotion engine as input. This allows it to generate negotiation strategies that include stress relief measures, words of encouragement, and tactical advice tailored to the user's emotional state. Machine learning algorithms are used in this process to improve the accuracy of emotion recognition.

[0722] Emotional feedback through user interface

[0723] The device not only presents the generated strategy to the user but also collects real-time responses to the user's emotional changes. This feedback is used in the next strategy generation process, facilitating system personalization. Through an intuitive and user-friendly interface, users can review their emotional state tracking results and receive stress management advice as needed.

[0724] Implementation of specific examples

[0725] For example, consider a situation where a user is feeling pressured while negotiating an important contract. The server analyzes the latest market trend data, and the device's emotion engine determines that the user's stress level is high. In this case, the server generates a strategy that includes encouraging words such as "Take a deep breath and stay calm," and the device presents this information to the user. By following the suggestion, the user can calm down and proceed with the negotiation calmly and effectively.

[0726] Thus, the system according to the present invention utilizes an emotion engine and advanced data analysis technology to provide individually optimized negotiation support to users.

[0727] The following describes the processing flow.

[0728] Step 1:

[0729] The server crawls business-related information from multiple data sources on the internet and stores it in a database. Furthermore, the server also receives private and sentiment data from users and prepares it for analysis.

[0730] Step 2:

[0731] The device acquires data on the user's facial expressions and voice in real time and analyzes the user's emotional state using an emotion engine. The results of this analysis are sent to the server as indicators such as stress levels and satisfaction levels.

[0732] Step 3:

[0733] The server integrates crawled business data with user sentiment data obtained from the sentiment engine and performs data analysis using a generative model. This analysis applies algorithms to generate negotiation strategies that take user sentiment into account.

[0734] Step 4:

[0735] Based on the analysis results, the server generates multiple negotiation strategy options. The strategies are tailored to the user's emotional state, and include advice to promote relaxation, especially if the user is experiencing high levels of stress.

[0736] Step 5:

[0737] The server sends the generated strategy proposals to the terminal, which then presents them to the user. Because they are displayed intuitively on the user interface, users can easily select strategies and respond to their emotions.

[0738] Step 6:

[0739] The user proceeds with the actual negotiation based on the presented strategy. The emotions and thoughts experienced during the negotiation are collected as feedback via the device and sent to the server for the purpose of formulating the next strategy.

[0740] Step 7:

[0741] The server analyzes new data in real time and continuously updates its strategies and emotional response approaches. This process continues until the negotiation is concluded, and the system is designed to provide optimal negotiation support throughout.

[0742] (Example 2)

[0743] 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".

[0744] Conventional negotiation support systems fail to consider the user's emotional state and struggle to perform real-time analysis of accumulated market information. Therefore, there is a need to provide negotiation strategies that are optimized for the user and tailored to their specific circumstances.

[0745] 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.

[0746] In this invention, the server includes means for collecting data from information sources, organizing and storing the collected data, means for analyzing the organized data using a generative model and making predictions as a result of the analysis, and means for generating negotiation methods based on the predictions and presenting the generated methods. This makes it possible to provide flexible and effective negotiation strategies that are tailored to the user's emotional state.

[0747] A "source of information" refers to the external or internal resources from which data is obtained.

[0748] "Collecting data" refers to the process of obtaining and storing necessary information from various sources.

[0749] "Organizing and memorizing" means classifying collected data according to its format and content, and then saving it.

[0750] A "generative model" is a mathematical or algorithmic method used to analyze data and generate predictions or insights.

[0751] "Analysis" is the process of evaluating data and extracting knowledge and information that is relevant to a specific purpose.

[0752] "Prediction" is the process of estimating future events based on currently available data.

[0753] "Negotiation methods" refer to the tactics and strategies that should be employed in negotiations.

[0754] "Presentation" refers to the act of informing the user about the method or information used to generate something.

[0755] "Emotion recognition" refers to a technology or method that identifies a user's emotional state and acquires that state as data.

[0756] "Adjusting" means changing the method or result based on the initial settings or conditions.

