system

Abstract

Provide a system. 【Solution means】 Means for receiving project information from a user and obtaining additional information from an external information source, Means for preprocessing the received data and unifying different data formats, Means for predicting the success probability of a business using a generation model with the preprocessed data, Means for generating improvement proposals for the business based on the success probability, Means for presenting the generated improvement plans to the user and updating the information, Means for executing an optimization and differentiation strategy for functions in a specific area based on the proposed improvement plan, Means including continuous evaluation and feedback provision in a specific area, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the planning of a new business, a major problem is that the success rate is low and the uncertainty is high. In addition, the data required for decision-making is diverse, and it is not easy to analyze them in a unified way. Furthermore, it is also difficult to quickly respond to the changing market environment and take appropriate improvement measures in real time. Therefore, it is required to solve these problems in order to increase the success rate of a new business plan.

Means for Solving the Problems

[0005] This invention provides a system that combines user input data with external information and uses a generative model to predict the success probability of a new business. This system preprocesses the input data to unify data in different formats and make it analyzable. Furthermore, it generates specific business improvement proposals based on the success probability and presents them to the user in real time. By analyzing multimodal data, it identifies success and risk factors, and through continuous data updates and re-evaluation using the generative model, it always provides optimal suggestions tailored to the latest situation.

[0006] A "user" is an individual or organization that uses the system to improve the probability of success of a new business.

[0007] "Project information" refers to data related to a new business, such as market size, competitive landscape, resource allocation, and team composition.

[0008] An "external information source" is an external database or API that the system accesses to obtain additional information.

[0009] A "generative model" is an artificial intelligence model that predicts the probability of success of a new business by analyzing diverse data.

[0010] "Preprocessing" is the process of converting received data into a format that can be analyzed, and includes data cleaning and formatting standardization.

[0011] "Success probability" is a numerical representation of the likelihood that a new business will achieve its goals.

[0012] An "improvement proposal" is a specific action plan to increase the success rate of a business, based on the success probability predicted by the generative model.

[0013] "Real-time" is a temporal concept that means updating data or presenting results immediately.

[0014] "Multimodal data" is a general term referring to data in different formats such as text, images, and audio.

[0015] "Success factors" are elements and conditions that contribute to the success of a business.

[0016] "Risk factors" are elements and conditions that pose obstacles to the execution of a business.

Brief Explanation of Drawings

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

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

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

[0020] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

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

[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 system is designed to predict the probability of success for new businesses and provide improvement suggestions. Users input project information using a terminal, including market size, competitive landscape, resource allocation, and team composition. The terminal then transmits the entered information to the server.

[0039] The server retrieves additional information from external sources based on the received data. This complements the user-provided project information with more detailed market reports and competitive analysis data. All collected data is pre-processed within the server and standardized into an analyzable format.

[0040] The server then provides the pre-processed data to a generative model to predict the probability of business success. The generative model is trained on historical new business data and can analyze multimodal data such as text, images, and audio. This identifies success and risk factors and calculates the overall probability of success.

[0041] Based on the success probability results, the server generates specific improvement suggestions to aim for business success. These include specific strategies for establishing a competitive advantage and adjustments to the marketing plan. The generated suggestions are sent to the terminal in real time and presented to the user.

[0042] For example, when a user develops a new mobile app, suggestions for specific UI / UX design improvements or feature additions are made based on market growth potential and the strength of competition. Because the information the user needs is provided immediately, decision-making can be done quickly.

[0043] In this way, users can leverage the highly accurate predictions and suggestions provided by the server to improve the probability of success for new businesses.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] Users input basic information about a new business via a terminal. This information includes market size, competitive landscape, resource allocation, and team structure. Once the user has finished entering the information, the terminal sends it to the server.

[0047] Step 2:

[0048] The server analyzes project information received from users and searches external sources to collect any necessary additional data. This includes market reports and competitor activity. The collected data is used for internal server analysis.

[0049] Step 3:

[0050] The server preprocesses the received information and any additional data collected. This includes cleaning the data, standardizing the format, correcting outliers, and preparing it for analysis. This process is crucial for improving the accuracy of the analysis.

[0051] Step 4:

[0052] The server inputs pre-processed data into a generative model. This generative model is designed to predict the probability of success for new businesses and is capable of analyzing multimodal data. The model identifies success and risk factors and calculates an overall probability of success.

[0053] Step 5:

[0054] Based on the output from the generative model, the server generates specific improvement suggestions. These suggestions include strategies and action plans to increase the project's success rate. The generated suggestions serve as a reference for users when adjusting their business operations.

[0055] Step 6:

[0056] The server sends the success probability analysis results and improvement suggestions to the terminal, presenting them to the user in real time. The user can then use this information to input new details and update their business plan. This process enables accurate decision-making based on the latest data at all times.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In planning new businesses, it is essential to efficiently analyze vast amounts of data and quickly and accurately predict the probability of success. However, current technology makes it difficult to integrate data from multiple sources and generate useful improvement suggestions in real time. Therefore, a system is needed that can quickly provide improvement suggestions to increase the success rate of new businesses.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for receiving activity information from users and acquiring additional information from external information sources, means for preprocessing the received information and unifying different information formats, and means for predicting the probability of success using a predictive model with the preprocessed information. This makes it possible to quickly and accurately analyze data and propose optimal improvement measures for the success of new businesses.

[0062] "User" refers to an individual or organization that uses the system to provide activity information and receive suggestions.

[0063] "Activity information" refers to data including market size, competitive landscape, resource allocation, and team composition related to projects and businesses.

[0064] "External information sources" refer to third-party databases and information services that the server accesses to supplement the information provided by the user.

[0065] "Preprocessing" refers to the process of cleaning or standardizing the data format of received or collected information in order to make it analyzable.

[0066] A "predictive model" refers to a computational model used to analyze collected information and estimate the probability of success for a new business.

[0067] A "generative model" refers to a machine learning model that is trained on historical data and can analyze multiple data formats such as text, images, and audio.

[0068] An "improvement suggestion" refers to specific measures and strategies aimed at increasing the success rate of a new business, based on the predicted probability of success.

[0069] "Information updates" refer to providing users with new data and suggestions immediately to support their decision-making process.

[0070] "Information in multiple formats" refers to a set of information that includes different data formats, such as text, images, and audio.

[0071] "Visualization" refers to the process of displaying data and proposals in the form of diagrams, charts, and other visual aids so that users can easily understand them.

[0072] This section describes an embodiment of this system. The user uses a terminal to input activity information related to the project. This activity information includes market size, competitive landscape, resource allocation, and team composition. The information entered by the user is transmitted from the terminal to the server.

[0073] The server accesses external information sources based on the received activity information and retrieves any necessary additional information. This interaction with external information sources involves using APIs to collect relevant data from databases and publicly available sources. The server preprocesses the received and collected information using the Python Pandas library. This includes handling missing values, cleaning the data, and standardizing the format.

[0074] The pre-processed information is input into a generative AI model built using TENSORFLOW® and PyTorch to predict the probability of business success. The generative AI model has the ability to analyze data in multiple formats, such as text, images, and audio, and identify success factors and risk factors.

[0075] Based on the predicted success rate, the server generates improvement suggestions for the success of the new business. These suggestions include revisions to specific strategies and marketing plans to strengthen competitive advantages. The server then formats the generated suggestions into a user-friendly format using natural language generation technology.

[0076] The server then sends the generated improvement suggestions to the terminal in real time. The terminal visualizes and presents the received suggestions to the user, enabling the user to make quick decisions.

[0077] For example, if a user is developing a new smartphone application, the system can assess market growth potential and competitive strength, and suggest improvements to specific user interfaces and user experience (UI / UX). The following prompts can be provided to encourage the user to use the system:

[0078] Please provide project information regarding the mobile app currently under development as a new business venture. Please include details such as market size, competitive landscape, and team structure.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] Users input activity information via a terminal. This information includes market size, competitive landscape, resource allocation, and team composition. Once input is complete, the terminal verifies the entered information, encodes it in the appropriate data format, and sends it to the server. The output of the terminal for the input data is the activity information sent to the server.

[0082] Step 2:

[0083] The server receives activity information sent from the terminal. Based on the received data, the server accesses external information sources to collect necessary additional information. In this process, the server uses APIs to query external databases and retrieve market reports and competitive analysis data. The input data is activity information, and the output data is supplementary, detailed information.

[0084] Step 3:

[0085] The server preprocesses the collected information, including imputing missing values, cleaning the data, and standardizing the format. This process uses the Python Pandas library to convert the data into a parseable format. The input data is imputed information, while the output data is preprocessed data.

[0086] Step 4:

[0087] The server inputs pre-processed data into a generative AI model. This model, built using TensorFlow or PyTorch, analyzes data in multiple formats and predicts the probability of business success. Because the generative AI model is trained on historical data, it has the ability to identify success factors and risk factors. The input data is pre-processed data, and the output data is the result of the success probability.

[0088] Step 5:

[0089] Based on the success probability results, the server generates specific improvement suggestions. These suggestions include revising strategies and marketing plans to strengthen competitive advantage. Natural language generation technology is used to format the suggestions in a user-friendly manner. The input data consists of the success probability and identified factors, while the output data consists of improvement suggestions for the user.

[0090] Step 6:

[0091] The server sends the generated improvement suggestions to the terminal in real time. The terminal receives the suggestions and presents them to the user in a visualized format. This allows the user to immediately review the information and make quick decisions. The input data is the generated suggestions, and the output data is the visualized information presented to the user.

[0092] (Application Example 1)

[0093] 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."

[0094] In today's world, there is a need to appropriately evaluate the success rate of new business launches and projects in specific areas, and to rapidly implement differentiation strategies in highly competitive markets. However, traditional methods of information gathering and analysis have been fragmented and inefficient. Therefore, a system is needed to support business success through rapid and continuous evaluation and improvement.

[0095] 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.

[0096] In this invention, the server includes means for receiving project information from users and obtaining additional information from external sources, means for preprocessing the received data and unifying different data formats, and means for implementing optimization and differentiation strategies for functions in specific areas based on proposed improvements. This makes it possible to improve the probability of business success through continuous evaluation and feedback in specific areas.

[0097] "Project information" refers to information that users need to provide when starting a new business or project, such as market size, competitive landscape, resource allocation, and team composition.

[0098] "External information sources" refer to data obtained from external sources, such as market reports, competitive analyses, and economic indicators, that are referenced to complement project information.

[0099] A "generative model" is a machine learning algorithm that analyzes multimodal input data to predict the probability of business success.

[0100] "Probability of success" is an evaluation metric that indicates the likelihood of a newly proposed business or project succeeding in the market.

[0101] An "improvement suggestion" is information that proposes modifications to specific strategies or measures in order to increase the probability of business success.

[0102] A "specific domain" refers to a unique market or technological area in various industries and fields, primarily such as electronic payment services.

[0103] "Functional optimization" refers to optimizing the functionality of services or products provided in a specific area to maximize their effectiveness.

[0104] A "differentiation strategy" is a tactic to secure a competitive advantage by developing services or products in the market that have unique features different from those of competitors.

[0105] "Continuous evaluation" refers to an analytical process that continuously reflects project progress and market trends in real time.

[0106] "Providing feedback" is the process by which the system returns information to users about the status of the business and areas for improvement.

[0107] This invention is a system that predicts the probability of success of a new business in a specific domain and provides optimal improvement suggestions. The system begins with the user sending project information from their terminal to a server. This project information includes market size, competitive landscape, resource allocation, and team composition. After receiving this information, the server retrieves relevant data from external sources.

[0108] The server integrates this data and uses a generative AI model to analyze it. This model is trained on past new business data and predicts the probability of success through multimodal data analysis. Based on the analysis results, it generates specific differentiation strategies and functional optimization suggestions to promote project success. The server presents these suggestions to the user's terminal in real time, helping users make immediate decisions.

[0109] In this embodiment, a specific example is a small or medium-sized enterprise (SME) planning to introduce a new QR code (registered trademark) payment function in the electronic payment service industry. By using the proposed system, companies can conduct market evaluations based on the entered project information and immediately obtain effective strategies for differentiating themselves from competitors. Furthermore, users can quickly modify and implement their strategies by utilizing the feedback provided in real time.

[0110] For processing specific generative models, programming languages ​​and libraries such as Python and TensorFlow can be used. The server will run on a computer infrastructure with sufficient performance for data preprocessing and analysis.

[0111] An example of a prompt message is: "Predict the market potential of the new QR code payment function and suggest improvements. The market size is 500,000, the level of competition is high, and resource allocation is moderate."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The user enters project information into the terminal. This information includes market size, competitive landscape, resource allocation, and team structure. This information forms a project overview and is prepared as a dataset to be sent to the server in the next step.

[0115] Step 2:

[0116] The terminal sends the entered project information to the server. The server analyzes the received data and retrieves relevant market and competitor information from external sources. Here, APIs are used to retrieve data and form a rich dataset that supplements the project information.

