System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting detailed information about a business idea by a user; means for receiving and pre-processing data of the input business idea; means for extracting similar past failure cases and success cases from a database based on the pre-processed data; means for analyzing the extracted cases and identifying causes of failure and factors of success; means for generating strategic recommendations from the identified causes and factors; and means for providing the generated recommendations to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Entrepreneurs and small and medium-sized enterprises starting new businesses want to learn from past failures, but they have limited resources to devote to gathering information. Furthermore, failure data on competitors is often not publicly available, and individual consulting is expensive. This creates the challenge of making it difficult to receive strategic recommendations to increase the success rate of new businesses. [Means for solving the problem]

[0005] The above-mentioned problems can be solved by a system including a means for a user to input detailed information about a business idea, a means for receiving and preprocessing the input business idea data, a means for extracting similar past failures and successes from a database based on the preprocessed data, a means for analyzing the extracted cases and identifying the causes of failure and factors of success, a means for generating strategic recommendations from the identified causes and factors, and a means for providing the generated recommendations to the user.

[0006] "User" means an individual or company that uses the system to input business ideas and related information.

[0007] A "business idea" is a concept or plan for a new business that a user wants to start.

[0008] "Data reception" refers to the process of transferring business idea data entered by a user into a terminal to a server.

[0009] "Preprocessing" refers to the normalization and encoding of data received by the server to convert it into a format suitable for analysis.

[0010] A "database" is a system that accumulates and manages past cases of failure and success, and provides data in response to queries.

[0011] "Similar case extraction" refers to the act of searching and retrieving past cases that closely resemble input data from a database.

[0012] "Failure cases" refer to detailed data on the failure of a particular business in the past and the reasons for its failure.

[0013] A "success story" is detailed data and factors that led to the success of a particular business in the past.

[0014] A "generative AI model" is an artificial intelligence that uses machine learning and natural language processing techniques to analyze data and generate recommendations.

[0015] "Strategic recommendations" are specific proposals based on past case analysis to help users make their business ideas successful.

[0016] "Real-time monitoring" refers to the process of constantly monitoring market changes and competitive conditions and providing the latest information. [Brief explanation of the drawings]

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

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

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

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

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

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

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] This invention relates to a system that utilizes generative AI and a historical database to identify the causes of failure of business ideas and provide strategic recommendations for success.

[0039] User operations

[0040] A user enters detailed information about a business idea (e.g., target market, product characteristics, competitor information, etc.) into a terminal, possibly via a web form or a mobile application. Once the user has completed the input and pressed the submit button, this data is sent to a server.

[0041] Data reception and preprocessing on the server

[0042] The server receives the business idea data sent from the device, and then preprocesses it, removing special characters and encoding the text data to make it easier to analyze.

[0043] Extraction and analysis of similar cases

[0044] After the preprocessing is complete, the server extracts similar failures and successes from a database of past cases. At this stage, a generative AI model is used to automatically identify the causes of failures and factors behind successes from past cases. The AI ​​model uses specific algorithms to analyze patterns and trends in the data.

[0045] Generating strategic recommendations

[0046] Based on the extracted causes of failure and factors of success, the generative AI model generates specific strategic recommendations, which may include revising marketing strategies, changing product features, and implementing specific action plans to improve competitive advantage.

[0047] User Feedback

[0048] The generated recommendations are sent from the server to the device for the user to review. Feedback is presented as a concrete action plan through data visualization. Based on this information, users can adjust their business strategies and take concrete measures to increase their chances of success.

[0049] Specific examples

[0050] For example, if a user inputs a business idea for a new health food (e.g., a protein bar), previous failures may identify "unplanned entry into a highly competitive market" as the cause of failure. On the other hand, successes may identify "differentiation through the incorporation of unique ingredients" as the key to success. Based on this information, the generative AI model will provide recommendations such as "use specific ingredients and conduct a marketing campaign with a narrow target market."

[0051] In this way, the system of the present invention can provide specific and effective improvement measures for business ideas provided by users, thereby increasing the probability of business success.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The user enters detailed information about the business idea, including the target market, product characteristics, competitor information, etc. Once the information is complete, the user presses the submit button.

[0055] Step 2:

[0056] The terminal receives the data entered by the user and sends it to the server, where the data is encoded in a standard format such as JSON.

[0057] Step 3:

[0058] The server receives the data sent from the terminal, stores it temporarily, and passes it on to the next process.

[0059] Step 4:

[0060] The server pre-processes the received data by removing special characters and encoding the text data into a format suitable for analysis.

[0061] Step 5:

[0062] The server uses the preprocessed data to run queries to extract past failures and successes from a database of similar business ideas.

[0063] Step 6:

[0064] The server then passes the failure and success cases extracted from the database to a generative AI model for analysis, which analyzes the data for patterns and trends to identify the causes of failure and the factors behind success.

[0065] Step 7:

[0066] The server generates strategic recommendations based on the analysis results obtained from the generative AI model, which may include reviewing marketing strategies or changing product characteristics.

[0067] Step 8:

[0068] The server encodes the generated recommendations and sends them to the device in a standard format such as JSON.

[0069] Step 9:

[0070] The device decodes the recommendations received from the server and displays them in an easy-to-read format for the user, who can then review them and use them to adjust their business strategies.

[0071] Through this series of processes, the system can provide users with specific and effective strategic recommendations, increasing the probability of business success.

[0072] Example 1

[0073] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0074] Conventional business strategy formulation systems often rely on manual analysis of past case data, resulting in a lack of accuracy and efficiency. They also face the problem of difficulty in monitoring market changes and competitive situations in real time and updating strategies immediately. This makes it difficult for users to quickly and accurately evaluate business ideas and receive strategic recommendations.

[0075] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0076] In this invention, the server includes means for a user to input detailed information about a business idea, means for receiving and preprocessing the input business idea data, means for extracting similar past failures and successes from a database based on the preprocessed data, means for analyzing the extracted cases using a generative AI model and identifying causes of failure and factors of success, means for generating strategic recommendations from the identified causes and factors, and means for providing the generated recommendations to the user, thereby enabling the user to receive a quick and accurate evaluation of their business idea and receive specific strategic recommendations in real time.

[0077] "User" means a person or organization that provides information about a business idea and uses the system to receive ratings and recommendations.

[0078] A "business idea" is a specific plan or concept for business activities, such as a new product or service offering method or market development strategy.

[0079] A "terminal" is an electronic device, such as a personal computer or smartphone, that a user uses to input information about a business idea.

[0080] A "server" is a computer system or software that receives business idea data sent by users, analyzes it, and generates recommendations.

[0081] "Preprocessing" refers to processes such as data cleaning and encoding to convert received data into a format that is easier to analyze.

[0082] A "database" is an information management system that systematically stores related information, such as past failures and successes, and allows for searching and extraction.

[0083] A "generative AI model" is an algorithm or model used to analyze patterns and trends in data using artificial intelligence to generate specific recommendations.

[0084] "Recommendations" are advice and guidelines provided to users by the system with the aim of proposing strategies and specific action plans for business success.

[0085] "Preprocessed data" means data that has been received, cleaned, encoded, and converted into a form suitable for analysis.

[0086] "Real-time" refers to processing and feedback that immediately reflects the current state without delay.

[0087] This invention is a system that allows users to input detailed information about a business idea, analyzes past case data using a generative AI model based on that information, and provides specific strategic recommendations. Next, a specific embodiment of this system will be described.

[0088] User operations

[0089] A user inputs detailed information about their business idea (such as the target market, product characteristics, and competitor information) into a terminal. This is typically done using a web form or a mobile application. For example, if a user inputs a business idea for a "new protein bar," they might enter specific information such as "fitness enthusiasts" as the target market, "high protein, low sugar" as the product characteristics, and "a product from a well-known health food company" as the competitor information.