[0757] A "user interface" is a means or screen through which a user interacts with a system and visually confirms information.

[0758] "Success rate" is an indicator that evaluates the probability that a proposed method will achieve its objective.

[0759] "Risk level" is an indicator that shows the degree of risk that may arise from implementing a method.

[0760] This invention is a system for providing flexible and effective strategies in business negotiations while considering the emotional state of the user. The server collects business-related data from information sources. This process involves running a wide range of programs for data acquisition, specifically crawling web information using common programming languages ​​and scripts. The collected data is stored in a database and used in subsequent processes.

[0761] The device receives video, audio, and text data provided by the user and analyzes it using an emotion engine. Specifically, a face detection algorithm is used for facial expression analysis, a voice waveform analysis tool for voice analysis, and a natural language processing tool for text sentiment analysis. This allows for real-time evaluation of the user's emotional state from their facial expressions, tone of voice, and messages.

[0762] The server uses a generative AI model to comprehensively analyze accumulated user sentiment information and business data to generate negotiation strategies based on the user's emotional state. Machine learning techniques are applied in this generation process. The strategies include specific word choices and responses for particular situations, which are then appropriately edited to communicate to the user.

[0763] For example, when a user is preparing for a meeting, the device might offer strategies that include advice such as, "It would be a good idea to practice your presentation and approach the meeting calmly." Such strategies are designed to alleviate user stress and anxiety.

[0764] An example of a prompt might be, "Generate appropriate advice based on the user's emotional state on how they should act to prepare for this meeting." This prompt allows the generative AI model to provide strategies to help the user achieve the best possible outcome.

[0765] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0766] Step 1:

[0767] The server collects business-related data from various sources. It uses publicly available information on the internet and data obtained from internal databases as input. Using this data, it employs web scraping techniques to acquire important market trends and company information, which is then stored in the database. This provides the material necessary for subsequent analysis.

[0768] Step 2:

[0769] The device acquires video, audio, and text data provided by the user. Inputs include, for example, audio and video data recorded by the user's camera and microphone, as well as manually entered text messages. Based on this, facial recognition software is used to analyze facial expressions, and a speech recognition algorithm is applied to analyze the tone of the voice. Furthermore, natural language processing tools are used to perform sentiment analysis of the text. This process allows for real-time analysis of the user's emotional state.

[0770] Step 3:

[0771] The server integrates emotional state data received from the terminal. The input includes emotional information from facial expressions, voice, and text obtained in the previous step. This information is input into a generating AI model, which performs analysis using machine learning techniques. As a result, insights based on the user's emotional state and business data are obtained.

[0772] Step 4:

[0773] The server generates negotiation strategies from integrated data. Inputs include user-specific data based on emotional states and business information. Using a generative model, it creates strategies that include action suggestions and emotional care methods tailored to specific situations. The output presents the user with effective strategic proposals.

[0774] Step 5:

[0775] The device presents strategies from the server through a user interface. Specifically, it visualizes strategies, including feedback based on emotional states, on the screen in a way that is easy for the user to understand. The user can then adjust their actions based on this information.

[0776] Step 6:

[0777] The user acts based on the strategy presented on the device and provides necessary feedback. The device returns changes in emotional state and the results of strategy execution as input. This allows the server to collect feedback data and use it to improve the system's accuracy in future strategy generation.

[0778] (Application Example 2)

[0779] 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".

[0780] Conventional negotiation support systems lack the ability to provide individualized support tailored to the user's emotional state, which prevents them from achieving maximum effectiveness in negotiations. Furthermore, they are insufficient in updating strategies to reflect real-time changes in the user's emotions, resulting in a lack of flexibility in adapting to changing situations.

[0781] 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.

[0782] In this invention, the server includes means for collecting information from a database, cleaning and storing the collected information, means for analyzing the cleansed information using a generative AI model and inferring trends from the analysis results, means for generating negotiation strategies based on the inferences and outputting the generated strategies, means for analyzing the user's facial expressions and voice and recognizing their emotional state, and means for generating personalized responses based on the recognized emotional state. This makes it possible to provide flexible and effective negotiation strategies that take the user's emotional state into consideration in real time.