[0117] Step 3:

[0118] The server preprocesses the received and retrieved data. Specifically, it normalizes text data, scales numerical data, and encodes categorical data. This unifies different data formats and creates a dataset that can be processed by generative AI models.

[0119] Step 4:

[0120] The server inputs pre-processed data into a generating AI model to predict the probability of business success. This model is trained on historical business data, constructs a neural network as the data computation for prediction, and performs rapid analysis. The output is the probability of success.

[0121] Step 5:

[0122] The server, having obtained a success probability, generates business improvement suggestions based on that. Here, AI-powered data analysis reveals specific action plans, such as adjustments to marketing strategies and suggestions for functional improvements. This output is then formatted in a way that is usable by the user.

[0123] Step 6:

[0124] The server sends the generated improvement suggestions back to the terminal and presents them to the user. The user receives the suggested improvements and can adjust the project strategy. This allows the user to quickly take action to improve the quality of decision-making and increase the chances of project success.

[0125] 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.

[0126] This invention realizes a system that predicts the probability of success of a new business and provides improvement suggestions using an emotion engine. Users input basic information about the business via a terminal. This information includes market size, competitive landscape, resource allocation, and team composition. The input data is transmitted from the terminal to a server.

[0127] The server first analyzes the provided data and retrieves additional market and competitor information from external sources. This ensures that the user-entered information is supplemented with detailed and comprehensive data. All received data undergoes a preprocessing process and is converted into a unified format suitable for analysis by generative models.

[0128] Next, the server inputs the pre-processed data into a generative model to identify the probability of success for the new business and the associated success and risk factors. The generative model can analyze multimodal data and predict the probability of success with high accuracy.

[0129] This system also incorporates an emotion engine that analyzes user emotions. The emotion engine analyzes voice data and facial images obtained from the user to determine the user's emotional state. For example, if a user expresses anxiety about a particular proposal, the emotion engine uses that information to adjust the proposal and improve it to a form that is more likely to be accepted by the user.

[0130] Subsequently, the server generates specific business improvement suggestions based on the success probability identified by the generative model and the analysis results of the emotion engine. These suggestions, which consist of strategies and action plans to increase the likelihood of success of the business plan, are provided to the user in real time via their device. The user can then use these results to adjust their business plan and provide additional information as needed.

[0131] For example, if a user is considering launching a product, the generative model predicts the probability of success based on market needs and competitive analysis. Simultaneously, the emotion engine analyzes the user's responses to determine which suggestions resonate most with them. In this way, users always receive accurate information and suggestions, enabling them to make decisions that improve the probability of business success.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The user inputs information about the new business from their device. This information includes market size, competitive landscape, resource allocation, and team composition. The device then sends the entered information to the server.

[0135] Step 2:

[0136] The server analyzes the information received from the user. It also collects additional data from external sources such as market databases and competitive analysis tools. This data helps to complement the background of the business plan.

[0137] Step 3:

[0138] The server preprocesses all collected data. Specifically, it cleans the data, standardizes the data format, and corrects for outliers. This ensures that the analysis model can operate with high accuracy.

[0139] Step 4:

[0140] The server inputs pre-processed data into a generative model. The generative model uses this data to predict the probability of success for a new business and extracts success and risk factors. Because the generative model can analyze diverse data, it can also analyze data that includes text, images, and audio.

[0141] Step 5:

[0142] The server activates an emotion engine to analyze the user's emotions. The terminal collects voice and facial images from the user and sends them to the server. The emotion engine uses this data to estimate the user's emotions.

[0143] Step 6:

[0144] By combining the analysis results from the emotion engine with the output from the generative model, the server generates specific suggestions for business improvement. This includes adjusting the suggestions according to the user's emotional state.

[0145] Step 7:

[0146] The server sends the predicted success rate, risk factors, success factors, and suggestions from the emotion engine to the terminal and presents them to the user. Based on these results, the user reviews the new business plan, provides additional information if necessary, or modifies the business plan.

[0147] (Example 2)

[0148] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0149] In new economic activities, there is a need to accurately predict the probability of success and to provide improvement suggestions that take into account the emotional state of users. However, conventional technologies do not have sufficient means to meet these requirements, and users are not being able to receive satisfactory information.

[0150] 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.

[0151] In this invention, the server includes means for collecting information on economic activities from information users and obtaining additional information from external information sources; means for preprocessing the collected information and unifying different information formats; and means for estimating the probability of success or failure of economic activities using a generative model based on the preprocessed information. As a result, users can receive more detailed and accurate success or failure predictions and make appropriate decisions based on those predictions.

[0152] An "information user" is an entity that uses a system to input information about economic activities and receives analysis results and suggestions.

[0153] "Economic activity" refers to commercial, business, or other economic projects, including activities in the market.

[0154] "Additional information" refers to data obtained from external sources that complements or expands upon the initial information provided by the user.

[0155] "Preprocessing" is the process of converting collected information into a standardized format and preparing it for data analysis.

[0156] A "generative model" is a model that uses machine learning or artificial intelligence to analyze data and includes mathematical or statistical methods to predict the probability of future events.

[0157] "Probability of success" is a numerical representation of the likelihood of a particular economic activity succeeding or failing.

[0158] "Psychological state" refers to the emotions and reactions that a user exhibits in response to specific information or suggestions.

[0159] An "improvement plan" is a specific strategy or idea for optimizing or improving a proposed economic activity, derived based on the probability of success or failure and psychological state.

[0160] This invention realizes a system that combines multiple hardware and software components to predict the probability of success for new economic activities and provide improvement suggestions. The main hardware components include a terminal that receives user input and a server that processes the data. The software components include a generative AI model that analyzes the data and an emotion engine that evaluates sentiment.

[0161] Users input basic business information using a terminal. This information includes market size, competitive landscape, resource allocation, and team structure. The entered data is sent from the terminal to the server. The server receives this data and retrieves additional market and competitive information from external sources. This supplements the information provided by the user with more specific and comprehensive data.

[0162] The server analyzes the received data, cleans and formats it, and converts it into a unified format that can be analyzed by the generative AI model. The generative AI model uses this pre-processed data to identify the probability of business success and related success and risk factors.

[0163] Furthermore, the emotion engine analyzes the user's voice data and facial images to determine the user's emotional state. For example, if a user expresses anxiety about a particular suggestion, the emotion engine adjusts the suggestion based on that information. This adjustment makes it possible to present suggestions in a way that is more likely to be accepted by the user.

[0164] The server ultimately integrates the success probabilities identified by the generation AI model with the analysis results of the emotion engine to generate specific business improvement suggestions. These suggestions are provided to the user in real time via the terminal, allowing the user to adjust their business plan based on this information.

[0165] As a concrete example, consider a scenario where a user is considering launching a new fitness app. The system analyzes market needs and competing apps to predict the success rate of the fitness app. It can also analyze user emotional responses to the proposed marketing strategy and suggest areas for improvement. An example of a prompt would be a specific instruction such as, "Please perform a market analysis and predict the success rate of a new fitness app."

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] The user enters basic business information through the terminal. This information includes market size, competitive landscape, resource allocation, and team structure. Once the user has finished entering the information, they press the submit button. The entered information is treated as input data sent from the terminal to the server.

[0169] Step 2:

[0170] The server receives data sent from the terminal. Based on this received data, it retrieves market data and competitor information from external sources. It connects to external databases using APIs to collect additional data. This additional information is used to supplement the user-provided information in detail. Input data consists of data from the user and data obtained from external sources, and by integrating these, comprehensive output data is formed.

[0171] Step 3:

[0172] The server preprocesses the integrated data. Preprocessing involves cleaning and formatting the data, unifying different data formats. This process includes imputing missing values ​​and correcting outliers. The server converts the input integrated data into an analyzable format and outputs it as a dataset that is easily processed by the generating AI model.

[0173] Step 4:

[0174] The server inputs pre-processed data into a generative AI model. The generative AI model analyzes this data and calculates the probability of success or failure of economic activities. Furthermore, it identifies success factors and risk factors. The results of this analysis are output as success probability and factor data.

[0175] Step 5:

[0176] The terminal receives emotional data (voice and facial images) from the user and sends it to the server. The server uses an emotion engine to analyze the input emotional data and determine the user's psychological state. The emotion engine combines speech recognition and image analysis technologies to output a numerical result representing the user's emotional state.

[0177] Step 6:

[0178] The server generates specific business improvement proposals based on calculated success / failure probabilities and emotional states. These proposals include strategies and action plans to maximize the likelihood of success. The final proposals are output to the terminal and provided to the user in real time.

[0179] Step 7:

[0180] Users review improvement suggestions presented on their devices. Based on this, they adjust their business plans and send feedback to the server, such as entering new information, to continuously improve the project.

[0181] (Application Example 2)

[0182] 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".

[0183] In today's advertising industry, predicting the success of new campaigns and advertising strategies presents a significant challenge. With numerous factors at play, identifying potential risk factors and quickly implementing effective corrective measures is crucial. However, the inability to comprehensively analyze market data and user responses necessitates efficient methods to increase advertising success rates.

[0184] 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.

[0185] In this invention, the server includes means for receiving business plan information from users and acquiring additional data from external information sources; processing means for preprocessing the received data and unifying different data formats; prediction means for predicting the probability of success using the preprocessed data; proposal means for generating strategic improvement proposals based on the probability of success; display means for presenting the generated proposals to users and updating the information in real time; and means for predicting the success of advertising campaigns and providing improvement proposals based on the results. This enables decision-making to increase the success rate of advertising campaigns.

[0186] A "user" is an individual or organization that uses the system to provide business plan information and data related to advertising campaigns, and to receive improvement suggestions.

[0187] "Business plan information" refers to detailed information provided by users to predict the probability of business success, including market data, competitor information, and resource allocation.

[0188] "External information sources" refer to external databases or information platforms that the system accesses to obtain additional market data or relevant information.

[0189] "Data preprocessing" is the process of standardizing the format of received data and preparing it so that it can be used in an analytical model.

[0190] "Predictive methods for predicting the probability of success" refer to methods for calculating the likelihood of success of a business or advertising campaign using statistical models or generative AI models.

[0191] A "strategized improvement proposal" is a proposal that outlines specific measures and action plans to enhance the effectiveness of a business or advertising campaign, based on the results of a success prediction.

[0192] A "display method that updates information in real time" is a method that provides users with immediate results of improvement suggestions and success predictions, and updates the information to the latest version as needed.

[0193] An "advertising campaign" is a series of promotional activities planned to advertise a specific product or service and attract market attention.

[0194] "Success prediction" refers to the act of making prediction calculations and analyses to estimate the success rate of new businesses or advertising campaigns.

[0195] The system for implementing this invention collects and analyzes information necessary to lead advertising campaigns to success and provides improvement suggestions to users. The system maximizes the effectiveness of advertising through the cooperation of the server, terminal, and user.

[0196] First, users input business plan information and advertising campaign details through a terminal. The terminal sends this information to a server. Based on the received data, the server retrieves additional market data from external sources and performs data preprocessing. This preprocessing unifies different data formats and prepares the data for analysis by a generative AI model.

[0197] The generative AI model analyzes diverse data to predict the probability of success for advertising campaigns. This model utilizes statistical analysis and machine learning techniques to achieve highly accurate predictions. Furthermore, the server uses a sentiment analysis engine to analyze user reactions. Based on these results, it generates and presents strategic improvement suggestions to users. These suggestions are provided to users in real time and are accessible at any time through their devices.

[0198] As a concrete example, when launching an advertising campaign for a new cosmetic product, the user inputs information on market trends and consumer preferences. Based on this information, the server predicts the probability of the advertisement's success and suggests specific improvement measures through a generative AI model. The user can then receive suggestions such as new taglines or changes to the visual style, and adjust the advertising campaign plan accordingly.

[0199] Examples of prompts for a generative AI model include the following:

[0200] "Please tell us the probability of success for this new cosmetics advertising campaign and provide suggestions for improvements to enhance its success. Market data and campaign specifications are as follows: Market data, Campaign specifications."

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] Users input business plan information and advertising campaign details through their devices. This information includes market data, competitor information, and campaign specifications. This data is then transmitted from the device to the server.

[0204] Step 2:

[0205] The server analyzes the data received from the user and retrieves additional market data from external sources. This ensures that the information provided by the user is supplemented with detailed and comprehensive data. The data received as input is pre-processed by the server and standardized into a consistent data format.

[0206] Step 3:

[0207] The server inputs pre-processed data into a generating AI model to predict the probability of success of an advertising campaign. At this stage, statistical models and machine learning algorithms are used to perform data calculations and output the success prediction results.

[0208] Step 4:

[0209] The server analyzes user responses using an emotion analysis engine. This involves inputting voice data and facial image data, and the emotion analysis algorithm identifies the user's emotional state. Based on this information, the server adjusts its suggestions.

[0210] Step 5:

[0211] The server generates strategic improvement suggestions based on the probability of success and the user's emotional state. These specific suggestions might include visual changes to advertisements or revisions to taglines. This information is output as suggestions and presented to the user.