[0090] Data reception and preprocessing on the server

[0091] The server receives the business idea data sent from the device. After receiving the data, the server preprocesses it. This preprocessing includes removing special characters and insignificant spaces. The server also converts the data into a format that is easier to analyze. For example, it normalizes and encodes text data. Specifically, it is common to use Python libraries (such as pandas or numpy) to format the data.

[0092] Extraction and analysis of similar cases

[0093] After the preprocessing is complete, the server extracts similar business ideas from a past database. For example, it uses an SQL query to search for past failures and successes. The extracted case data is fed into a generative AI model, which then identifies the causes of failure and factors behind success. Generative AI models are built using deep learning frameworks such as TensorFlow and PyTorch, and may use supervised learning and reinforcement learning algorithms.

[0094] Generating strategic recommendations

[0095] The causes of failure and factors of success identified by the AI ​​model are used to generate specific strategic recommendations, such as using specific ingredients and conducting targeted marketing campaigns. The recommendations are then analyzed through algorithms developed using tools such as Jupyter Notebook and Google Colab.

[0096] User Feedback

[0097] The generated recommendations are sent from the server to the device, where the user can review them. Feedback is presented as a concrete action plan through data visualization, for example, using data visualization tools such as Grafana or Tableau, which can be easily understood by the user.

[0098] Specific examples

[0099] As a concrete example, let's consider the case where a user inputs a business idea for a new health food product (e.g., a protein bar). Based on past failures, the cause of failure was identified as "unplanned entry into a highly competitive market." On the other hand, based on successful cases, the key to success was identified as "differentiation through the incorporation of unique ingredients." Based on this information, the generative AI model provides recommendations such as "use specific ingredients and conduct a marketing campaign with a narrow target market."

[0100] Prompt Sentence Examples

[0101] Below are some examples of prompts for generative AI models:

[0102] "A user is considering launching a new protein bar into the market. They have entered their target market and product characteristics. Based on past similar cases, please analyze the possible causes of failure and factors for success and provide specific strategic recommendations."

[0103] In this way, users can adjust their business strategies based on the specific improvements provided and increase their chances of success.

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1: User Input and Data Submission

[0106] The user enters detailed information about their business idea into the device, including the target market, product characteristics, and competitor information. For example, when a user enters a business idea for a "new protein bar," they enter data such as the target market (fitness enthusiasts), product characteristics (high protein, low sugar), and competitor information (product from a health food company). Once this data is entered, the user presses the submit button, and the entered data is sent from the device to the server. Input is made into a text field, and after submission, the data is encoded in JSON format and sent to the server.

[0107] Input: Details of your business idea entered by the user

[0108] Output: JSON encoded data

[0109] Step 2: Data reception and preprocessing

[0110] The server receives business idea data sent from the device. The received data is logged and preprocessing begins. Preprocessing involves removing special characters, deleting meaningless spaces, and normalizing the data. For example, text data such as "high protein, low sugar" is converted to lowercase and encoded into a numeric vector or TF-IDF format. Python libraries (e.g., pandas, numpy) are used for preprocessing.

[0111] Input: Business idea data in JSON format

[0112] Output: Normalized and encoded data

[0113] Step 3: Extracting similar cases

[0114] After the preprocessing is complete, the server extracts similar failure and success cases from the past database. It uses an SQL query to search for past cases related to, for example, "protein bars." The extracted cases are used to classify the factors behind success and failure based on past training data.

[0115] Input: Normalized and encoded data

[0116] Output: Similar past failures and successes

[0117] Step 4: Analysis by generative AI model

[0118] The server analyzes the extracted cases using a generative AI model (e.g., a deep learning model) that analyzes patterns and trends based on past data to identify causes of failure and factors of success. The model is built using frameworks such as TensorFlow and PyTorch.

[0119] Input: Similar past failures and successes

[0120] Output: Identified causes of failure and factors of success

[0121] Step 5: Generate strategic recommendations

[0122] Based on the identified causes of failure and factors of success, the server uses a generative AI model to generate strategic recommendations, such as a specific action plan such as "use specific ingredients and conduct a marketing campaign targeting the target market." This process is typically carried out using tools such as Jupyter Notebook or Google Colab.

[0123] Input: Identified causes of failure and factors of success

[0124] Output: Specific strategic recommendations

[0125] Step 6: User feedback

[0126] The generated recommendations are sent from the server to the device, and the feedback is presented as a concrete action plan through data visualization, for example, using tools such as Grafana or Tableau, in a visually easy-to-understand format.

[0127] Input: Specific strategic recommendations

[0128] Output: Feedback via data visualization

[0129] Prompt Sentence Examples

[0130] Below are some examples of prompts for generative AI models:

[0131] "A user is considering launching a new protein bar into the market. They have entered their target market and product characteristics. Based on past similar cases, please analyze the possible causes of failure and factors for success and provide specific strategic recommendations."

[0132] (Application example 1)

[0133] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0134] Conventional business idea evaluation systems struggle to identify the causes of failure and factors for success from past cases, making it impossible to provide effective strategic recommendations. Furthermore, they are unable to reflect market changes and competitive situations in real time, making it impossible to provide users with practical feedback. Furthermore, the data entered by users comes in a variety of formats, and if proper preprocessing is not performed, the accuracy of analysis can decrease. This makes it difficult to increase the success rate of businesses.

[0135] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0136] In this invention, the server includes: a means for a user to input detailed information about a business idea; a means for receiving and preprocessing the input business idea data; a means for extracting similar past failures and successes from a database based on the preprocessed data; a means for analyzing the extracted cases and identifying causes of failure and factors of success; a means for generating strategic recommendations from the identified causes and factors; a means for providing the generated recommendations to the user; a means for using a generative AI model to generate recommendations and performing analysis based on prompt statements; and a means for updating and displaying the generated recommendations in real time. This allows the generative AI model to provide effective recommendations for business ideas based on past cases, enabling real-time feedback that reflects market changes and competitive conditions. Furthermore, by normalizing and encoding the format of the data entered by the user, the accuracy of analysis can be improved, making it possible to provide specific strategies for business success.

[0137] A "user" is someone who inputs detailed information about a business idea and receives evaluation results and recommendations.

[0138] A "business idea" is a concept or detailed information about a new product, service, or business model.

[0139] "Detailed information" refers to specific data related to the business idea, such as the target market, product characteristics, and competitor information.

[0140] A "database" is an information collection that stores data such as past failures and successes.

[0141] "Causes of failure" are the reasons or factors that led to businesses not being successful in past cases.

[0142] "Factors for success" are the reasons and factors that led to business success in past cases.

[0143] "Strategic recommendations" refer to specific strategies and action plans to increase the success rate of a business idea.

[0144] A "generative AI model" is an algorithm that uses artificial intelligence to analyze patterns and trends in data and generate recommendations.

[0145] A "prompt sentence" is text data input into a generative AI model, and is an instruction sentence that the model uses to analyze and generate.

[0146] "Real-time" is a time concept that means data processing and information updates are instantaneous.

[0147] "Normalization" is the process of standardizing data into a certain format.

[0148] "Encoding" is the process of converting data into a format that is easy to analyze.

[0149] The present invention is a system that utilizes a generative AI model to identify causes of failure and factors for success of business ideas from a past database and provides strategic recommendations. The system includes the following means.

[0150] User data entry

[0151] Users use a terminal to input detailed information about new product ideas and business strategies, including target markets, product characteristics, and competitor information.

[0152] Data transmission and preprocessing

[0153] The entered data is sent from the terminal to the server, which preprocesses the received data, removing special characters and encoding the text data.

[0154] Extraction and analysis of similar cases

[0155] Based on the pre-processed data, the server extracts similar past failures and successes from the database. A generative AI model is then used to analyze the extracted cases and identify the causes of failures and factors behind successes. Specific algorithms are used to analyze the data for patterns and trends.

[0156] Generating strategic recommendations

[0157] From the identified causes and factors, the generative AI model generates specific strategic recommendations, such as revising marketing strategies, changing product features, and providing specific action plans to improve competitive advantage.