[0783] "Methods for collecting, cleansing, and storing information" refers to the process of processing raw data obtained from a database, removing inaccurate or duplicate data, organizing it, and storing it in a format suitable for later analysis.

[0784] "Analysis using generative AI models" refers to a method that utilizes artificial intelligence models to analyze cleansed data and scientifically predict hidden patterns and trends.

[0785] "A means of generating and outputting negotiation strategies" refers to a technology that designs the best action plan for achieving negotiation objectives based on results obtained from data analysis and provides it to the user.

[0786] "Means for analyzing a user's facial expressions and voice to recognize their emotional state" refers to a process that processes the visual and auditory signals emitted by a user as data to identify their emotional responses and psychological state.

[0787] "Means for generating personalized responses" refers to methods for designing optimal responses and actions for a target individual based on their recognized emotional state and individual user information.

[0788] To realize this invention, a system is configured in which a server and a terminal work together. The server first collects business-related information from a database and cleanses the acquired information. Specifically, it removes noise and eliminates duplicate data, then organizes and stores the data. Next, it uses a generative AI model to analyze the cleansed data and predict trends. In the analysis, machine learning frameworks such as TensorFlow and PyTorch are used to extract useful insights from the data.

[0789] Meanwhile, the device acquires the user's facial expressions and voice data in real time to recognize their emotional state. This is achieved by collecting data through the camera and microphone and identifying emotions using machine learning algorithms. An automated analysis system evaluates the user's psychological state. This recognition result is sent to a server and input into the generated negotiation strategy.

[0790] Based on the user's emotional state, the server generates a user-optimized response and presents it to the user through the terminal. This process involves dynamically generated dialogue using Node.js and Dialogflow. The user interface also collects emotional feedback that helps in generating future strategies, thereby promoting system personalization.

[0791] As a concrete example, when a user returns home tired from work, the robot gently greets them with, "Welcome back. How was your day?" and suggests playing their preferred relaxing music. An example of a prompt message is, "Please recognize the user's emotions from their facial expression and tone of voice, and come up with a suggestion to help them relax." This system enables negotiation support that flexibly responds to the user's emotional changes.

[0792] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0793] Step 1:

[0794] The server collects business-related information from a database. It uses raw data crawled from the internet as input and produces cleaned data (de-noised and de-duplicated) as output. This data is then organized for later analysis. Specifically, a crawler program periodically collects new data from the web.

[0795] Step 2:

[0796] The server analyzes the cleansed data using a generative AI model. Using the cleansed data as input, it obtains analysis results for predicting trends as output. The generative AI model (e.g., using TensorFlow) executes a deep learning algorithm on the dataset to extract patterns and latent trends. In its specific operation, the model activates a neural network using trained weights to perform inference.

[0797] Step 3:

[0798] The device collects the user's facial expressions and voice data to recognize their emotional state in real time. It uses visual and audio data acquired through the camera and microphone as input, and outputs a report of the recognized emotional state. Data processing involves analyzing facial expressions with image processing algorithms and evaluating tone with a voice analysis program. Specifically, this analysis is performed using machine learning models.

[0799] Step 4:

[0800] The server generates the next negotiation strategy based on the user's emotional state. Using analysis results and emotional state reports as input, the optimized negotiation strategy is presented as output. Data processing involves inputting analysis results into a support system and executing a strategy generation algorithm tailored to the conditions. Specifically, Node.js and Dialogflow are used to dynamically construct the dialogue strategy.

[0801] Step 5:

[0802] The terminal presents the generated negotiation strategy to the user and collects emotional feedback in real time. It uses strategies sent from the server as input and collects user feedback information as output. Operationally, it provides visual and auditory feedback functions on the interface and continuously monitors the user's evolving emotional state. Specifically, it sends the collected feedback information to the server for continuous strategy improvement.

[0803] 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.

[0804] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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."

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] The following is further disclosed regarding the embodiments described above.