[0212] Step 6:

[0213] The device displays improvement suggestions sent from the server to the user in real time. The user adjusts the advertising campaign based on the suggestions received and sends feedback to the server as needed, which leads to further data updates and re-evaluation of the suggestions.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] 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.

[0220] 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).

[0221] 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.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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".

[0230] This system is designed to predict the probability of success for new businesses and provide improvement suggestions. Users input project information using a terminal, including market size, competitive landscape, resource allocation, and team composition. The terminal then transmits the entered information to the server.

[0231] The server retrieves additional information from external sources based on the received data. This complements the user-provided project information with more detailed market reports and competitive analysis data. All collected data is pre-processed within the server and standardized into an analyzable format.

[0232] The server then provides the pre-processed data to a generative model to predict the probability of business success. The generative model is trained on historical new business data and can analyze multimodal data such as text, images, and audio. This identifies success and risk factors and calculates the overall probability of success.

[0233] Based on the success probability results, the server generates specific improvement suggestions to aim for business success. These include specific strategies for establishing a competitive advantage and adjustments to the marketing plan. The generated suggestions are sent to the terminal in real time and presented to the user.

[0234] For example, when a user develops a new mobile app, suggestions for specific UI / UX design improvements or feature additions are made based on market growth potential and the strength of competition. Because the information the user needs is provided immediately, decision-making can be done quickly.

[0235] In this way, users can leverage the highly accurate predictions and suggestions provided by the server to improve the probability of success for new businesses.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] Users input basic information about a new business via a terminal. This information includes market size, competitive landscape, resource allocation, and team structure. Once the user has finished entering the information, the terminal sends it to the server.

[0239] Step 2:

[0240] The server analyzes project information received from users and searches external sources to collect necessary additional data. This includes market reports and competitor activity. The collected data is used for internal server analysis.

[0241] Step 3:

[0242] The server preprocesses the received information and any additional data collected. This includes cleaning the data, standardizing the format, correcting outliers, and preparing it for analysis. This process is crucial for improving the accuracy of the analysis.

[0243] Step 4:

[0244] The server inputs pre-processed data into a generative model. This generative model is designed to predict the probability of success for new businesses and is capable of analyzing multimodal data. The model identifies success and risk factors and calculates an overall probability of success.

[0245] Step 5:

[0246] Based on the output from the generative model, the server generates specific improvement suggestions. These suggestions include strategies and action plans to increase the project's success rate. The generated suggestions serve as a reference for users when adjusting their business operations.

[0247] Step 6:

[0248] The server sends the success probability analysis results and improvement suggestions to the terminal, presenting them to the user in real time. The user can then use this information to input new details and update their business plan. This process enables accurate decision-making based on the latest data at all times.

[0249] (Example 1)

[0250] 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."

[0251] In planning new businesses, it is essential to efficiently analyze vast amounts of data and quickly and accurately predict the probability of success. However, current technology makes it difficult to integrate data from multiple sources and generate useful improvement suggestions in real time. Therefore, a system is needed that can quickly provide improvement suggestions to increase the success rate of new businesses.

[0252] 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.

[0253] In this invention, the server includes means for receiving activity information from users and acquiring additional information from external information sources, means for preprocessing the received information and unifying different information formats, and means for predicting the probability of success using a predictive model with the preprocessed information. This makes it possible to quickly and accurately analyze data and propose optimal improvement measures for the success of new businesses.

[0254] "User" refers to an individual or organization that uses the system to provide activity information and receive suggestions.

[0255] "Activity information" refers to data including market size, competitive landscape, resource allocation, and team composition related to projects and businesses.

[0256] "External information sources" refer to third-party databases and information services that the server accesses to supplement the information provided by the user.

[0257] "Preprocessing" refers to the process of cleaning or standardizing the data format of received or collected information in order to make it analyzable.

[0258] A "predictive model" refers to a computational model used to analyze collected information and estimate the probability of success for a new business.

[0259] A "generative model" refers to a machine learning model that is trained on historical data and can analyze multiple data formats such as text, images, and audio.

[0260] An "improvement suggestion" refers to specific measures and strategies aimed at increasing the success rate of a new business, based on the predicted probability of success.

[0261] "Information updates" refer to providing users with new data and suggestions immediately to support their decision-making process.

[0262] "Information in multiple formats" refers to a set of information that includes different data formats, such as text, images, and audio.

[0263] "Visualization" refers to the process of displaying data and proposals in the form of diagrams, charts, and other visual aids so that users can easily understand them.

[0264] This section describes an embodiment of this system. The user uses a terminal to input activity information related to the project. This activity information includes market size, competitive landscape, resource allocation, and team composition. The information entered by the user is transmitted from the terminal to the server.

[0265] The server accesses external information sources based on the received activity information and retrieves any necessary additional information. This interaction with external information sources involves using APIs to collect relevant data from databases and publicly available sources. The server preprocesses the received and collected information using the Python Pandas library. This includes handling missing values, cleaning the data, and standardizing the format.

[0266] The pre-processed information is input into a generative AI model built using TensorFlow or PyTorch to predict the probability of business success. The generative AI model has the ability to analyze data in multiple formats, such as text, images, and audio, and identify factors for success and risk.

[0267] Based on the predicted success rate, the server generates improvement suggestions for the success of the new business. These suggestions include revisions to specific strategies and marketing plans to strengthen competitive advantages. The server then formats the generated suggestions into a user-friendly format using natural language generation technology.

[0268] The server then sends the generated improvement suggestions to the terminal in real time. The terminal visualizes and presents the received suggestions to the user, enabling the user to make quick decisions.

[0269] For example, if a user is developing a new smartphone application, the system can assess market growth potential and competitive strength, and suggest improvements to specific user interfaces and user experience (UI / UX). The following prompts can be provided to encourage the user to use the system:

[0270] Please provide project information regarding the mobile app currently under development as a new business venture. Please include details such as market size, competitive landscape, and team structure.

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] Users input activity information via a terminal. This information includes market size, competitive landscape, resource allocation, and team composition. Once input is complete, the terminal verifies the entered information, encodes it in the appropriate data format, and sends it to the server. The output of the terminal for the input data is the activity information sent to the server.

[0274] Step 2:

[0275] The server receives activity information sent from the terminal. Based on the received data, the server accesses external information sources to collect necessary additional information. In this process, the server uses APIs to query external databases and retrieve market reports and competitive analysis data. The input data is activity information, and the output data is supplementary, detailed information.

[0276] Step 3:

[0277] The server preprocesses the collected information, including imputing missing values, cleaning the data, and standardizing the format. This process uses the Python Pandas library to convert the data into a parseable format. The input data is imputed information, while the output data is preprocessed data.

[0278] Step 4:

[0279] The server inputs pre-processed data into a generative AI model. This model, built using TensorFlow or PyTorch, analyzes data in multiple formats and predicts the probability of business success. Because the generative AI model is trained on historical data, it has the ability to identify success factors and risk factors. The input data is pre-processed data, and the output data is the result of the success probability.

[0280] Step 5:

[0281] Based on the success probability results, the server generates specific improvement suggestions. These suggestions include revising strategies and marketing plans to strengthen competitive advantage. Natural language generation technology is used to format the suggestions in a user-friendly manner. The input data consists of the success probability and identified factors, while the output data consists of improvement suggestions for the user.

[0282] Step 6:

[0283] The server transmits the generated improvement proposals to the terminal in real time. The terminal receives the proposals and visually presents them to the user. Thus, the user can immediately check the information and make a decision quickly. The input data is the generated proposals, and the output data is the visualized information presented to the user.

[0284] (Application Example 1)

[0285] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0286] In modern times, it is required to appropriately evaluate the success probability of starting a new business or project in a specific area and quickly execute a differentiation strategy in a highly competitive market. However, in the conventional method, the collection and analysis of information are fragmentary and inefficient. Therefore, a system for supporting business success through rapid and continuous evaluation and improvement is necessary.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0288] In this invention, the server includes means for receiving project information from the user and obtaining additional information from an external information source, means for preprocessing the received data and unifying different data formats, and means for executing the optimization of functions and the differentiation strategy in a specific area based on the proposed improvement plans. Thereby, it becomes possible to improve the success probability of the business through continuous evaluation and feedback in a specific area.

[0289] "Project information" refers to information such as the market scale, competition situation, resource allocation, and team composition that the user needs to provide when starting a new business or project.

[0290] "External information sources" refer to data obtained from external sources, such as market reports, competitive analyses, and economic indicators, that are referenced to complement project information.

[0291] A "generative model" is a machine learning algorithm that analyzes multimodal input data to predict the probability of business success.

[0292] "Probability of success" is an evaluation metric that indicates the likelihood of a newly proposed business or project succeeding in the market.

[0293] An "improvement suggestion" is information that proposes modifications to specific strategies or measures in order to increase the probability of business success.

[0294] A "specific domain" refers to a unique market or technological area in various industries and fields, primarily such as electronic payment services.

[0295] "Functional optimization" refers to optimizing the functionality of services or products provided in a specific area to maximize their effectiveness.

[0296] A "differentiation strategy" is a tactic to secure a competitive advantage by developing services or products in the market that have unique features different from those of competitors.

[0297] "Continuous evaluation" refers to an analytical process that continuously reflects project progress and market trends in real time.

[0298] "Providing feedback" is the process by which the system returns information to users about the status of the business and areas for improvement.

[0299] This invention is a system that predicts the probability of success of a new business in a specific domain and provides optimal improvement suggestions. The system begins with the user sending project information from their terminal to a server. This project information includes market size, competitive landscape, resource allocation, and team composition. After receiving this information, the server retrieves relevant data from external sources.

[0300] The server integrates this data and uses a generative AI model to analyze it. This model is trained on past new business data and predicts the probability of success through multimodal data analysis. Based on the analysis results, it generates specific differentiation strategies and functional optimization suggestions to promote project success. The server presents these suggestions to the user's terminal in real time, helping users make immediate decisions.

[0301] In this embodiment, a specific example is a small or medium-sized enterprise (SME) planning to introduce a new QR code payment function in the electronic payment service industry. By using the proposed system, the company can conduct a market assessment based on the entered project information and immediately obtain effective strategies for differentiating itself from competitors. Furthermore, users can quickly modify and implement their strategies by utilizing the feedback provided in real time.

[0302] For processing specific generative models, programming languages ​​and libraries such as Python and TensorFlow can be used. The server will run on a computer infrastructure with sufficient performance for data preprocessing and analysis.

[0303] An example of a prompt message is: "Predict the market potential of the new QR code payment function and suggest improvements. The market size is 500,000, the level of competition is high, and resource allocation is moderate."

[0304] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0305] Step 1:

[0306] The user inputs project information into the terminal. The information to be input includes market size, competitive situation, resource allocation, and team composition. These information form the outline of the project and are prepared as a dataset to be sent to the server in the next step.

[0307] Step 2:

[0308] The terminal sends the input project information to the server. The server analyzes the received data and obtains relevant market data and competitive information from external information sources. Here, the API is used to obtain data, forming a rich dataset to supplement the project information.

[0309] Step 3:

[0310] The server preprocesses the received and obtained data. Specifically, it performs normalization of text data, scaling of numerical data, and encoding of categorical data. This unifies different data formats and creates a dataset that can be processed by the generated AI model.

[0311] Step 4:

[0312] The server inputs the preprocessed data into the generated AI model to predict the success probability of the business. This model is trained from past business data, constructs a neural network for data calculation for prediction, and performs analysis quickly. The success probability is obtained as the output.

[0313] Step 5:

[0314] The server that has obtained the success probability generates improvement proposals for the business based on it. Here, through AI-based data analysis, specific action plans such as adjustment of marketing strategies and improvement plans for functions are shown. This output is formatted in a form that can be used by the user.

[0315] Step 6:

[0316] The server sends the generated improvement suggestions back to the terminal and presents them to the user. The user receives the suggested improvements and can adjust the project strategy. This allows the user to quickly take action to improve the quality of decision-making and increase the chances of project success.

[0317] 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.

[0318] This invention realizes a system that predicts the probability of success of a new business and provides improvement suggestions using an emotion engine. Users input basic information about the business via a terminal. This information includes market size, competitive landscape, resource allocation, and team composition. The input data is transmitted from the terminal to a server.

[0319] The server first analyzes the provided data and retrieves additional market and competitor information from external sources. This ensures that the user-entered information is supplemented with detailed and comprehensive data. All received data undergoes a preprocessing process and is converted into a unified format suitable for analysis by generative models.

[0320] Next, the server inputs the pre-processed data into a generative model to identify the probability of success for the new business and the associated success and risk factors. The generative model can analyze multimodal data and predict the probability of success with high accuracy.

[0321] This system also incorporates an emotion engine that analyzes user emotions. The emotion engine analyzes voice data and facial images obtained from the user to determine the user's emotional state. For example, if a user expresses anxiety about a particular proposal, the emotion engine uses that information to adjust the proposal and improve it to a form that is more likely to be accepted by the user.