[0158] Providing real-time recommendations

[0159] The generated recommendations are sent from the server to the device and provided to the user, where the generative AI model has the ability to update the recommendations in real time based on market changes and competitive conditions.

[0160] Hardware and software used

[0161] Cloud servers (e.g., Amazon AWS, Google Cloud Platform)

[0162] Local PC or mobile device

[0163] Software: Flask (Python Web Framework), OpenAI GPT-3 API (generative AI model)

[0164] Specific example explanation

[0165] For example, if a user is entering a business idea for a new eco-friendly detergent, the following information may be entered:

[0166] Idea: Eco-friendly detergent

[0167] Target market: Environmentally conscious young families

[0168] Product Features: Natural ingredients, reusable packaging

[0169] Competitive Intelligence: Leading Eco-Friendly Detergents on the Market Today

[0170] Based on this, the server processes the data and the generative AI model provides recommendations as follows:

[0171] The causes of failure were identified as "barriers to purchase due to high price range" and "lack of name recognition in the market," while the factors for success were identified as "better ingredients than competitors" and "implementation of a unique marketing campaign." As a result, specific action plans were proposed as strategic recommendations, including "adjusting the price range by taking cost-reduction measures to lower the barrier to purchase," "developing a marketing campaign using social media and influencers to increase name recognition," and "providing empirical data proving the effectiveness of the product to gain consumer trust."

[0172] Prompt Sentence Examples

[0173] New Product Idea: Eco-Friendly Detergent

[0174] Target market: Environmentally conscious young families

[0175] Product Features: Natural ingredients, reusable packaging

[0176] Competitive Intelligence: Leading Eco-Friendly Detergents on the Market Today

[0177] Identify causes of failure and factors of success and provide strategic recommendations.

[0178] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0179] Step 1: User Data Entry

[0180] Users input detailed information about new product ideas and business strategies into the device, including specific information about the target market, product characteristics, and competitor information. The input information is stored on the device as structured data and prepared for transmission to the server.

[0181] Input: Business idea, target market, product characteristics, competitor information

[0182] Output: Structured data ready to send

[0183] Step 2: Data transmission and preprocessing

[0184] The terminal sends the entered data to the server, which preprocesses the received data. Preprocessing includes removing special characters and encoding text data, converting the data into a format that can be analyzed.

[0185] Input: Structured data sent from the device

[0186] Output: Preprocessed, analyzable data

[0187] Step 3: Extracting similar cases

[0188] Based on the preprocessed data, the server extracts similar past failures and successes from the database and uses a generative AI model to select cases with high similarity.

[0189] Input: Preprocessed data, database of past cases

[0190] Output: Extracted similar past cases

[0191] Step 4: Case analysis

[0192] The server analyzes the extracted past cases to identify the causes of failure and the factors behind success. The generative AI model detects patterns and trends in the data and outputs the causes and factors as analysis results.

[0193] Input: Extracted similar cases

[0194] Output: Identified causes of failure and factors of success

[0195] Step 5: Generate strategic recommendations

[0196] The server uses generative AI models to generate strategic recommendations based on the identified causes of failure and factors of success, and prompts are used to create detailed recommendations.

[0197] Input: Identified causes of failure and factors of success

[0198] Output: Strategic recommendations

[0199] Step 6: Providing and updating recommendations

[0200] The generated recommendations are sent from the server to the device and provided to the user. The server monitors market changes and competitive conditions in real time and updates the recommendations using the generative AI model.

[0201] Inputs: Strategic recommendations, real-time market data

[0202] Output: Updated and served latest recommendations

[0203] Through the above processing steps, users can obtain specific strategies and feedback for new business ideas in real time.

[0204] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0205] The present invention relates to a system that combines an emotion engine that recognizes user emotions in order to perform more advanced analysis of business ideas. Specific embodiments for carrying out the present invention will be described in detail below.

[0206] User operations

[0207] Users input detailed information about their business idea (such as target market, product characteristics, competitor information, etc.) into the terminal. As they input information, the user's emotional state is also analyzed in real time by the emotion engine.

[0208] Data reception and preprocessing on the server

[0209] The server receives the business idea data sent from the device and the user's emotion data recognized by the emotion engine. The received data is preprocessed and converted into a format suitable for analysis. This conversion includes normalizing and encoding the text data.

[0210] Emotion data integration and similar case extraction

[0211] Based on the preprocessed data and emotional data, the server extracts similar failure and success cases from the database. In particular, it is possible to perform analysis taking emotional data into consideration. The database stores information on past cases associated with emotional data.

[0212] Generative AI model analysis and recommendation generation

[0213] For each case drawn from the database, the generative AI model identifies the causes of failure and the factors behind success. By incorporating emotional data, the model generates recommendations tailored to the user's emotional state, such as adjusting marketing strategies to take into account stress and anxiety levels.

[0214] User Feedback

[0215] The generated strategic recommendations are sent from the server to the device, which then displays them to the user. The information is presented as a concrete action plan that also reflects the user's emotional state. Based on this, the user can reevaluate their business strategy and make adjustments to increase the probability of success.

[0216] Specific examples

[0217] For example, when a user inputs a business idea for a new health food product (e.g., a protein bar), the emotion engine may sense the user's anxiety. This information is then linked to the cause of failure, such as intense market competition, by the generative AI model, and specific advice is provided, such as "use specific ingredients, differentiate the product, and develop a targeted marketing campaign." In this way, this system can provide more accurate strategic advice by analyzing complex information, including emotion data.

[0218] By introducing a new approach that takes into account the user's emotional state, the system of the present invention is able to provide more advanced analysis and recommendations than conventional business consulting methods.

[0219] The processing flow will be explained below.

[0220] Step 1:

[0221] Users input detailed information about their business idea, including target markets, product characteristics, competitor information, etc. As they input information, the emotion engine also captures the user's emotions in real time via the camera and microphone.

[0222] Step 2:

[0223] The device receives data entered by the user and emotion data recognized by the emotion engine, and temporarily stores the received data.

[0224] Step 3:

[0225] The device encodes the stored data into a format that can be parsed and sends it to the server in a standard format such as JSON.

[0226] Step 4:

[0227] The server receives the data sent from the terminal and stores the received data for preprocessing.

[0228] Step 5:

[0229] The server preprocesses the received data, removing special characters and converting text data into a format suitable for analysis by normalizing and encoding it. Emotion data is also formatted for analysis.

[0230] Step 6:

[0231] The server uses the preprocessed data to execute queries to extract past failures and successes from the database. Since past cases also contain similar emotional data, extraction based on emotional data is possible.

[0232] Step 7:

[0233] The server uses a generative AI model to analyze the failure and success cases extracted from the database. The AI ​​model analyzes data patterns and trends to identify causes of failure and factors for success. By incorporating emotional data into the analysis, it can provide accurate recommendations based on the user's emotional state.

[0234] Step 8:

[0235] Based on the analysis results of the generative AI model, the server generates strategic recommendations that take into account emotional data, including recommendations for reviewing marketing strategies, changing product characteristics, and specific action plans.

[0236] Step 9:

[0237] The server encodes the generated recommendations in a standard format such as JSON and sends them to the device.

[0238] Step 10:

[0239] The device decodes the recommendations received from the server and displays them to the user in an easy-to-read format, including a specific action plan tailored based on the user's emotional data.

[0240] Step 11:

[0241] Users can review the displayed recommendations and adjust or improve their business strategies. By taking into account advice based on emotion data, they can create more accurate business plans.

[0242] Through this series of processes, the system can provide users with specific and effective strategic recommendations, increasing the probability of business success. The incorporation of an emotion engine enables advanced business consulting that adapts to the user's psychological state.

[0243] Example 2

[0244] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0245] Conventional business idea analysis systems do not take into account the user's emotional state, making it difficult to provide optimal recommendations. Furthermore, they ignore the impact of the user's emotional state on the success or failure of a business, making them inadequate for strategic decision-making. Furthermore, there is no method for analyzing detailed business idea information and emotional data in an integrated manner, so more accurate analysis is needed.