[0825] (Claim 1)

[0826] A means of crawling information from a database, cleansing the crawled information, and saving it,

[0827] A means of analyzing cleansed information using a generative model and predicting trends based on the analysis results,

[0828] A means for generating negotiation strategies based on predictions and outputting the generated strategies,

[0829] A means of collecting and analyzing new data in real time and updating strategies,

[0830] A means of presenting strategies and update information through a user interface,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, which implements a protocol for encrypting communications and protects privacy.

[0834] (Claim 3)

[0835] The system according to claim 1, which generates multiple strategy candidates based on the analysis of collected data and evaluates the success rate and risk level of each.

[0836] "Example 1"

[0837] (Claim 1)

[0838] A means of automatically acquiring information from information sources, organizing and storing the acquired information,

[0839] A means of analyzing information organized using trained techniques and predicting future trends based on the analysis results,

[0840] A means for generating action guidelines based on predictions and outputting the generated guidelines,

[0841] A means of collecting and analyzing new information in real time and updating guidelines,

[0842] Means for presenting guidelines and update information through a visual display device,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, which implements encryption technology to protect communications.

[0846] (Claim 3)

[0847] The system according to claim 1, which generates multiple candidate guidelines based on an analysis of collected information and evaluates the likelihood of success and potential risks of each.

[0848] "Application Example 1"

[0849] (Claim 1)

[0850] A means of obtaining data from information sources, organizing and recording the obtained data,

[0851] A means of analyzing organized data using generative models and inferring trends from the analysis results,

[0852] A means for generating a policy based on inferences and displaying the generated policy,

[0853] A means of acquiring and analyzing new data in real time and updating policies,

[0854] A means of providing policies and update information through a user interface,

[0855] To support negotiations in electronic payments, we provide means to present optimal policies regarding payment fees and the introduction of new technologies,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, which implements a method for encrypting communications and protecting personal information.

[0859] (Claim 3)

[0860] The system according to claim 1, which generates multiple candidate strategies based on the analysis of acquired data and evaluates the success probability and risk level of each.

[0861] "Example 2 of combining an emotion engine"

[0862] (Claim 1)

[0863] A means of collecting data from information sources, organizing and storing the collected data,

[0864] A means of analyzing data organized using a generative model and making predictions based on the analysis results,

[0865] A means of generating negotiation methods based on predictions and presenting the generated methods,

[0866] A means of acquiring data based on emotion recognition in real time and adjusting negotiation methods,

[0867] Means for displaying methods and adjustment information through a user interface,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, which incorporates technology for encrypting communications in order to protect information.

[0871] (Claim 3)

[0872] The system according to claim 1, which generates multiple method proposals based on collected information and evaluates the success rate and risk level of each.

[0873] "Application example 2 when combining with an emotional engine"

[0874] (Claim 1)

[0875] A means of collecting information from a database, and cleaning and storing the collected information,

[0876] A method for analyzing cleansed information using a generative AI model and inferring trends from the analysis results,

[0877] A means for generating negotiation strategies based on speculation and outputting the generated strategies,

[0878] A means to collect and analyze new data in real time and update strategies,

[0879] A means of presenting strategies and update information through a user interface,

[0880] A means of analyzing the user's facial expressions and voice to recognize their emotional state,

[0881] A means of generating an individual-optimized response based on recognized emotional states,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, which implements a protocol for encrypting communications and maintains privacy.

[0885] (Claim 3)

[0886] The system according to claim 1, which generates multiple strategy candidates based on the analysis of collected data and recognized emotional information, and evaluates the success probability and risk level of each. [Explanation of Symbols]

[0887] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining data from information sources, organizing and recording the obtained data, A means of analyzing organized data using generative models and inferring trends from the analysis results, A means for generating a policy based on inferences and displaying the generated policy, A means of acquiring and analyzing new data in real time and updating policies, A means of providing policies and update information through a user interface, To support negotiations in electronic payments, we provide means to present optimal policies regarding payment fees and the introduction of new technologies, A system that includes this.

2. The system according to claim 1, which implements a method for encrypting communications and protecting personal information.

3. The system according to claim 1, which generates multiple candidate strategies based on the analysis of acquired data and evaluates the success probability and risk level of each.

Images