[0322] Subsequently, the server generates specific business improvement suggestions based on the success probability identified by the generative model and the analysis results of the emotion engine. These suggestions, which consist of strategies and action plans to increase the likelihood of success of the business plan, are provided to the user in real time via their device. The user can then use these results to adjust their business plan and provide additional information as needed.

[0323] For example, if a user is considering launching a product, the generative model predicts the probability of success based on market needs and competitive analysis. Simultaneously, the emotion engine analyzes the user's responses to determine which suggestions resonate most with them. In this way, users always receive accurate information and suggestions, enabling them to make decisions that improve the probability of business success.

[0324] The following describes the processing flow.

[0325] Step 1:

[0326] The user inputs information about the new business from their device. This information includes market size, competitive landscape, resource allocation, and team composition. The device then sends the entered information to the server.

[0327] Step 2:

[0328] The server analyzes the information received from the user. It also collects additional data from external sources such as market databases and competitive analysis tools. This data helps to complement the background of the business plan.

[0329] Step 3:

[0330] The server preprocesses all collected data. Specifically, it cleans the data, standardizes the data format, and corrects for outliers. This ensures that the analysis model can operate with high accuracy.

[0331] Step 4:

[0332] The server inputs pre-processed data into a generative model. The generative model uses this data to predict the probability of success for a new business and extracts success and risk factors. Because the generative model can analyze diverse data, it can also analyze data that includes text, images, and audio.

[0333] Step 5:

[0334] The server activates an emotion engine to analyze the user's emotions. The terminal collects voice and facial images from the user and sends them to the server. The emotion engine uses this data to estimate the user's emotions.

[0335] Step 6:

[0336] By combining the analysis results from the emotion engine with the output from the generative model, the server generates specific suggestions for business improvement. This includes adjusting the suggestions according to the user's emotional state.

[0337] Step 7:

[0338] The server sends the predicted success rate, risk factors, success factors, and suggestions from the emotion engine to the terminal and presents them to the user. Based on these results, the user reviews the new business plan, provides additional information if necessary, or modifies the business plan.

[0339] (Example 2)

[0340] 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".

[0341] In new economic activities, there is a need to accurately predict the probability of success and to provide improvement suggestions that take into account the emotional state of users. However, conventional technologies do not have sufficient means to meet these requirements, and users are not being able to receive satisfactory information.

[0342] 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.

[0343] In this invention, the server includes means for collecting information on economic activities from information users and obtaining additional information from external information sources; means for preprocessing the collected information and unifying different information formats; and means for estimating the probability of success or failure of economic activities using a generative model based on the preprocessed information. As a result, users can receive more detailed and accurate success or failure predictions and make appropriate decisions based on those predictions.

[0344] An "information user" is an entity that uses a system to input information about economic activities and receives analysis results and suggestions.

[0345] "Economic activity" refers to commercial, business, or other economic projects, including activities in the market.

[0346] "Additional information" refers to data obtained from external sources that complements or expands upon the initial information provided by the user.

[0347] "Preprocessing" is the process of converting collected information into a standardized format and preparing it for data analysis.

[0348] A "generative model" is a model that uses machine learning or artificial intelligence to analyze data and includes mathematical or statistical methods to predict the probability of future events.

[0349] "Probability of success" is a numerical representation of the likelihood of a particular economic activity succeeding or failing.

[0350] "Psychological state" refers to the emotions and reactions that a user exhibits in response to specific information or suggestions.

[0351] An "improvement plan" is a specific strategy or idea for optimizing or improving a proposed economic activity, derived based on the probability of success or failure and psychological state.

[0352] This invention realizes a system that combines multiple hardware and software components to predict the probability of success for new economic activities and provide improvement suggestions. The main hardware components include a terminal that receives user input and a server that processes the data. The software components include a generative AI model that analyzes the data and an emotion engine that evaluates sentiment.

[0353] Users input basic business information using a terminal. This information includes market size, competitive landscape, resource allocation, and team structure. The entered data is sent from the terminal to the server. The server receives this data and retrieves additional market and competitive information from external sources. This supplements the information provided by the user with more specific and comprehensive data.

[0354] The server analyzes the received data, cleans and formats it, and converts it into a unified format that can be analyzed by the generative AI model. The generative AI model uses this pre-processed data to identify the probability of business success and related success and risk factors.

[0355] Furthermore, the emotion engine analyzes the user's voice data and facial images to determine the user's emotional state. For example, if a user expresses anxiety about a particular suggestion, the emotion engine adjusts the suggestion based on that information. This adjustment makes it possible to present suggestions in a way that is more likely to be accepted by the user.

[0356] The server ultimately integrates the success probabilities identified by the generation AI model with the analysis results of the emotion engine to generate specific business improvement suggestions. These suggestions are provided to the user in real time via the terminal, allowing the user to adjust their business plan based on this information.

[0357] As a concrete example, consider a scenario where a user is considering launching a new fitness app. The system analyzes market needs and competing apps to predict the success rate of the fitness app. It can also analyze user emotional responses to the proposed marketing strategy and suggest areas for improvement. An example of a prompt would be a specific instruction such as, "Please perform a market analysis and predict the success rate of a new fitness app."

[0358] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0359] Step 1:

[0360] The user enters basic business information through the terminal. This information includes market size, competitive landscape, resource allocation, and team structure. Once the user has finished entering the information, they press the submit button. The entered information is treated as input data sent from the terminal to the server.

[0361] Step 2:

[0362] The server receives data sent from the terminal. Based on this received data, it retrieves market data and competitor information from external sources. It connects to external databases using APIs to collect additional data. This additional information is used to supplement the user-provided information in detail. Input data consists of data from the user and data obtained from external sources, and by integrating these, comprehensive output data is formed.

[0363] Step 3:

[0364] The server preprocesses the integrated data. Preprocessing involves cleaning and formatting the data, unifying different data formats. This process includes imputing missing values ​​and correcting outliers. The server converts the input integrated data into an analyzable format and outputs it as a dataset that is easily processed by the generating AI model.

[0365] Step 4:

[0366] The server inputs pre-processed data into a generative AI model. The generative AI model analyzes this data and calculates the probability of success or failure of economic activities. Furthermore, it identifies success factors and risk factors. The results of this analysis are output as success probability and factor data.

[0367] Step 5:

[0368] The terminal receives emotional data (voice and facial images) from the user and sends it to the server. The server uses an emotion engine to analyze the input emotional data and determine the user's psychological state. The emotion engine combines speech recognition and image analysis technologies to output a numerical result representing the user's emotional state.

[0369] Step 6:

[0370] The server generates specific business improvement proposals based on calculated success / failure probabilities and emotional states. These proposals include strategies and action plans to maximize the likelihood of success. The final proposal is output to the terminal and provided to the user in real time.

[0371] Step 7:

[0372] Users review improvement suggestions presented on their devices. Based on this, they adjust their business plans and send feedback to the server, such as entering new information, to continuously improve the project.

[0373] (Application Example 2)

[0374] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0375] In today's advertising industry, predicting the success of new campaigns and advertising strategies presents a significant challenge. With numerous factors at play, identifying potential risk factors and quickly implementing effective corrective measures is crucial. However, the inability to comprehensively analyze market data and user responses necessitates efficient methods to increase advertising success rates.

[0376] 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.

[0377] In this invention, the server includes means for receiving business plan information from users and acquiring additional data from external information sources; processing means for preprocessing the received data and unifying different data formats; prediction means for predicting the probability of success using the preprocessed data; proposal means for generating strategic improvement proposals based on the probability of success; display means for presenting the generated proposals to users and updating the information in real time; and means for predicting the success of advertising campaigns and providing improvement proposals based on the results. This enables decision-making to increase the success rate of advertising campaigns.

[0378] A "user" is an individual or organization that uses the system to provide business plan information and data related to advertising campaigns, and to receive improvement suggestions.

[0379] "Business plan information" refers to detailed information provided by users to predict the probability of business success, including market data, competitor information, and resource allocation.

[0380] "External information sources" refer to external databases or information platforms that the system accesses to obtain additional market data or relevant information.

[0381] "Data preprocessing" is the process of standardizing the format of received data and preparing it so that it can be used in an analytical model.

[0382] "Predictive methods for predicting the probability of success" refer to methods for calculating the likelihood of success of a business or advertising campaign using statistical models or generative AI models.

[0383] A "strategized improvement proposal" is a proposal that, based on success predictions, outlines specific measures and action plans to enhance the effectiveness of a business or advertising campaign.

[0384] A "display method that updates information in real time" is a method that provides users with immediate results of improvement suggestions and success predictions, and updates the information to the latest version as needed.

[0385] An "advertising campaign" is a series of promotional activities planned to advertise a specific product or service and attract market attention.

[0386] "Success prediction" refers to the act of making prediction calculations and analyses to estimate the success rate of new businesses or advertising campaigns.

[0387] The system for implementing this invention collects and analyzes information necessary to lead advertising campaigns to success and provides improvement suggestions to users. The system maximizes the effectiveness of advertising through the collaboration of the server, terminal, and user.

[0388] First, users input business plan information and advertising campaign details through a terminal. The terminal sends this information to a server. Based on the received data, the server retrieves additional market data from external sources and performs data preprocessing. This preprocessing unifies different data formats and prepares the data for analysis by a generative AI model.

[0389] The generative AI model analyzes diverse data to predict the probability of success for advertising campaigns. This model utilizes statistical analysis and machine learning techniques to achieve highly accurate predictions. Furthermore, the server uses a sentiment analysis engine to analyze user reactions. Based on these results, it generates and presents strategic improvement suggestions to users. These suggestions are provided to users in real time and are accessible at any time through their devices.

[0390] As a concrete example, when launching an advertising campaign for a new cosmetic product, the user inputs information on market trends and consumer preferences. Based on this information, the server predicts the probability of the advertisement's success and suggests specific improvement measures through a generative AI model. The user can then receive suggestions such as new taglines or changes to the visual style, and adjust the advertising campaign plan accordingly.

[0391] Examples of prompts for a generative AI model include the following:

[0392] "Please tell us the probability of success for this new cosmetics advertising campaign and provide suggestions for improvements to enhance its success. Market data and campaign specifications are as follows: Market data, Campaign specifications."

[0393] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0394] Step 1:

[0395] Users input business plan information and advertising campaign details through their devices. This information includes market data, competitor information, and campaign specifications. This data is then transmitted from the device to the server.

[0396] Step 2:

[0397] The server analyzes the data received from the user and retrieves additional market data from external sources. This ensures that the information provided by the user is supplemented with detailed and comprehensive data. The data received as input is pre-processed by the server and standardized into a consistent data format.

[0398] Step 3:

[0399] The server inputs pre-processed data into a generating AI model to predict the probability of success of an advertising campaign. At this stage, statistical models and machine learning algorithms are used to perform data calculations and output the success prediction results.

[0400] Step 4:

[0401] The server analyzes user responses using an emotion analysis engine. This involves inputting voice data and facial image data, and the emotion analysis algorithm identifies the user's emotional state. Based on this information, the server adjusts its suggestions.

[0402] Step 5:

[0403] The server generates strategic improvement suggestions based on the probability of success and the user's emotional state. These specific suggestions might include visual changes to advertisements or revisions to taglines. This information is output as suggestions and presented to the user.

[0404] Step 6:

[0405] The device displays improvement suggestions sent from the server to the user in real time. The user adjusts the advertising campaign based on the suggestions received and sends feedback to the server as needed, which leads to further data updates and re-evaluation of the suggestions.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] [Third Embodiment]

[0410] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0411] 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.

[0412] 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).

[0413] 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.

[0414] 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.

[0415] 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).

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] 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".

[0422] This system is designed to predict the probability of success for new businesses and provide improvement suggestions. Users input project information using a terminal, including market size, competitive landscape, resource allocation, and team composition. The terminal then transmits the entered information to the server.

[0423] The server retrieves additional information from external sources based on the received data. This complements the user-provided project information with more detailed market reports and competitive analysis data. All collected data is pre-processed within the server and standardized into an analyzable format.

[0424] The server then provides the pre-processed data to a generative model to predict the probability of business success. The generative model is trained on historical new business data and can analyze multimodal data such as text, images, and audio. This identifies success and risk factors and calculates the overall probability of success.

[0425] Based on the success probability results, the server generates specific improvement suggestions to aim for business success. These include specific strategies for establishing a competitive advantage and adjustments to the marketing plan. The generated suggestions are sent to the terminal in real time and presented to the user.

[0426] For example, when a user develops a new mobile app, suggestions for specific UI / UX design improvements or feature additions are made based on market growth potential and the strength of competition. Because the information the user needs is provided immediately, decision-making can be done quickly.

[0427] In this way, users can leverage the highly accurate predictions and suggestions provided by the server to improve the probability of success for new businesses.

[0428] The following describes the processing flow.

[0429] Step 1:

[0430] Users input basic information about a new business via a terminal. This information includes market size, competitive landscape, resource allocation, and team structure. Once the user has finished entering the information, the terminal sends it to the server.