[0246] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0247] In this invention, the server includes means for analyzing the user's emotional state in real time at the time of input, means for receiving and preprocessing the input business idea data and emotional data, means for extracting similar past failures and successes from a database based on the preprocessed data, means for analyzing the extracted cases and identifying the causes of failure and factors of success, means for generating strategic recommendations based on the identified causes and factors in accordance with the user's emotional state, and means for providing the generated recommendations to the user. This enables advanced analysis and recommendation of business ideas that take the user's emotions into consideration.

[0248] "User" refers to a person who enters details about a business idea into the system.

[0249] "Business Idea" means a plan or strategy for a particular product or service that a User devises and enters into the System.

[0250] "Detailed information" refers to specific data entered by the user regarding the business idea, including target markets, product characteristics, competitor information, and the like.

[0251] "Terminal" refers to the electronic device used by a user to input business ideas and receive recommendations.

[0252] "Emotional state" refers to the psychological state that is analyzed by the emotion engine when a user inputs a business idea.

[0253] An "emotion engine" refers to an algorithm or software that analyzes a user's emotional state from input text or voice information.

[0254] "Data" refers to information about business ideas and emotional states that is received, pre-processed and analyzed by the System.

[0255] "Preprocessing" refers to the process of normalizing and encoding input data into a format that is easy to analyze.

[0256] A "database" refers to a collection of information that stores past success stories and failure stories.

[0257] The "similar past failures and successes" are past cases related to the input business idea, and are extracted from the database.

[0258] A "generative AI model" refers to an artificial intelligence algorithm that identifies causes of failure and factors of success based on input data and emotional data, and generates recommendations.

[0259] "Recommendations" refers to strategic advice or suggestions provided based on the results of analysis by a generative AI model.

[0260] "Normalization" refers to the process of converting input data into a uniform format.

[0261] "Encoding" refers to the process of converting data into a format that is easier to analyze.

[0262] The present invention relates to an advanced business idea analysis system that takes into account the user's emotional state. Specifically, the system generates highly accurate recommendations using an emotion engine that analyzes the user's emotional state in real time when the user inputs a business idea. Specific embodiments of the present invention are described in detail below.

[0263] Hardware and software used

[0264] Hardware

[0265] Server: Use a dedicated server with a high-performance processor and sufficient memory to smoothly receive data, preprocess it, search the database, and run the generative AI model.

[0266] Terminal: A PC, tablet, or smartphone is used for user input. The terminal communicates with the emotion engine to obtain the user's emotion data.

[0267] software

[0268] Emotion engine: Software that analyzes the user's emotional state from input data, for example, using Azure's Emotion API.

[0269] Database: Use MySQL or another relational database system to manage historical case information.

[0270] Generative AI model: Uses OpenAI's GPT-4 and other models to generate recommendations based on business ideas and emotional data.

[0271] Specific operation example

[0272] 1. User operations

[0273] The user inputs detailed information about their business idea into the device. For example, the user might input, "I want to sell a new protein bar to people in their 30s." The device then uses an emotion engine to analyze the user's emotional state in real time. For example, the device may return a result such as, "The user is feeling anxious."

[0274] 2. Data reception and preprocessing by the server

[0275] The server receives the business idea data and sentiment data sent from the device. The server preprocesses the received data, normalizing and encoding it as necessary. For example, the server converts the input "The target market is health-conscious people in their 30s" into "target_market: 30s health-conscious consumers."

[0276] 3. Case extraction and analysis by the server

[0277] After the preprocessing is complete, the server extracts similar past failures and successes from the database. The server also takes into account emotional data to find the most relevant cases. For example, it searches for "protein bars for health-conscious people in their 30s" and "anxiety."

[0278] 4. Server-generated recommendations

[0279] The server analyzes the cases extracted from the database using a generative AI model. The generative AI model identifies the causes of failure and factors of success and generates recommendations that best fit the user's emotional state. For example, specific advice is provided, such as "conduct thorough market research" or "emphasize low-carb and limit the target to people in their 30s."

[0280] 5. Feedback from the server to the device

[0281] The generated strategic recommendations are sent from the server to the terminal, which displays them to the user as concrete action plans, allowing the user to reevaluate their business strategies based on them.

[0282] Prompt Sentence Examples

[0283] "I'm starting a new health food business and would like some advice on how to succeed in a crowded market. I need advice on using specific ingredients to differentiate my product and developing targeted marketing campaigns."

[0284] In this way, this system provides advanced analysis and recommendations of business ideas that take into account the user's emotional state, thereby supporting more accurate strategic decision-making than conventional methods.

[0285] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0286] Step 1:

[0287] The user enters the details.

[0288] Specifically, the user inputs information about their business idea (e.g., target market, product characteristics, competitor information, etc.) into the terminal. Once the input is complete, the emotion engine analyzes the user's emotional state in real time.

[0289] Input: Business idea details and the user's emotional state.

[0290] Output: Sentiment data parsed by the emotion engine.

[0291] Specific operation: When a user enters "I want to sell a new protein bar to people in their 30s," the device records this and simultaneously sends emotional data such as the user's anxieties and expectations to the emotion engine for analysis.

[0292] Step 2:

[0293] Send data from the terminal to the server.

[0294] The terminal transmits the business idea data entered by the user and the emotion data analyzed by the emotion engine to the server.

[0295] Input: Business idea details, sentiment data.

[0296] Output: Business idea data and emotion data received by the server.

[0297] Specific operation: The device compiles data such as "The target market is health-conscious people in their 30s" and "The user is feeling anxious" and sends it to the server.

[0298] Step 3:

[0299] The server receives and preprocesses the data.

[0300] The server preprocesses the received business idea data and sentiment data, normalizing and encoding them as necessary.

[0301] Input: Received business idea data, sentiment data.

[0302] Output: Preprocessed data.

[0303] Specific operation: The server converts the data into a format suitable for analysis, such as "target_market: 30s health-conscious consumers" or "users are anxious."

[0304] Step 4:

[0305] The server performs data integration and case extraction.

[0306] Based on the pre-processed data, the server extracts similar past failures and successes from a database, and searches the database, taking into account the sentiment data, to find the most relevant cases.

[0307] Input: Preprocessed business idea data, sentiment data.

[0308] Output: Extracted historical case data.

[0309] Specific operation: The server searches the database and extracts past cases related to "protein bars for health-conscious people in their 30s" and "anxiety."

[0310] Step 5:

[0311] The server performs case analysis and recommendation generation.

[0312] Based on the extracted cases, the server uses a generative AI model to analyze them, identify the causes of failure and the factors behind success, and generate recommendations that best fit the user's emotional state.

[0313] Input: extracted case data, generative AI model.

[0314] Output: The generated recommendations.

[0315] Specific operation: The generative AI model generates recommendations such as "You should conduct thorough market research" and "Emphasis on low-carb and narrow the target to people in their 30s."

[0316] Step 6:

[0317] The server sends the recommendations to the device.

[0318] The generated recommendations are sent from the server to the device, which displays this information to the user.

[0319] Input: The generated recommendations.

[0320] Output: The recommendations that are served to the user.

[0321] Specific operation: The server sends a recommendation to the device, such as "Low-sugar, high-protein protein bars are in high demand. Marketing should be strengthened, especially for health-conscious people in their 30s," and the device displays it to the user.

[0322] (Application example 2)

[0323] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0324] The present invention aims to solve the problem that, when users realize their business ideas, conventional systems provide general advice without considering the user's emotional state, making it difficult to generate accurate recommendations that correspond to the individual situation and emotional state of the user.In particular, the present invention aims to reduce the stress and anxiety felt by operators who operate and maintain robots in factories and other workplaces, thereby achieving safe and efficient operation.