[0431] Step 2:

[0432] The server analyzes project information received from users and searches external sources to collect necessary additional data. This includes market reports and competitor activity. The collected data is used for internal server analysis.

[0433] Step 3:

[0434] The server preprocesses the received information and any additional data collected. This includes cleaning the data, standardizing the format, correcting outliers, and preparing it for analysis. This process is crucial for improving the accuracy of the analysis.

[0435] Step 4:

[0436] The server inputs pre-processed data into a generative model. This generative model is designed to predict the probability of success for new businesses and is capable of analyzing multimodal data. The model identifies success and risk factors and calculates an overall probability of success.

[0437] Step 5:

[0438] Based on the output from the generative model, the server generates specific improvement suggestions. These suggestions include strategies and action plans to increase the project's success rate. The generated suggestions serve as a reference for users when adjusting their business operations.

[0439] Step 6:

[0440] The server sends the success probability analysis results and improvement suggestions to the terminal, presenting them to the user in real time. The user can then use this information to input new details and update their business plan. This process enables accurate decision-making based on the latest data at all times.

[0441] (Example 1)

[0442] 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."

[0443] In planning new businesses, it is essential to efficiently analyze vast amounts of data and quickly and accurately predict the probability of success. However, current technology makes it difficult to integrate data from multiple sources and generate useful improvement suggestions in real time. Therefore, a system is needed that can quickly provide improvement suggestions to increase the success rate of new businesses.

[0444] 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.

[0445] In this invention, the server includes means for receiving activity information from users and acquiring additional information from external information sources, means for preprocessing the received information and unifying different information formats, and means for predicting the probability of success using a predictive model with the preprocessed information. This makes it possible to quickly and accurately analyze data and propose optimal improvement measures for the success of new businesses.

[0446] "User" refers to an individual or organization that uses the system to provide activity information and receive suggestions.

[0447] "Activity information" refers to data including market size, competitive landscape, resource allocation, and team composition related to projects and businesses.

[0448] "External information sources" refer to third-party databases and information services that the server accesses to supplement the information provided by the user.

[0449] "Preprocessing" refers to the process of cleaning or standardizing the data format of received or collected information in order to make it analyzable.

[0450] A "predictive model" refers to a computational model used to analyze collected information and estimate the probability of success for a new business.

[0451] A "generative model" refers to a machine learning model that is trained on historical data and can analyze multiple data formats such as text, images, and audio.

[0452] An "improvement suggestion" refers to specific measures and strategies aimed at increasing the success rate of a new business, based on the predicted probability of success.

[0453] "Information updates" refer to providing users with new data and suggestions immediately to support their decision-making process.

[0454] "Information in multiple formats" refers to a set of information that includes different data formats, such as text, images, and audio.

[0455] "Visualization" refers to the process of displaying data and proposals in the form of diagrams, charts, and other visual aids so that users can easily understand them.

[0456] This section describes an embodiment of this system. The user uses a terminal to input activity information related to the project. This activity information includes market size, competitive landscape, resource allocation, and team composition. The information entered by the user is transmitted from the terminal to the server.

[0457] The server accesses external information sources based on the received activity information and retrieves any necessary additional information. This interaction with external information sources involves using APIs to collect relevant data from databases and publicly available sources. The server preprocesses the received and collected information using the Python Pandas library. This includes handling missing values, cleaning the data, and standardizing the format.

[0458] The pre-processed information is input into a generative AI model built using TensorFlow or PyTorch to predict the probability of business success. The generative AI model has the ability to analyze data in multiple formats, such as text, images, and audio, and identify success factors and risk factors.

[0459] Based on the predicted success probability, the server generates improvement suggestions for the success of the new business. These suggestions include revisions to specific strategies and marketing plans to strengthen competitive advantages. The server then formats the generated suggestions into a user-friendly format using natural language generation technology.

[0460] The server then sends the generated improvement suggestions to the terminal in real time. The terminal visualizes and presents the received suggestions to the user, enabling the user to make quick decisions.

[0461] For example, if a user is developing a new smartphone application, the system can assess market growth potential and competitive strength, and suggest improvements to specific user interfaces and user experience (UI / UX). The following prompts can be provided to encourage the user to use the system:

[0462] Please provide project information regarding the mobile app currently under development as a new business venture. Please include details such as market size, competitive landscape, and team structure.

[0463] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0464] Step 1:

[0465] Users input activity information via a terminal. This information includes market size, competitive landscape, resource allocation, and team composition. Once input is complete, the terminal verifies the entered information, encodes it in the appropriate data format, and sends it to the server. The output of the terminal for the input data is the activity information sent to the server.

[0466] Step 2:

[0467] The server receives activity information sent from the terminal. Based on the received data, the server accesses external information sources to collect necessary additional information. In this process, the server uses APIs to query external databases and retrieve market reports and competitive analysis data. The input data is activity information, and the output data is supplementary, detailed information.

[0468] Step 3:

[0469] The server preprocesses the collected information, including imputing missing values, cleaning the data, and standardizing the format. This process uses the Python Pandas library to convert the data into a parseable format. The input data is imputed information, while the output data is preprocessed data.

[0470] Step 4:

[0471] The server inputs pre-processed data into a generative AI model. This model, built using TensorFlow or PyTorch, analyzes data in multiple formats and predicts the probability of business success. Because the generative AI model is trained on historical data, it has the ability to identify success factors and risk factors. The input data is pre-processed data, and the output data is the result of the success probability.

[0472] Step 5:

[0473] Based on the success probability results, the server generates specific improvement suggestions. These suggestions include revising strategies and marketing plans to strengthen competitive advantage. Natural language generation technology is used to format the suggestions in a user-friendly manner. The input data consists of the success probability and identified factors, while the output data consists of improvement suggestions for the user.

[0474] Step 6:

[0475] The server sends the generated improvement suggestions to the terminal in real time. The terminal receives the suggestions and presents them to the user in a visualized format. This allows the user to immediately review the information and make quick decisions. The input data is the generated suggestions, and the output data is the visualized information presented to the user.

[0476] (Application Example 1)

[0477] 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."

[0478] In today's world, there is a need to appropriately evaluate the success rate of new business launches and projects in specific areas, and to rapidly implement differentiation strategies in highly competitive markets. However, traditional methods of information gathering and analysis have been fragmented and inefficient. Therefore, a system is needed to support business success through rapid and continuous evaluation and improvement.

[0479] 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.

[0480] In this invention, the server includes means for receiving project information from users and obtaining additional information from external sources, means for preprocessing the received data and unifying different data formats, and means for implementing optimization and differentiation strategies for functions in specific areas based on proposed improvements. This makes it possible to improve the probability of business success through continuous evaluation and feedback in specific areas.

[0481] "Project information" refers to information that users need to provide when starting a new business or project, such as market size, competitive landscape, resource allocation, and team composition.

[0482] "External information sources" refer to data obtained from external sources, such as market reports, competitive analyses, and economic indicators, that are referenced to complement project information.

[0483] A "generative model" is a machine learning algorithm that analyzes multimodal input data to predict the probability of business success.

[0484] "Probability of success" is an evaluation metric that indicates the likelihood of a newly proposed business or project succeeding in the market.

[0485] An "improvement suggestion" is information that proposes modifications to specific strategies or measures in order to increase the probability of business success.

[0486] A "specific domain" refers to a unique market or technological area in various industries and fields, primarily such as electronic payment services.

[0487] "Functional optimization" refers to optimizing the functionality of services or products provided in a specific area to maximize their effectiveness.

[0488] A "differentiation strategy" is a tactic to secure a competitive advantage by developing services or products in the market that have unique features different from those of competitors.

[0489] "Continuous evaluation" refers to an analytical process that continuously reflects project progress and market trends in real time.

[0490] "Providing feedback" is the process by which the system returns information to users about the status of the business and areas for improvement.

[0491] This invention is a system that predicts the probability of success of a new business in a specific domain and provides optimal improvement suggestions. The system begins with the user sending project information from their terminal to a server. This project information includes market size, competitive landscape, resource allocation, and team composition. After receiving this information, the server retrieves relevant data from external sources.

[0492] The server integrates this data and uses a generative AI model to analyze it. This model is trained on past new business data and predicts the probability of success through multimodal data analysis. Based on the analysis results, it generates specific differentiation strategies and functional optimization suggestions to promote project success. The server presents these suggestions to the user's terminal in real time, helping users make immediate decisions.

[0493] In this embodiment, a specific example is a small or medium-sized enterprise (SME) planning to introduce a new QR code payment function in the electronic payment service industry. By using the proposed system, the company can conduct a market assessment based on the entered project information and immediately obtain effective strategies for differentiating itself from competitors. Furthermore, users can quickly modify and implement their strategies by utilizing the feedback provided in real time.

[0494] For processing specific generative models, programming languages ​​and libraries such as Python and TensorFlow can be used. The server will run on a computer infrastructure with sufficient performance for data preprocessing and analysis.

[0495] An example of a prompt message is: "Predict the market potential of the new QR code payment function and suggest improvements. The market size is 500,000, the level of competition is high, and resource allocation is moderate."

[0496] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0497] Step 1:

[0498] The user enters project information into the terminal. This information includes market size, competitive landscape, resource allocation, and team structure. This information forms a project overview and is prepared as a dataset to be sent to the server in the next step.

[0499] Step 2:

[0500] The terminal sends the entered project information to the server. The server analyzes the received data and retrieves relevant market and competitor information from external sources. Here, APIs are used to retrieve data and form a rich dataset that supplements the project information.

[0501] Step 3:

[0502] The server preprocesses the received and retrieved data. Specifically, it normalizes text data, scales numerical data, and encodes categorical data. This unifies different data formats and creates a dataset that can be processed by generative AI models.

[0503] Step 4:

[0504] The server inputs pre-processed data into a generating AI model to predict the probability of business success. This model is trained on historical business data, constructs a neural network as the data computation for prediction, and performs rapid analysis. The output is the probability of success.

[0505] Step 5:

[0506] The server, having obtained a success probability, generates business improvement suggestions based on that. Here, AI-powered data analysis reveals specific action plans, such as adjustments to marketing strategies and suggestions for functional improvements. This output is then formatted in a way that is usable by the user.

[0507] Step 6:

[0508] The server sends the generated improvement suggestions back to the terminal and presents them to the user. The user receives the suggested improvements and can adjust the project strategy. This allows the user to quickly take action to improve the quality of decision-making and increase the chances of project success.

[0509] 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.

[0510] This invention realizes a system that predicts the probability of success of a new business and provides improvement suggestions using an emotion engine. Users input basic information about the business via a terminal. This information includes market size, competitive landscape, resource allocation, and team composition. The input data is transmitted from the terminal to a server.

[0511] The server first analyzes the provided data and retrieves additional market and competitor information from external sources. This ensures that the user-entered information is supplemented with detailed and comprehensive data. All received data undergoes a preprocessing process and is converted into a unified format suitable for analysis by generative models.

[0512] Next, the server inputs the pre-processed data into a generative model to identify the probability of success for the new business and the associated success and risk factors. The generative model can analyze multimodal data and predict the probability of success with high accuracy.

[0513] This system also incorporates an emotion engine that analyzes user emotions. The emotion engine analyzes voice data and facial images obtained from the user to determine the user's emotional state. For example, if a user expresses anxiety about a particular proposal, the emotion engine uses that information to adjust the proposal and improve it to a form that is more likely to be accepted by the user.

[0514] Subsequently, the server generates specific business improvement suggestions based on the success probability identified by the generative model and the analysis results of the emotion engine. These suggestions, which consist of strategies and action plans to increase the likelihood of success of the business plan, are provided to the user in real time via their device. The user can then use these results to adjust their business plan and provide additional information as needed.

[0515] For example, if a user is considering launching a product, the generative model predicts the probability of success based on market needs and competitive analysis. Simultaneously, the emotion engine analyzes the user's responses to determine which suggestions resonate most with them. In this way, users always receive accurate information and suggestions, enabling them to make decisions that improve the probability of business success.

[0516] The following describes the processing flow.

[0517] Step 1:

[0518] The user inputs information about the new business from their device. This information includes market size, competitive landscape, resource allocation, and team composition. The device then sends the entered information to the server.

[0519] Step 2:

[0520] The server analyzes the information received from the user. It also collects additional data from external sources such as market databases and competitive analysis tools. This data helps to complement the background of the business plan.

[0521] Step 3:

[0522] The server preprocesses all collected data. Specifically, it cleans the data, standardizes the data format, and corrects for outliers. This ensures that the analysis model can operate with high accuracy.

[0523] Step 4:

[0524] The server inputs pre-processed data into a generative model. The generative model uses this data to predict the probability of success for a new business and extracts success and risk factors. Because the generative model can analyze diverse data, it can also analyze data that includes text, images, and audio.

[0525] Step 5:

[0526] The server activates an emotion engine to analyze the user's emotions. The terminal collects voice and facial images from the user and sends them to the server. The emotion engine uses this data to estimate the user's emotions.