[0325] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0326] In this invention, the server includes: a means for a user to input detailed information about a business idea; a means for receiving and preprocessing the input business idea data; a means for combining the preprocessed data with an emotion engine that analyzes the user's emotional state in real time; a means for extracting similar past failures and successes from a database along with the emotion engine data; a means for analyzing the extracted cases and identifying causes of failure and factors of success; a means for generating strategic recommendations that take the user's emotional state into account from the identified causes and factors; and a means for providing the generated recommendations to the user. This makes it possible to provide advanced recommendations tailored to the user's emotional state when implementing the business idea. Furthermore, in a factory, analyzing the stress levels experienced by operators when operating or maintaining robots and providing maintenance procedures and solutions tailored to those levels enables safe and efficient operation.

[0327] "User" refers to the entity that uses the system to input business ideas and detailed information on the operation and maintenance of the robot.

[0328] A "business idea" is detailed information about a specific business or project, including market analysis, product characteristics, and competitive information.

[0329] "Emotion engine" is a general term for software and hardware that analyzes a user's emotional state in real time.

[0330] The "database" is a data storage system that accumulates information on past failures and successes associated with business ideas and emotional data.

[0331] "Preprocessing" is the process of converting data received from a user into a form suitable for analysis, including text normalization and encoding.

[0332] "Similar past failures and successes" refers to past cases extracted from the database that are similar to the current business idea or on-site situation.

[0333] "Generated recommendations" are strategic advice and specific action plans provided by generative AI models based on the results of data and sentiment analysis.

[0334] "Strategic recommendations" refer to specific advice and suggestions tailored to the user's emotional state and situation to improve the chances of business success.

[0335] This invention relates to a system that analyzes a user's emotional state and generates accurate recommendations for business ideas and on-site operations. This system mainly consists of an emotion engine, a generative AI model, a database, and a user interface.

[0336] Hardware and Software Configuration

[0337] The hardware required includes a user terminal (tablet or PC) and a wearable device for emotion analysis (such as a smartwatch), while the software includes an emotion engine, a database management system, a generative AI model, and a user interface application.

[0338] Specific processing of the system

[0339] 1. Acquiring emotion data:

[0340] A user wears a wearable device (e.g., a smartwatch) for emotion analysis, and emotion-related data such as heart rate and skin galvanic response are acquired in real time. These data are then transmitted to the user's device.

[0341] 2. Enter your business idea:

[0342] The user uses the interface of the user terminal to input detailed information about the business idea, including the target market, product characteristics, and competitor information.

[0343] 3. Data preprocessing and integration:

[0344] The data sent from the user's device is received by the server and preprocessed. The text data is normalized and encoded to convert it into a format suitable for analysis. The data is then integrated with the emotion engine data and prepared for analysis.

[0345] 4. Extraction of similar cases:

[0346] Based on the preprocessed data and the emotion data, the server extracts similar failure and success cases from a database of past cases, which stores past cases and their associated emotion data.

[0347] 5. Generating recommendations:

[0348] For each case drawn from the database, the generative AI model identifies the causes of failure and the factors behind success. By incorporating emotional data, the system generates targeted recommendations based on the user's emotional state, such as adjusting marketing strategies to take into account stress and anxiety levels.

[0349] 6. User Feedback:

[0350] The generated recommendations are sent from the server to the user's device and presented to the user through a user interface. Based on this feedback, the user can reevaluate and adjust their business strategy and on-site operations.

[0351] Specific examples

[0352] For example, if a user inputs a business idea for a new health food product (e.g., a protein bar), the emotion engine will sense the user's concerns. This information is then combined with the competitive intensity of the market through a generative AI model to provide specific recommendations, such as using specific ingredients to differentiate the product and developing a targeted marketing campaign.

[0353] Prompt Sentence Examples

[0354] "An operator is performing maintenance on a robot under high stress. Based on past cases, what smooth maintenance procedures and solutions would you recommend?"

[0355] This allows the system to perform complex information analysis, including the user's emotional state, and provide more accurate strategic advice.In factories, the system supports a safe and efficient work environment by providing maintenance procedures and solutions that take into account the operator's stress level.

[0356] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0357] Step 1:

[0358] The user wears a wearable device (e.g., a smartwatch) for emotion analysis, and physiological data such as heart rate and skin galvanic response are collected in real time.

[0359] Input: User physiological data (heart rate, galvanic skin response, etc.)

[0360] Output: Physiological data is sent to the device

[0361] How it works: The wearable device sends the data it senses to the user's device via Bluetooth or Wi-Fi.

[0362] Step 2:

[0363] The user enters detailed information about the business idea using the terminal interface, including target market, product characteristics, and competitor information.

[0364] Input: Detailed information about your business idea (text data)

[0365] Output: Detailed information is logged to the terminal

[0366] Operation: Accepts input from the keyboard or touch screen through the user device's UI.

[0367] Step 3:

[0368] The server receives the business idea data and emotion data transmitted from the terminal.

[0369] Input: Business idea data, physiological data

[0370] Output: Received data is saved on the server

[0371] Operation: The device sends the business idea and emotion data to the server as an HTTP request.

[0372] Step 4:

[0373] The server pre-processes the received data, which includes normalizing and encoding the text data and analyzing sentiment data in real time.

[0374] Input: Business idea data, physiological data

[0375] Output: Preprocessed text data and analysis results

[0376] How it works: Data is processed on the server side using a text normalizer and sentiment engine (sentiment analysis software).

[0377] Step 5:

[0378] Based on the preprocessed data, the server extracts similar past failures and successes from the database.

[0379] Input: Preprocessed text data and sentiment analysis results

[0380] Output: Extracted similar cases

[0381] How it works: The server uses a database management system (DBMS) to run queries and extract similar past cases.

[0382] Step 6:

[0383] The generative AI model analyzes the extracted cases to identify causes of failure and factors of success, and then generates strategic recommendations that take into account the user's emotional state.

[0384] Input: Extracted similar cases, sentiment analysis results

[0385] Output: Generated recommendations

[0386] How it works: A generative AI model (e.g., a GPT-based model) analyzes data and generates specific advice that reflects the user's emotional state.

[0387] Step 7:

[0388] The server transmits the generated recommendations to the user terminal and presents them to the user through a user interface.

[0389] Input: Generated recommendations

[0390] Output: Recommendations served to the user

[0391] How it works: The server sends recommendations as an HTTP response, which the device's UI application displays.

[0392] Step 8:

[0393] Example prompt: "An operator is performing maintenance on a robot under high stress. Based on past experience, what smooth maintenance procedures and solutions would you recommend?"

[0394] In this way, the system can analyze complex information, including the user's emotional state, and provide more accurate strategic recommendations.

[0395] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0396] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0397] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0398] [Second embodiment]

[0399] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0400] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0401] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0402] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0403] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0404] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0405] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0406] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0407] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0408] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0409] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0410] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0411] This invention relates to a system that utilizes generative AI and a historical database to identify the causes of failure of business ideas and provide strategic recommendations for success.

[0412] User operations

[0413] A user enters detailed information about a business idea (e.g., target market, product characteristics, competitor information, etc.) into a terminal, possibly via a web form or a mobile application. Once the user has completed the input and pressed the submit button, this data is sent to a server.

[0414] Data reception and preprocessing on the server

[0415] The server receives the business idea data sent from the device, and then preprocesses it, removing special characters and encoding the text data to make it easier to analyze.

[0416] Extraction and analysis of similar cases

[0417] After the preprocessing is complete, the server extracts similar failures and successes from a database of past cases. At this stage, a generative AI model is used to automatically identify the causes of failures and factors behind successes from past cases. The AI ​​model uses specific algorithms to analyze patterns and trends in the data.

[0418] Generating strategic recommendations

[0419] Based on the extracted causes of failure and factors of success, the generative AI model generates specific strategic recommendations, which may include revising marketing strategies, changing product features, and implementing specific action plans to improve competitive advantage.