[0527] Step 6:

[0528] By combining the analysis results from the emotion engine with the output from the generative model, the server generates specific suggestions for business improvement. This includes adjusting the suggestions according to the user's emotional state.

[0529] Step 7:

[0530] The server sends the predicted success rate, risk factors, success factors, and suggestions from the emotion engine to the terminal and presents them to the user. Based on these results, the user reviews the new business plan, provides additional information if necessary, or modifies the business plan.

[0531] (Example 2)

[0532] 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."

[0533] In new economic activities, there is a need to accurately predict the probability of success and to provide improvement suggestions that take into account the emotional state of users. However, conventional technologies do not have sufficient means to meet these requirements, and users are not being able to receive satisfactory information.

[0534] 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.

[0535] In this invention, the server includes means for collecting information on economic activities from information users and obtaining additional information from external information sources; means for preprocessing the collected information and unifying different information formats; and means for estimating the probability of success or failure of economic activities using a generative model based on the preprocessed information. As a result, users can receive more detailed and accurate success or failure predictions and make appropriate decisions based on those predictions.

[0536] An "information user" is an entity that uses a system to input information about economic activities and receives analysis results and suggestions.

[0537] "Economic activity" refers to commercial, business, or other economic projects, including activities in the market.

[0538] "Additional information" refers to data obtained from external sources that complements or expands upon the initial information provided by the user.

[0539] "Preprocessing" is the process of converting collected information into a standardized format and preparing it for data analysis.

[0540] A "generative model" is a model that uses machine learning or artificial intelligence to analyze data and includes mathematical or statistical methods to predict the probability of future events.

[0541] "Probability of success" is a numerical representation of the likelihood of a particular economic activity succeeding or failing.

[0542] "Psychological state" refers to the emotions and reactions that a user exhibits in response to specific information or suggestions.

[0543] An "improvement plan" is a specific strategy or idea for optimizing or improving a proposed economic activity, derived based on the probability of success or failure and psychological state.

[0544] This invention realizes a system that combines multiple hardware and software components to predict the probability of success for new economic activities and provide improvement suggestions. The main hardware components include a terminal that receives user input and a server that processes the data. The software components include a generative AI model that analyzes the data and an emotion engine that evaluates sentiment.

[0545] Users input basic business information using a terminal. This information includes market size, competitive landscape, resource allocation, and team structure. The entered data is sent from the terminal to the server. The server receives this data and retrieves additional market and competitive information from external sources. This supplements the information provided by the user with more specific and comprehensive data.

[0546] The server analyzes the received data, cleans and formats it, and converts it into a unified format that can be analyzed by the generative AI model. The generative AI model uses this pre-processed data to identify the probability of business success and related success and risk factors.

[0547] Furthermore, the emotion engine analyzes the user's voice data and facial images to determine the user's emotional state. For example, if a user expresses anxiety about a particular suggestion, the emotion engine adjusts the suggestion based on that information. This adjustment makes it possible to present suggestions in a way that is more likely to be accepted by the user.

[0548] The server ultimately integrates the success probabilities identified by the generation AI model with the analysis results of the emotion engine to generate specific business improvement suggestions. These suggestions are provided to the user in real time via the terminal, allowing the user to adjust their business plan based on this information.

[0549] As a concrete example, consider a scenario where a user is considering launching a new fitness app. The system analyzes market needs and competing apps to predict the success rate of the fitness app. It can also analyze user emotional responses to the proposed marketing strategy and suggest areas for improvement. An example of a prompt would be a specific instruction such as, "Please perform a market analysis and predict the success rate of a new fitness app."

[0550] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0551] Step 1:

[0552] The user enters basic business information through the terminal. This information includes market size, competitive landscape, resource allocation, and team structure. Once the user has finished entering the information, they press the submit button. The entered information is treated as input data sent from the terminal to the server.

[0553] Step 2:

[0554] The server receives data sent from the terminal. Based on this received data, it retrieves market data and competitor information from external sources. It connects to external databases using APIs to collect additional data. This additional information is used to supplement the user-provided information in detail. Input data consists of data from the user and data obtained from external sources, and by integrating these, comprehensive output data is formed.

[0555] Step 3:

[0556] The server preprocesses the integrated data. Preprocessing involves cleaning and formatting the data, unifying different data formats. This process includes imputing missing values ​​and correcting outliers. The server converts the input integrated data into an analyzable format and outputs it as a dataset that is easily processed by the generating AI model.

[0557] Step 4:

[0558] The server inputs pre-processed data into a generative AI model. The generative AI model analyzes this data and calculates the probability of success or failure of economic activities. Furthermore, it identifies success factors and risk factors. The results of this analysis are output as success probability and factor data.

[0559] Step 5:

[0560] The terminal receives emotional data (voice and facial images) from the user and sends it to the server. The server uses an emotion engine to analyze the input emotional data and determine the user's psychological state. The emotion engine combines speech recognition and image analysis technologies to output a numerical result representing the user's emotional state.

[0561] Step 6:

[0562] The server generates specific business improvement proposals based on calculated success / failure probabilities and emotional states. These proposals include strategies and action plans to maximize the likelihood of success. The final proposals are output to the terminal and provided to the user in real time.

[0563] Step 7:

[0564] Users review improvement suggestions presented on their devices. Based on this, they adjust their business plans and send feedback to the server, such as entering new information, to continuously improve the project.

[0565] (Application Example 2)

[0566] 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."

[0567] In today's advertising industry, predicting the success of new campaigns and advertising strategies presents a significant challenge. With numerous factors at play, identifying potential risk factors and quickly implementing effective corrective measures is crucial. However, the inability to comprehensively analyze market data and user responses necessitates efficient methods to increase advertising success rates.

[0568] 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.

[0569] In this invention, the server includes means for receiving business plan information from users and acquiring additional data from external information sources; processing means for preprocessing the received data and unifying different data formats; prediction means for predicting the probability of success using the preprocessed data; proposal means for generating strategic improvement proposals based on the probability of success; display means for presenting the generated proposals to users and updating the information in real time; and means for predicting the success of advertising campaigns and providing improvement proposals based on the results. This enables decision-making to increase the success rate of advertising campaigns.

[0570] A "user" is an individual or organization that uses the system to provide business plan information and data related to advertising campaigns, and to receive improvement suggestions.

[0571] "Business plan information" refers to detailed information provided by users to predict the probability of business success, including market data, competitor information, and resource allocation.

[0572] "External information sources" refer to external databases or information platforms that the system accesses to obtain additional market data or relevant information.

[0573] "Data preprocessing" is the process of standardizing the format of received data and preparing it so that it can be used in an analytical model.

[0574] "Predictive methods for predicting the probability of success" refer to methods for calculating the likelihood of success of a business or advertising campaign using statistical models or generative AI models.

[0575] A "strategized improvement proposal" is a proposal that outlines specific measures and action plans to enhance the effectiveness of a business or advertising campaign, based on the results of a success prediction.

[0576] A "display method that updates information in real time" is a method that provides users with immediate results of improvement suggestions and success predictions, and updates the information to the latest version as needed.

[0577] An "advertising campaign" is a series of promotional activities planned to advertise a specific product or service and attract market attention.

[0578] "Success prediction" refers to the act of making prediction calculations and analyses to estimate the success rate of new businesses or advertising campaigns.

[0579] The system for implementing this invention collects and analyzes information necessary to lead advertising campaigns to success and provides improvement suggestions to users. The system maximizes the effectiveness of advertising through the cooperation of the server, terminal, and user.

[0580] First, users input business plan information and advertising campaign details through a terminal. The terminal sends this information to a server. Based on the received data, the server retrieves additional market data from external sources and performs data preprocessing. This preprocessing unifies different data formats and prepares the data for analysis by a generative AI model.

[0581] The generative AI model analyzes diverse data to predict the probability of success for advertising campaigns. This model utilizes statistical analysis and machine learning techniques to achieve highly accurate predictions. Furthermore, the server uses a sentiment analysis engine to analyze user reactions. Based on these results, it generates and presents strategic improvement suggestions to users. These suggestions are provided to users in real time and are accessible at any time through their devices.

[0582] As a concrete example, when launching an advertising campaign for a new cosmetic product, the user inputs information on market trends and consumer preferences. Based on this information, the server predicts the probability of the advertisement's success and suggests specific improvement measures through a generative AI model. The user can then receive suggestions such as new taglines or changes to the visual style, and adjust the advertising campaign plan accordingly.

[0583] Examples of prompts for a generative AI model include the following:

[0584] "Please tell us the probability of success for this new cosmetics advertising campaign and provide suggestions for improvements to enhance its success. Market data and campaign specifications are as follows: Market data, Campaign specifications."

[0585] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0586] Step 1:

[0587] Users input business plan information and advertising campaign details through their devices. This information includes market data, competitor information, and campaign specifications. This data is then transmitted from the device to the server.

[0588] Step 2:

[0589] The server analyzes the data received from the user and retrieves additional market data from external sources. This ensures that the information provided by the user is supplemented with detailed and comprehensive data. The data received as input is pre-processed by the server and standardized into a consistent data format.

[0590] Step 3:

[0591] The server inputs pre-processed data into a generating AI model to predict the probability of success of an advertising campaign. At this stage, statistical models and machine learning algorithms are used to perform data calculations and output the success prediction results.

[0592] Step 4:

[0593] The server analyzes user responses using an emotion analysis engine. This involves inputting voice data and facial image data, and the emotion analysis algorithm identifies the user's emotional state. Based on this information, the server adjusts its suggestions.

[0594] Step 5:

[0595] The server generates strategic improvement suggestions based on the probability of success and the user's emotional state. These specific suggestions might include visual changes to advertisements or revisions to taglines. This information is output as suggestions and presented to the user.

[0596] Step 6:

[0597] The device displays improvement suggestions sent from the server to the user in real time. The user adjusts the advertising campaign based on the suggestions received and sends feedback to the server as needed, which leads to further data updates and re-evaluation of the suggestions.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] [Fourth Embodiment]

[0602] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0603] 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.

[0604] 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).

[0605] 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.

[0606] 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.

[0607] 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).

[0608] 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.

[0609] 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.

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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".

[0615] This system is designed to predict the probability of success for new businesses and provide improvement suggestions. Users input project information using a terminal, including market size, competitive landscape, resource allocation, and team composition. The terminal then transmits the entered information to the server.

[0616] The server retrieves additional information from external sources based on the received data. This complements the user-provided project information with more detailed market reports and competitive analysis data. All collected data is pre-processed within the server and standardized into an analyzable format.

[0617] The server then provides the pre-processed data to a generative model to predict the probability of business success. The generative model is trained on historical new business data and can analyze multimodal data such as text, images, and audio. This identifies success and risk factors and calculates the overall probability of success.

[0618] Based on the success probability results, the server generates specific improvement suggestions to aim for business success. These include specific strategies for establishing a competitive advantage and adjustments to the marketing plan. The generated suggestions are sent to the terminal in real time and presented to the user.

[0619] For example, when a user develops a new mobile app, suggestions for specific UI / UX design improvements or feature additions are made based on market growth potential and the strength of competition. Because the information the user needs is provided immediately, decision-making can be done quickly.

[0620] In this way, users can leverage the highly accurate predictions and suggestions provided by the server to improve the probability of success for new businesses.

[0621] The following describes the processing flow.

[0622] Step 1:

[0623] Users input basic information about a new business via a terminal. This information includes market size, competitive landscape, resource allocation, and team structure. Once the user has finished entering the information, the terminal sends it to the server.

[0624] Step 2:

[0625] The server analyzes project information received from users and searches external sources to collect necessary additional data. This includes market reports and competitor activity. The collected data is used for internal server analysis.

[0626] Step 3:

[0627] The server preprocesses the received information and any additional data collected. This includes cleaning the data, standardizing the format, correcting outliers, and preparing it for analysis. This process is crucial for improving the accuracy of the analysis.

[0628] Step 4:

[0629] The server inputs pre-processed data into a generative model. This generative model is designed to predict the probability of success for new businesses and is capable of analyzing multimodal data. The model identifies success and risk factors and calculates an overall probability of success.

[0630] Step 5:

[0631] Based on the output from the generative model, the server generates specific improvement suggestions. These suggestions include strategies and action plans to increase the project's success rate. The generated suggestions serve as a reference for users when adjusting their business operations.

[0632] Step 6:

[0633] The server sends the success probability analysis results and improvement suggestions to the terminal, presenting them to the user in real time. The user can then use this information to input new details and update their business plan. This process enables accurate decision-making based on the latest data at all times.

[0634] (Example 1)

[0635] 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".

[0636] In planning new businesses, it is essential to efficiently analyze vast amounts of data and quickly and accurately predict the probability of success. However, current technology makes it difficult to integrate data from multiple sources and generate useful improvement suggestions in real time. Therefore, a system is needed that can quickly provide improvement suggestions to increase the success rate of new businesses.

[0637] 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.