[0420] User Feedback

[0421] The generated recommendations are sent from the server to the device for the user to review. Feedback is presented as a concrete action plan through data visualization. Based on this information, users can adjust their business strategies and take concrete measures to increase their chances of success.

[0422] Specific examples

[0423] For example, if a user inputs a business idea for a new health food (e.g., a protein bar), previous failures may identify "unplanned entry into a highly competitive market" as the cause of failure. On the other hand, successes may identify "differentiation through the incorporation of unique ingredients" as the key to success. Based on this information, the generative AI model will provide recommendations such as "use specific ingredients and conduct a marketing campaign with a narrow target market."

[0424] In this way, the system of the present invention can provide specific and effective improvement measures for business ideas provided by users, thereby increasing the probability of business success.

[0425] The processing flow will be explained below.

[0426] Step 1:

[0427] The user enters detailed information about the business idea, including the target market, product characteristics, competitor information, etc. Once the information is complete, the user presses the submit button.

[0428] Step 2:

[0429] The terminal receives the data entered by the user and sends it to the server, where the data is encoded in a standard format such as JSON.

[0430] Step 3:

[0431] The server receives the data sent from the terminal, stores it temporarily, and passes it on to the next process.

[0432] Step 4:

[0433] The server pre-processes the received data by removing special characters and encoding the text data into a format suitable for analysis.

[0434] Step 5:

[0435] The server uses the preprocessed data to run queries to extract past failures and successes from a database of similar business ideas.

[0436] Step 6:

[0437] The server then passes the failure and success cases extracted from the database to a generative AI model for analysis, which analyzes the data for patterns and trends to identify the causes of failure and the factors behind success.

[0438] Step 7:

[0439] The server generates strategic recommendations based on the analysis results obtained from the generative AI model, which may include reviewing marketing strategies or changing product characteristics.

[0440] Step 8:

[0441] The server encodes the generated recommendations and sends them to the device in a standard format such as JSON.

[0442] Step 9:

[0443] The device decodes the recommendations received from the server and displays them in an easy-to-read format for the user, who can then review them and use them to adjust their business strategies.

[0444] Through this series of processes, the system can provide users with specific and effective strategic recommendations, increasing the probability of business success.

[0445] Example 1

[0446] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0447] Conventional business strategy formulation systems often rely on manual analysis of past case data, resulting in a lack of accuracy and efficiency. They also face the problem of difficulty in monitoring market changes and competitive situations in real time and updating strategies immediately. This makes it difficult for users to quickly and accurately evaluate business ideas and receive strategic recommendations.

[0448] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0449] In this invention, the server includes means for a user to input detailed information about a business idea, means for receiving and preprocessing the input business idea data, means for extracting similar past failures and successes from a database based on the preprocessed data, means for analyzing the extracted cases using a generative AI model and identifying causes of failure and factors of success, means for generating strategic recommendations from the identified causes and factors, and means for providing the generated recommendations to the user, thereby enabling the user to receive a quick and accurate evaluation of their business idea and receive specific strategic recommendations in real time.

[0450] "User" means a person or organization that provides information about a business idea and uses the system to receive ratings and recommendations.

[0451] A "business idea" is a specific plan or concept for business activities, such as a new product or service offering method or market development strategy.

[0452] A "terminal" is an electronic device, such as a personal computer or smartphone, that a user uses to input information about a business idea.

[0453] A "server" is a computer system or software that receives business idea data sent by users, analyzes it, and generates recommendations.

[0454] "Preprocessing" refers to processes such as data cleaning and encoding to convert received data into a format that is easier to analyze.

[0455] A "database" is an information management system that systematically stores related information, such as past failures and successes, and allows for searching and extraction.

[0456] A "generative AI model" is an algorithm or model used to analyze patterns and trends in data using artificial intelligence to generate specific recommendations.

[0457] "Recommendations" are advice and guidelines provided to users by the system with the aim of proposing strategies and specific action plans for business success.

[0458] "Preprocessed data" means data that has been received, cleaned, encoded, and converted into a form suitable for analysis.

[0459] "Real-time" refers to processing and feedback that immediately reflects the current state without delay.

[0460] This invention is a system that allows users to input detailed information about a business idea, analyzes past case data using a generative AI model based on that information, and provides specific strategic recommendations. Next, a specific embodiment of this system will be described.

[0461] User operations

[0462] A user inputs detailed information about their business idea (such as the target market, product characteristics, and competitor information) into a terminal. This is typically done using a web form or a mobile application. For example, if a user inputs a business idea for a "new protein bar," they might enter specific information such as "fitness enthusiasts" as the target market, "high protein, low sugar" as the product characteristics, and "a product from a well-known health food company" as the competitor information.

[0463] Data reception and preprocessing on the server

[0464] The server receives the business idea data sent from the device. After receiving the data, the server preprocesses it. This preprocessing includes removing special characters and insignificant spaces. The server also converts the data into a format that is easier to analyze. For example, it normalizes and encodes text data. Specifically, it is common to use Python libraries (such as pandas or numpy) to format the data.

[0465] Extraction and analysis of similar cases

[0466] After the preprocessing is complete, the server extracts similar business ideas from a past database. For example, it uses an SQL query to search for past failures and successes. The extracted case data is fed into a generative AI model, which then identifies the causes of failure and factors behind success. Generative AI models are built using deep learning frameworks such as TensorFlow and PyTorch, and may use supervised learning and reinforcement learning algorithms.

[0467] Generating strategic recommendations

[0468] The causes of failure and factors of success identified by the AI ​​model are used to generate specific strategic recommendations, such as using specific ingredients and conducting targeted marketing campaigns. The recommendations are then analyzed through algorithms developed using tools such as Jupyter Notebook and Google Colab.

[0469] User Feedback

[0470] The generated recommendations are sent from the server to the device, where the user can review them. Feedback is presented as a concrete action plan through data visualization, for example, using data visualization tools such as Grafana or Tableau, which can be easily understood by the user.

[0471] Specific examples

[0472] As a concrete example, let's consider the case where a user inputs a business idea for a new health food product (e.g., a protein bar). Based on past failures, the cause of failure was identified as "unplanned entry into a highly competitive market." On the other hand, based on successful cases, the key to success was identified as "differentiation through the incorporation of unique ingredients." Based on this information, the generative AI model provides recommendations such as "use specific ingredients and conduct a marketing campaign with a narrow target market."

[0473] Prompt Sentence Examples

[0474] Below are some examples of prompts for generative AI models:

[0475] "A user is considering launching a new protein bar into the market. They have entered their target market and product characteristics. Based on past similar cases, please analyze the possible causes of failure and factors for success and provide specific strategic recommendations."

[0476] In this way, users can adjust their business strategies based on the specific improvements provided and increase their chances of success.

[0477] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0478] Step 1: User Input and Data Submission

[0479] The user enters detailed information about their business idea into the device, including the target market, product characteristics, and competitor information. For example, when a user enters a business idea for a "new protein bar," they enter data such as the target market (fitness enthusiasts), product characteristics (high protein, low sugar), and competitor information (product from a health food company). Once this data is entered, the user presses the submit button, and the entered data is sent from the device to the server. Input is made into a text field, and after submission, the data is encoded in JSON format and sent to the server.

[0480] Input: Details of your business idea entered by the user

[0481] Output: JSON encoded data

[0482] Step 2: Data reception and preprocessing

[0483] The server receives business idea data sent from the device. The received data is logged and preprocessing begins. Preprocessing involves removing special characters, deleting meaningless spaces, and normalizing the data. For example, text data such as "high protein, low sugar" is converted to lowercase and encoded into a numeric vector or TF-IDF format. Python libraries (e.g., pandas, numpy) are used for preprocessing.

[0484] Input: Business idea data in JSON format

[0485] Output: Normalized and encoded data

[0486] Step 3: Extracting similar cases

[0487] After the preprocessing is complete, the server extracts similar failure and success cases from the past database. It uses an SQL query to search for past cases related to, for example, "protein bars." The extracted cases are used to classify the factors behind success and failure based on past training data.