[0638] In this invention, the server includes means for receiving activity information from users and acquiring additional information from external information sources, means for preprocessing the received information and unifying different information formats, and means for predicting the probability of success using a predictive model with the preprocessed information. This makes it possible to quickly and accurately analyze data and propose optimal improvement measures for the success of new businesses.

[0639] "User" refers to an individual or organization that uses the system to provide activity information and receive suggestions.

[0640] "Activity information" refers to data including market size, competitive landscape, resource allocation, and team composition related to projects and businesses.

[0641] "External information sources" refer to third-party databases and information services that the server accesses to supplement the information provided by the user.

[0642] "Preprocessing" refers to the process of cleaning or standardizing the data format of received or collected information in order to make it analyzable.

[0643] A "predictive model" refers to a computational model used to analyze collected information and estimate the probability of success for a new business.

[0644] A "generative model" refers to a machine learning model that is trained on historical data and can analyze multiple data formats such as text, images, and audio.

[0645] An "improvement suggestion" refers to specific measures and strategies aimed at increasing the success rate of a new business, based on the predicted probability of success.

[0646] "Information updates" refer to providing users with new data and suggestions immediately to support their decision-making process.

[0647] "Information in multiple formats" refers to a set of information that includes different data formats, such as text, images, and audio.

[0648] "Visualization" refers to the process of displaying data and proposals in the form of diagrams, charts, and other visual aids so that users can easily understand them.

[0649] This section describes an embodiment of this system. The user uses a terminal to input activity information related to the project. This activity information includes market size, competitive landscape, resource allocation, and team composition. The information entered by the user is transmitted from the terminal to the server.

[0650] The server accesses external information sources based on the received activity information and retrieves any necessary additional information. This interaction with external information sources involves using APIs to collect relevant data from databases and publicly available sources. The server preprocesses the received and collected information using the Python Pandas library. This includes handling missing values, cleaning the data, and standardizing the format.

[0651] The pre-processed information is input into a generative AI model built using TensorFlow or PyTorch to predict the probability of business success. The generative AI model has the ability to analyze data in multiple formats, such as text, images, and audio, and identify success factors and risk factors.

[0652] Based on the predicted success probability, the server generates improvement suggestions for the success of the new business. These suggestions include revisions to specific strategies and marketing plans to strengthen competitive advantages. The server then formats the generated suggestions into a user-friendly format using natural language generation technology.

[0653] The server then sends the generated improvement suggestions to the terminal in real time. The terminal visualizes and presents the received suggestions to the user, enabling the user to make quick decisions.

[0654] For example, if a user is developing a new smartphone application, the system can assess market growth potential and competitive strength, and suggest improvements to specific user interfaces and user experience (UI / UX). The following prompts can be provided to encourage the user to use the system:

[0655] Please provide project information regarding the mobile app currently under development as a new business venture. Please include details such as market size, competitive landscape, and team structure.

[0656] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0657] Step 1:

[0658] Users input activity information via a terminal. This information includes market size, competitive landscape, resource allocation, and team composition. Once input is complete, the terminal verifies the entered information, encodes it in the appropriate data format, and sends it to the server. The output of the terminal for the input data is the activity information sent to the server.

[0659] Step 2:

[0660] The server receives activity information sent from the terminal. Based on the received data, the server accesses external information sources to collect necessary additional information. In this process, the server uses APIs to query external databases and retrieve market reports and competitive analysis data. The input data is activity information, and the output data is supplementary, detailed information.

[0661] Step 3:

[0662] The server preprocesses the collected information, including imputing missing values, cleaning the data, and standardizing the format. This process uses the Python Pandas library to convert the data into a parseable format. The input data is imputed information, while the output data is preprocessed data.

[0663] Step 4:

[0664] The server inputs pre-processed data into a generative AI model. This model, built using TensorFlow or PyTorch, analyzes data in multiple formats and predicts the probability of business success. Because the generative AI model is trained on historical data, it has the ability to identify success factors and risk factors. The input data is pre-processed data, and the output data is the result of the success probability.

[0665] Step 5:

[0666] Based on the success probability results, the server generates specific improvement suggestions. These suggestions include revising strategies and marketing plans to strengthen competitive advantage. Natural language generation technology is used to format the suggestions in a user-friendly manner. The input data consists of the success probability and identified factors, while the output data consists of improvement suggestions for the user.

[0667] Step 6:

[0668] The server sends the generated improvement suggestions to the terminal in real time. The terminal receives the suggestions and presents them to the user in a visualized format. This allows the user to immediately review the information and make quick decisions. The input data is the generated suggestions, and the output data is the visualized information presented to the user.

[0669] (Application Example 1)

[0670] 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".

[0671] In today's world, there is a need to appropriately evaluate the success rate of new business launches and projects in specific areas, and to rapidly implement differentiation strategies in highly competitive markets. However, traditional methods of information gathering and analysis have been fragmented and inefficient. Therefore, a system is needed to support business success through rapid and continuous evaluation and improvement.

[0672] 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.

[0673] In this invention, the server includes means for receiving project information from users and obtaining additional information from external sources, means for preprocessing the received data and unifying different data formats, and means for implementing optimization and differentiation strategies for functions in specific areas based on proposed improvements. This makes it possible to improve the probability of business success through continuous evaluation and feedback in specific areas.

[0674] "Project information" refers to information that users need to provide when starting a new business or project, such as market size, competitive landscape, resource allocation, and team composition.

[0675] "External information sources" refer to data obtained from external sources, such as market reports, competitive analyses, and economic indicators, that are referenced to complement project information.

[0676] A "generative model" is a machine learning algorithm that analyzes multimodal input data to predict the probability of business success.

[0677] "Probability of success" is an evaluation metric that indicates the likelihood of a newly proposed business or project succeeding in the market.

[0678] An "improvement suggestion" is information that proposes modifications to specific strategies or measures in order to increase the probability of business success.

[0679] A "specific domain" refers to a unique market or technological area in various industries and fields, primarily such as electronic payment services.

[0680] "Functional optimization" refers to optimizing the functionality of services or products provided in a specific area to maximize their effectiveness.

[0681] A "differentiation strategy" is a tactic to secure a competitive advantage by developing services or products in the market that have unique features different from those of competitors.

[0682] "Continuous evaluation" refers to an analytical process that continuously reflects project progress and market trends in real time.

[0683] "Providing feedback" is the process by which the system returns information to users about the status of the business and areas for improvement.

[0684] This invention is a system that predicts the probability of success of a new business in a specific domain and provides optimal improvement suggestions. The system begins with the user sending project information from their terminal to a server. This project information includes market size, competitive landscape, resource allocation, and team composition. After receiving this information, the server retrieves relevant data from external sources.

[0685] The server integrates this data and uses a generative AI model to analyze it. This model is trained on past new business data and predicts the probability of success through multimodal data analysis. Based on the analysis results, it generates specific differentiation strategies and functional optimization suggestions to promote project success. The server presents these suggestions to the user's terminal in real time, helping users make immediate decisions.

[0686] In this embodiment, a specific example is a small or medium-sized enterprise (SME) planning to introduce a new QR code payment function in the electronic payment service industry. By using the proposed system, the company can conduct a market assessment based on the entered project information and immediately obtain effective strategies for differentiating itself from competitors. Furthermore, users can quickly modify and implement their strategies by utilizing the feedback provided in real time.

[0687] For processing specific generative models, programming languages ​​and libraries such as Python and TensorFlow can be used. The server will run on a computer infrastructure with sufficient performance for data preprocessing and analysis.

[0688] An example of a prompt message is: "Predict the market potential of the new QR code payment function and suggest improvements. The market size is 500,000, the level of competition is high, and resource allocation is moderate."

[0689] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0690] Step 1:

[0691] The user enters project information into the terminal. This information includes market size, competitive landscape, resource allocation, and team structure. This information forms a project overview and is prepared as a dataset to be sent to the server in the next step.

[0692] Step 2:

[0693] The terminal sends the entered project information to the server. The server analyzes the received data and retrieves relevant market and competitor information from external sources. Here, APIs are used to retrieve data and form a rich dataset that supplements the project information.

[0694] Step 3:

[0695] The server preprocesses the received and retrieved data. Specifically, it normalizes text data, scales numerical data, and encodes categorical data. This unifies different data formats and creates a dataset that can be processed by generative AI models.

[0696] Step 4:

[0697] The server inputs pre-processed data into a generating AI model to predict the probability of business success. This model is trained on historical business data, constructs a neural network as the data computation for prediction, and performs rapid analysis. The output is the probability of success.

[0698] Step 5:

[0699] The server, having obtained a success probability, generates business improvement suggestions based on that. Here, AI-powered data analysis reveals specific action plans, such as adjustments to marketing strategies and suggestions for functional improvements. This output is then formatted in a way that is usable by the user.

[0700] Step 6:

[0701] The server sends the generated improvement suggestions back to the terminal and presents them to the user. The user receives the suggested improvements and can adjust the project strategy. This allows the user to quickly take action to improve the quality of decision-making and increase the chances of project success.

[0702] 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.

[0703] This invention realizes a system that predicts the probability of success of a new business and provides improvement suggestions using an emotion engine. Users input basic information about the business via a terminal. This information includes market size, competitive landscape, resource allocation, and team composition. The input data is transmitted from the terminal to a server.

[0704] The server first analyzes the provided data and retrieves additional market and competitor information from external sources. This ensures that the user-entered information is supplemented with detailed and comprehensive data. All received data undergoes a preprocessing process and is converted into a unified format suitable for analysis by generative models.

[0705] Next, the server inputs the pre-processed data into a generative model to identify the probability of success for the new business and the associated success and risk factors. The generative model can analyze multimodal data and predict the probability of success with high accuracy.

[0706] This system also incorporates an emotion engine that analyzes user emotions. The emotion engine analyzes voice data and facial images obtained from the user to determine the user's emotional state. For example, if a user expresses anxiety about a particular proposal, the emotion engine uses that information to adjust the proposal and improve it to a form that is more likely to be accepted by the user.

[0707] Subsequently, the server generates specific business improvement suggestions based on the success probability identified by the generative model and the analysis results of the emotion engine. These suggestions, which consist of strategies and action plans to increase the likelihood of success of the business plan, are provided to the user in real time via their device. The user can then use these results to adjust their business plan and provide additional information as needed.

[0708] For example, if a user is considering launching a product, the generative model predicts the probability of success based on market needs and competitive analysis. Simultaneously, the emotion engine analyzes the user's responses to determine which suggestions resonate most with them. In this way, users always receive accurate information and suggestions, enabling them to make decisions that improve the probability of business success.

[0709] The following describes the processing flow.

[0710] Step 1:

[0711] The user inputs information about the new business from their device. This information includes market size, competitive landscape, resource allocation, and team composition. The device then sends the entered information to the server.

[0712] Step 2:

[0713] The server analyzes the information received from the user. It also collects additional data from external sources such as market databases and competitive analysis tools. This data helps to complement the background of the business plan.

[0714] Step 3:

[0715] The server preprocesses all collected data. Specifically, it cleans the data, standardizes the data format, and corrects for outliers. This ensures that the analysis model can operate with high accuracy.

[0716] Step 4:

[0717] The server inputs pre-processed data into a generative model. The generative model uses this data to predict the probability of success for a new business and extracts success and risk factors. Because the generative model can analyze diverse data, it can also analyze data that includes text, images, and audio.

[0718] Step 5:

[0719] The server activates an emotion engine to analyze the user's emotions. The terminal collects voice and facial images from the user and sends them to the server. The emotion engine uses this data to estimate the user's emotions.

[0720] Step 6:

[0721] By combining the analysis results from the emotion engine with the output from the generative model, the server generates specific suggestions for business improvement. This includes adjusting the suggestions according to the user's emotional state.

[0722] Step 7:

[0723] The server sends the predicted success rate, risk factors, success factors, and suggestions from the emotion engine to the terminal and presents them to the user. Based on these results, the user reviews the new business plan, provides additional information if necessary, or modifies the business plan.

[0724] (Example 2)

[0725] 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".

[0726] In new economic activities, there is a need to accurately predict the probability of success and to provide improvement suggestions that take into account the emotional state of users. However, conventional technologies do not have sufficient means to meet these requirements, and users are not being able to receive satisfactory information.

[0727] 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.

[0728] In this invention, the server includes means for collecting information on economic activities from information users and obtaining additional information from external information sources; means for preprocessing the collected information and unifying different information formats; and means for estimating the probability of success or failure of economic activities using a generative model based on the preprocessed information. As a result, users can receive more detailed and accurate success or failure predictions and make appropriate decisions based on those predictions.

[0729] An "information user" is an entity that uses a system to input information about economic activities and receives analysis results and suggestions.

[0730] "Economic activity" refers to commercial, business, or other economic projects, including activities in the market.

[0731] "Additional information" refers to data obtained from external sources that complements or expands upon the initial information provided by the user.

[0732] "Preprocessing" is the process of converting collected information into a standardized format and preparing it for data analysis.

[0733] A "generative model" is a model that uses machine learning or artificial intelligence to analyze data and includes mathematical or statistical methods to predict the probability of future events.

[0734] "Probability of success" is a numerical representation of the likelihood of a particular economic activity succeeding or failing.

[0735] "Psychological state" refers to the emotions and reactions that a user exhibits in response to specific information or suggestions.

[0736] An "improvement plan" is a specific strategy or idea for optimizing or improving a proposed economic activity, derived based on the probability of success or failure and psychological state.

[0737] This invention realizes a system that combines multiple hardware and software components to predict the probability of success for new economic activities and provide improvement suggestions. The main hardware components include a terminal that receives user input and a server that processes the data. The software components include a generative AI model that analyzes the data and an emotion engine that evaluates sentiment.

[0738] Users input basic business information using a terminal. This information includes market size, competitive landscape, resource allocation, and team structure. The entered data is sent from the terminal to the server. The server receives this data and retrieves additional market and competitive information from external sources. This supplements the information provided by the user with more specific and comprehensive data.

[0739] The server analyzes the received data, cleans and formats it, and converts it into a unified format that can be analyzed by the generative AI model. The generative AI model uses this pre-processed data to identify the probability of business success and related success and risk factors.

[0740] Furthermore, the emotion engine analyzes the user's voice data and facial images to determine the user's emotional state. For example, if a user expresses anxiety about a particular suggestion, the emotion engine adjusts the suggestion based on that information. This adjustment makes it possible to present suggestions in a way that is more likely to be accepted by the user.

[0741] The server ultimately integrates the success probabilities identified by the generation AI model with the analysis results of the emotion engine to generate specific business improvement suggestions. These suggestions are provided to the user in real time via the terminal, allowing the user to adjust their business plan based on this information.

[0742] As a concrete example, consider a scenario where a user is considering launching a new fitness app. The system analyzes market needs and competing apps to predict the success rate of the fitness app. It can also analyze user emotional responses to the proposed marketing strategy and suggest areas for improvement. An example of a prompt would be a specific instruction such as, "Please perform a market analysis and predict the success rate of a new fitness app."

[0743] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0744] Step 1:

[0745] The user enters basic business information through the terminal. This information includes market size, competitive landscape, resource allocation, and team structure. Once the user has finished entering the information, they press the submit button. The entered information is treated as input data sent from the terminal to the server.

[0746] Step 2:

[0747] The server receives data sent from the terminal. Based on this received data, it retrieves market data and competitor information from external sources. It connects to external databases using APIs to collect additional data. This additional information is used to supplement the user-provided information in detail. Input data consists of data from the user and data obtained from external sources, and by integrating these, comprehensive output data is formed.

[0748] Step 3:

[0749] The server preprocesses the integrated data. Preprocessing involves cleaning and formatting the data, unifying different data formats. This process includes imputing missing values ​​and correcting outliers. The server converts the input integrated data into an analyzable format and outputs it as a dataset that is easily processed by the generating AI model.

[0750] Step 4:

[0751] The server inputs pre-processed data into a generative AI model. The generative AI model analyzes this data and calculates the probability of success or failure of economic activities. Furthermore, it identifies success factors and risk factors. The results of this analysis are output as success probability and factor data.

[0752] Step 5:

[0753] The terminal receives emotional data (voice and facial images) from the user and sends it to the server. The server uses an emotion engine to analyze the input emotional data and determine the user's psychological state. The emotion engine combines speech recognition and image analysis technologies to output a numerical result representing the user's emotional state.

[0754] Step 6:

[0755] The server generates specific business improvement proposals based on calculated success / failure probabilities and emotional states. These proposals include strategies and action plans to maximize the likelihood of success. The final proposals are output to the terminal and provided to the user in real time.

[0756] Step 7:

[0757] Users review improvement suggestions presented on their devices. Based on this, they adjust their business plans and send feedback to the server, such as entering new information, to continuously improve the project.

[0758] (Application Example 2)

[0759] 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".

[0760] In today's advertising industry, predicting the success of new campaigns and advertising strategies presents a significant challenge. With numerous factors at play, identifying potential risk factors and quickly implementing effective corrective measures is crucial. However, the inability to comprehensively analyze market data and user responses necessitates efficient methods to increase advertising success rates.

[0761] 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.

[0762] In this invention, the server includes means for receiving business plan information from users and acquiring additional data from external information sources; processing means for preprocessing the received data and unifying different data formats; prediction means for predicting the probability of success using the preprocessed data; proposal means for generating strategic improvement proposals based on the probability of success; display means for presenting the generated proposals to users and updating the information in real time; and means for predicting the success of advertising campaigns and providing improvement proposals based on the results. This enables decision-making to increase the success rate of advertising campaigns.

[0763] A "user" is an individual or organization that uses the system to provide business plan information and data related to advertising campaigns, and to receive improvement suggestions.

[0764] "Business plan information" refers to detailed information provided by users to predict the probability of business success, including market data, competitor information, and resource allocation.

[0765] "External information sources" refer to external databases or information platforms that the system accesses to obtain additional market data or relevant information.

[0766] "Data preprocessing" is the process of standardizing the format of received data and preparing it so that it can be used in an analytical model.

[0767] "Predictive methods for predicting the probability of success" refer to methods for calculating the likelihood of success of a business or advertising campaign using statistical models or generative AI models.

[0768] A "strategized improvement proposal" is a proposal that outlines specific measures and action plans to enhance the effectiveness of a business or advertising campaign, based on the results of a success prediction.

[0769] A "display method that updates information in real time" is a method that provides users with immediate results of improvement suggestions and success predictions, and updates the information to the latest version as needed.

[0770] An "advertising campaign" is a series of promotional activities planned to advertise a specific product or service and attract market attention.

[0771] "Success prediction" refers to the act of making prediction calculations and analyses to estimate the success rate of new businesses or advertising campaigns.

[0772] The system for implementing this invention collects and analyzes information necessary to lead advertising campaigns to success and provides improvement suggestions to users. The system maximizes the effectiveness of advertising through the cooperation of the server, terminal, and user.

[0773] First, users input business plan information and advertising campaign details through a terminal. The terminal sends this information to a server. Based on the received data, the server retrieves additional market data from external sources and performs data preprocessing. This preprocessing unifies different data formats and prepares the data for analysis by a generative AI model.

[0774] The generative AI model analyzes diverse data to predict the probability of success for advertising campaigns. This model utilizes statistical analysis and machine learning techniques to achieve highly accurate predictions. Furthermore, the server uses a sentiment analysis engine to analyze user reactions. Based on these results, it generates and presents strategic improvement suggestions to users. These suggestions are provided to users in real time and are accessible at any time through their devices.

[0775] As a concrete example, when launching an advertising campaign for a new cosmetic product, the user inputs information on market trends and consumer preferences. Based on this information, the server predicts the probability of the advertisement's success and suggests specific improvement measures through a generative AI model. The user can then receive suggestions such as new taglines or changes to the visual style, and adjust the advertising campaign plan accordingly.

[0776] Examples of prompts for a generative AI model include the following:

[0777] "Please tell us the probability of success for this new cosmetics advertising campaign and provide suggestions for improvements to enhance its success. Market data and campaign specifications are as follows: Market data, Campaign specifications."

[0778] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0779] Step 1:

[0780] Users input business plan information and advertising campaign details through their devices. This information includes market data, competitor information, and campaign specifications. This data is then transmitted from the device to the server.

[0781] Step 2:

[0782] The server analyzes the data received from the user and retrieves additional market data from external sources. This ensures that the information provided by the user is supplemented with detailed and comprehensive data. The data received as input is pre-processed by the server and standardized into a consistent data format.

[0783] Step 3:

[0784] The server inputs pre-processed data into a generating AI model to predict the probability of success of an advertising campaign. At this stage, statistical models and machine learning algorithms are used to perform data calculations and output the success prediction results.

[0785] Step 4:

[0786] The server analyzes user responses using an emotion analysis engine. This involves inputting voice data and facial image data, and the emotion analysis algorithm identifies the user's emotional state. Based on this information, the server adjusts its suggestions.

[0787] Step 5:

[0788] The server generates strategic improvement suggestions based on the probability of success and the user's emotional state. These specific suggestions might include visual changes to advertisements or revisions to taglines. This information is output as suggestions and presented to the user.

[0789] Step 6:

[0790] The device displays improvement suggestions sent from the server to the user in real time. The user adjusts the advertising campaign based on the suggestions received and sends feedback to the server as needed, which leads to further data updates and re-evaluation of the suggestions.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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."

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] The following is further disclosed regarding the embodiments described above.

[0813] (Claim 1)

[0814] A means of receiving project information from users and obtaining additional information from external sources,

[0815] A means of preprocessing received data and unifying different data formats,

[0816] A method for predicting the probability of business success using a generative model with preprocessed data,

[0817] A means of generating business improvement proposals based on the probability of success,

[0818] A means of presenting the generated improvement proposals to users and updating the information,

[0819] A system that includes this.

[0820] (Claim 2)

[0821] The system according to claim 1, comprising a generative model that analyzes multimodal data and means for identifying success factors and risk factors.

[0822] (Claim 3)

[0823] The system according to claim 1, comprising means for performing continuous re-evaluation by a generative model through real-time data updates.

[0824] "Example 1"

[0825] (Claim 1)

[0826] A means of receiving activity information from users and obtaining additional information from external sources,

[0827] A means of preprocessing received information and unifying different information formats,

[0828] A means of predicting the probability of success using a predictive model with preprocessed information,

[0829] A means of generating improvement suggestions based on the probability of success,

[0830] A means of presenting generated suggestions to users and updating information,

[0831] A means of instantly visualizing and presenting the generated information to the user,

[0832] A system that includes this.

[0833] (Claim 2)

[0834] The system according to claim 1, comprising a predictive model that analyzes multiple forms of information and means for identifying success factors and risk factors.

[0835] (Claim 3)

[0836] The system according to claim 1, comprising means for repeatedly performing evaluations by a predictive model through continuous and instantaneous information updates.

[0837] "Application Example 1"

[0838] (Claim 1)

[0839] A means of receiving project information from users and obtaining additional information from external sources,

[0840] A means of preprocessing received data and unifying different data formats,

[0841] A method for predicting the probability of business success using a generative model with preprocessed data,

[0842] A means of generating business improvement proposals based on the probability of success,

[0843] A means of presenting the generated improvement proposals to users and updating the information,

[0844] Based on the proposed improvements, the means to implement optimization and differentiation strategies for functions in specific areas,

[0845] Means including continuous evaluation and provision of feedback in a specific area,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, comprising a generative model that analyzes multimodal data and means for identifying success factors and risk factors.

[0849] (Claim 3)

[0850] The system according to claim 1, comprising means for real-time data updates and user decision-making support in a specific domain.

[0851] "Example 2 of combining an emotion engine"

[0852] (Claim 1)

[0853] A means of collecting information on economic activities from information users and obtaining additional information from external sources,

[0854] A means of preprocessing the collected information and unifying different information formats,

[0855] A means for estimating the probability of success or failure of economic activity using a generative model with preprocessed information,

[0856] A means for generating improvement plans for economic activities based on the probability of success or failure and related factors,

[0857] A means of analyzing the psychological state of users and adjusting improvement plans for economic activity,

[0858] A means of displaying the generated improvement proposals to information users and updating the information,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, comprising a generative model that analyzes diverse information and means for identifying success factors and crisis factors.

[0862] (Claim 3)

[0863] The system according to claim 1, comprising means for instantaneously updating information and performing continuous re-evaluation using a generative model.

[0864] "Application example 2 when combining with an emotional engine"

[0865] (Claim 1)

[0866] A means of receiving business plan information from users and obtaining additional data from external sources,

[0867] A processing method for pre-processing received data and unifying different data formats,

[0868] A prediction means for predicting the probability of success using preprocessed data,

[0869] A proposal method for generating strategic improvement proposals based on the probability of success,

[0870] A display means that presents the generated proposals to the user and updates the information in real time,

[0871] A means of predicting the success of an advertising campaign and providing improvement suggestions based on the results,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, comprising a generative model that analyzes multimodal data, identifies success factors and risk factors, and adjusts advertising strategies.

[0875] (Claim 3)

[0876] The system according to claim 1, comprising means for continuous re-evaluation by a generative model and improvement of the effectiveness of advertising campaigns through real-time data updates. [Explanation of symbols]

[0877] 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 receiving project information from users and obtaining additional information from external sources, A means of preprocessing received data and unifying different data formats, A method for predicting the probability of business success using a generative model with preprocessed data, A means of generating business improvement proposals based on the probability of success, A means of presenting the generated improvement proposals to users and updating the information, Based on the proposed improvements, the means to implement optimization and differentiation strategies for functions in specific areas, Means including continuous evaluation and provision of feedback in a specific area, A system that includes this.

2. The system according to claim 1, comprising a generative model that analyzes multimodal data and means for identifying success factors and risk factors.

3. The system according to claim 1, comprising means for real-time data updates and user decision-making support in a specific domain.

Images