[0488] Input: Normalized and encoded data

[0489] Output: Similar past failures and successes

[0490] Step 4: Analysis by generative AI model

[0491] The server analyzes the extracted cases using a generative AI model (e.g., a deep learning model) that analyzes patterns and trends based on past data to identify causes of failure and factors of success. The model is built using frameworks such as TensorFlow and PyTorch.

[0492] Input: Similar past failures and successes

[0493] Output: Identified causes of failure and factors of success

[0494] Step 5: Generate strategic recommendations

[0495] Based on the identified causes of failure and factors of success, the server uses a generative AI model to generate strategic recommendations, such as a specific action plan such as "use specific ingredients and conduct a marketing campaign targeting the target market." This process is typically carried out using tools such as Jupyter Notebook or Google Colab.

[0496] Input: Identified causes of failure and factors of success

[0497] Output: Specific strategic recommendations

[0498] Step 6: User feedback

[0499] The generated recommendations are sent from the server to the device, and the feedback is presented as a concrete action plan through data visualization, for example, using tools such as Grafana or Tableau, in a visually easy-to-understand format.

[0500] Input: Specific strategic recommendations

[0501] Output: Feedback via data visualization

[0502] Prompt Sentence Examples

[0503] Below are some examples of prompts for generative AI models:

[0504] "A user is considering launching a new protein bar into the market. They have entered their target market and product characteristics. Based on past similar cases, please analyze the possible causes of failure and factors for success and provide specific strategic recommendations."

[0505] (Application example 1)

[0506] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0507] Conventional business idea evaluation systems struggle to identify the causes of failure and factors for success from past cases, making it impossible to provide effective strategic recommendations. Furthermore, they are unable to reflect market changes and competitive situations in real time, making it impossible to provide users with practical feedback. Furthermore, the data entered by users comes in a variety of formats, and if proper preprocessing is not performed, the accuracy of analysis can decrease. This makes it difficult to increase the success rate of businesses.

[0508] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0509] In this invention, the server includes: a means for a user to input detailed information about a business idea; a means for receiving and preprocessing the input business idea data; a means for extracting similar past failures and successes from a database based on the preprocessed data; a means for analyzing the extracted cases and identifying causes of failure and factors of success; a means for generating strategic recommendations from the identified causes and factors; a means for providing the generated recommendations to the user; a means for using a generative AI model to generate recommendations and performing analysis based on prompt statements; and a means for updating and displaying the generated recommendations in real time. This allows the generative AI model to provide effective recommendations for business ideas based on past cases, enabling real-time feedback that reflects market changes and competitive conditions. Furthermore, by normalizing and encoding the format of the data entered by the user, the accuracy of analysis can be improved, making it possible to provide specific strategies for business success.

[0510] A "user" is someone who inputs detailed information about a business idea and receives evaluation results and recommendations.

[0511] A "business idea" is a concept or detailed information about a new product, service, or business model.

[0512] "Detailed information" refers to specific data related to the business idea, such as the target market, product characteristics, and competitor information.

[0513] A "database" is an information collection that stores data such as past failures and successes.

[0514] "Causes of failure" are the reasons or factors that led to businesses not being successful in past cases.

[0515] "Factors for success" are the reasons and factors that led to business success in past cases.

[0516] "Strategic recommendations" refer to specific strategies and action plans to increase the success rate of a business idea.

[0517] A "generative AI model" is an algorithm that uses artificial intelligence to analyze patterns and trends in data and generate recommendations.

[0518] A "prompt sentence" is text data input into a generative AI model, and is an instruction sentence that the model uses to analyze and generate.

[0519] "Real-time" is a time concept that means data processing and information updates are instantaneous.

[0520] "Normalization" is the process of standardizing data into a certain format.

[0521] "Encoding" is the process of converting data into a format that is easy to analyze.

[0522] The present invention is a system that utilizes a generative AI model to identify causes of failure and factors for success of business ideas from a past database and provides strategic recommendations. The system includes the following means.

[0523] User data entry

[0524] Users use a terminal to input detailed information about new product ideas and business strategies, including target markets, product characteristics, and competitor information.

[0525] Data transmission and preprocessing

[0526] The entered data is sent from the terminal to the server, which preprocesses the received data, removing special characters and encoding the text data.

[0527] Extraction and analysis of similar cases

[0528] Based on the pre-processed data, the server extracts similar past failures and successes from the database. A generative AI model is then used to analyze the extracted cases and identify the causes of failures and factors behind successes. Specific algorithms are used to analyze the data for patterns and trends.

[0529] Generating strategic recommendations

[0530] From the identified causes and factors, the generative AI model generates specific strategic recommendations, such as revising marketing strategies, changing product features, and providing specific action plans to improve competitive advantage.

[0531] Providing real-time recommendations

[0532] The generated recommendations are sent from the server to the device and provided to the user, where the generative AI model has the ability to update the recommendations in real time based on market changes and competitive conditions.

[0533] Hardware and software used

[0534] Cloud servers (e.g., Amazon AWS, Google Cloud Platform)

[0535] Local PC or mobile device

[0536] Software: Flask (Python Web Framework), OpenAI GPT-3 API (generative AI model)

[0537] Specific example explanation

[0538] For example, if a user is entering a business idea for a new eco-friendly detergent, the following information may be entered:

[0539] Idea: Eco-friendly detergent

[0540] Target market: Environmentally conscious young families

[0541] Product Features: Natural ingredients, reusable packaging

[0542] Competitive Intelligence: Leading Eco-Friendly Detergents on the Market Today

[0543] Based on this, the server processes the data and the generative AI model provides recommendations as follows:

[0544] The causes of failure were identified as "barriers to purchase due to high price range" and "lack of name recognition in the market," while the factors for success were identified as "better ingredients than competitors" and "implementation of a unique marketing campaign." As a result, specific action plans were proposed as strategic recommendations, including "adjusting the price range by taking cost-reduction measures to lower the barrier to purchase," "developing a marketing campaign using social media and influencers to increase name recognition," and "providing empirical data proving the effectiveness of the product to gain consumer trust."

[0545] Prompt Sentence Examples

[0546] New Product Idea: Eco-Friendly Detergent

[0547] Target market: Environmentally conscious young families

[0548] Product Features: Natural ingredients, reusable packaging

[0549] Competitive Intelligence: Leading Eco-Friendly Detergents on the Market Today

[0550] Identify causes of failure and factors of success and provide strategic recommendations.

[0551] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0552] Step 1: User Data Entry

[0553] Users input detailed information about new product ideas and business strategies into the device, including specific information about the target market, product characteristics, and competitor information. The input information is stored on the device as structured data and prepared for transmission to the server.

[0554] Input: Business idea, target market, product characteristics, competitor information

[0555] Output: Structured data ready to send

[0556] Step 2: Data transmission and preprocessing

[0557] The terminal sends the entered data to the server, which preprocesses the received data. Preprocessing includes removing special characters and encoding text data, converting the data into a format that can be analyzed.

[0558] Input: Structured data sent from the device

[0559] Output: Preprocessed, analyzable data

[0560] Step 3: Extracting similar cases

[0561] Based on the preprocessed data, the server extracts similar past failures and successes from the database and uses a generative AI model to select cases with high similarity.

[0562] Input: Preprocessed data, database of past cases

[0563] Output: Extracted similar past cases

[0564] Step 4: Case analysis

[0565] The server analyzes the extracted past cases to identify the causes of failure and the factors behind success. The generative AI model detects patterns and trends in the data and outputs the causes and factors as analysis results.

[0566] Input: Extracted similar cases

[0567] Output: Identified causes of failure and factors of success

[0568] Step 5: Generate strategic recommendations

[0569] The server uses generative AI models to generate strategic recommendations based on the identified causes of failure and factors of success, and prompts are used to create detailed recommendations.

[0570] Input: Identified causes of failure and factors of success

[0571] Output: Strategic recommendations

[0572] Step 6: Providing and updating recommendations

[0573] The generated recommendations are sent from the server to the device and provided to the user. The server monitors market changes and competitive conditions in real time and updates the recommendations using the generative AI model.

[0574] Inputs: Strategic recommendations, real-time market data

[0575] Output: Updated and served latest recommendations

[0576] Through the above processing steps, users can obtain specific strategies and feedback for new business ideas in real time.

[0577] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0578] The present invention relates to a system that combines an emotion engine that recognizes user emotions in order to perform more advanced analysis of business ideas. Specific embodiments for carrying out the present invention will be described in detail below.

[0579] User operations

[0580] Users input detailed information about their business idea (such as target market, product characteristics, competitor information, etc.) into the terminal. As they input information, the user's emotional state is also analyzed in real time by the emotion engine.

[0581] Data reception and preprocessing on the server

[0582] The server receives the business idea data sent from the device and the user's emotion data recognized by the emotion engine. The received data is preprocessed and converted into a format suitable for analysis. This conversion includes normalizing and encoding the text data.

[0583] Emotion data integration and similar case extraction

[0584] Based on the preprocessed data and emotional data, the server extracts similar failure and success cases from the database. In particular, it is possible to perform analysis taking emotional data into consideration. The database stores information on past cases associated with emotional data.

[0585] Generative AI model analysis and recommendation generation

[0586] For each case drawn from the database, the generative AI model identifies the causes of failure and the factors behind success. By incorporating emotional data, the model generates recommendations tailored to the user's emotional state, such as adjusting marketing strategies to take into account stress and anxiety levels.

[0587] User Feedback

[0588] The generated strategic recommendations are sent from the server to the device, which then displays them to the user. The information is presented as a concrete action plan that also reflects the user's emotional state. Based on this, the user can reevaluate their business strategy and make adjustments to increase the probability of success.

[0589] Specific examples

[0590] For example, when a user inputs a business idea for a new health food product (e.g., a protein bar), the emotion engine may sense the user's anxiety. This information is then linked to the cause of failure, such as intense market competition, by the generative AI model, and specific advice is provided, such as "use specific ingredients, differentiate the product, and develop a targeted marketing campaign." In this way, this system can provide more accurate strategic advice by analyzing complex information, including emotion data.

[0591] By introducing a new approach that takes into account the user's emotional state, the system of the present invention is able to provide more advanced analysis and recommendations than conventional business consulting methods.

[0592] The processing flow will be explained below.

[0593] Step 1:

[0594] Users input detailed information about their business idea, including target markets, product characteristics, competitor information, etc. As they input information, the emotion engine also captures the user's emotions in real time via the camera and microphone.

[0595] Step 2:

[0596] The device receives data entered by the user and emotion data recognized by the emotion engine, and temporarily stores the received data.

[0597] Step 3:

[0598] The device encodes the stored data into a format that can be parsed and sends it to the server in a standard format such as JSON.

[0599] Step 4:

[0600] The server receives the data sent from the terminal and stores the received data for preprocessing.

[0601] Step 5:

[0602] The server preprocesses the received data, removing special characters and converting text data into a format suitable for analysis by normalizing and encoding it. Emotion data is also formatted for analysis.

[0603] Step 6:

[0604] The server uses the preprocessed data to execute queries to extract past failures and successes from the database. Since past cases also contain similar emotional data, extraction based on emotional data is possible.

[0605] Step 7:

[0606] The server uses a generative AI model to analyze the failure and success cases extracted from the database. The AI ​​model analyzes data patterns and trends to identify causes of failure and factors for success. By incorporating emotional data into the analysis, it can provide accurate recommendations based on the user's emotional state.

[0607] Step 8:

[0608] Based on the analysis results of the generative AI model, the server generates strategic recommendations that take into account emotional data, including recommendations for reviewing marketing strategies, changing product characteristics, and specific action plans.

[0609] Step 9:

[0610] The server encodes the generated recommendations in a standard format such as JSON and sends them to the device.

[0611] Step 10:

[0612] The device decodes the recommendations received from the server and displays them to the user in an easy-to-read format, including a specific action plan tailored based on the user's emotional data.

[0613] Step 11:

[0614] Users can review the displayed recommendations and adjust or improve their business strategies. By taking into account advice based on emotion data, they can create more accurate business plans.

[0615] Through this series of processes, the system can provide users with specific and effective strategic recommendations, increasing the probability of business success. The incorporation of an emotion engine enables advanced business consulting that adapts to the user's psychological state.

[0616] Example 2

[0617] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0618] Conventional business idea analysis systems do not take into account the user's emotional state, making it difficult to provide optimal recommendations. Furthermore, they ignore the impact of the user's emotional state on the success or failure of a business, making them inadequate for strategic decision-making. Furthermore, there is no method for analyzing detailed business idea information and emotional data in an integrated manner, so more accurate analysis is needed.

[0619] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0620] In this invention, the server includes means for analyzing the user's emotional state in real time at the time of input, means for receiving and preprocessing the input business idea data and emotional data, means for extracting similar past failures and successes from a database based on the preprocessed data, means for analyzing the extracted cases and identifying the causes of failure and factors of success, means for generating strategic recommendations based on the identified causes and factors in accordance with the user's emotional state, and means for providing the generated recommendations to the user. This enables advanced analysis and recommendation of business ideas that take the user's emotions into consideration.

[0621] "User" refers to a person who enters details about a business idea into the system.

[0622] "Business Idea" means a plan or strategy for a particular product or service that a User devises and enters into the System.

[0623] "Detailed information" refers to specific data entered by the user regarding the business idea, including target markets, product characteristics, competitor information, and the like.

[0624] "Terminal" refers to the electronic device used by a user to input business ideas and receive recommendations.

[0625] "Emotional state" refers to the psychological state that is analyzed by the emotion engine when a user inputs a business idea.

[0626] An "emotion engine" refers to an algorithm or software that analyzes a user's emotional state from input text or voice information.

[0627] "Data" refers to information about business ideas and emotional states that is received, pre-processed and analyzed by the System.

[0628] "Preprocessing" refers to the process of normalizing and encoding input data into a format that is easy to analyze.

[0629] A "database" refers to a collection of information that stores past success stories and failure stories.

[0630] The "similar past failures and successes" are past cases related to the input business idea, and are extracted from the database.

[0631] A "generative AI model" refers to an artificial intelligence algorithm that identifies causes of failure and factors of success based on input data and emotional data, and generates recommendations.

[0632] "Recommendations" refers to strategic advice or suggestions provided based on the results of analysis by a generative AI model.

[0633] "Normalization" refers to the process of converting input data into a uniform format.

[0634] "Encoding" refers to the process of converting data into a format that is easier to analyze.

[0635] The present invention relates to an advanced business idea analysis system that takes into account the user's emotional state. Specifically, the system generates highly accurate recommendations using an emotion engine that analyzes the user's emotional state in real time when the user inputs a business idea. Specific embodiments of the present invention are described in detail below.

[0636] Hardware and software used

[0637] Hardware

[0638] Server: Use a dedicated server with a high-performance processor and sufficient memory to smoothly receive data, preprocess it, search the database, and run the generative AI model.

[0639] Terminal: A PC, tablet, or smartphone is used for user input. The terminal communicates with the emotion engine to obtain the user's emotion data.

[0640] software

[0641] Emotion engine: Software that analyzes the user's emotional state from input data, for example, using Azure's Emotion API.

[0642] Database: Use MySQL or another relational database system to manage historical case information.

[0643] Generative AI model: Uses OpenAI's GPT-4 and other models to generate recommendations based on business ideas and emotional data.

[0644] Specific operation example

[0645] 1. User operations

[0646] The user inputs detailed information about their business idea into the device. For example, the user might input, "I want to sell a new protein bar to people in their 30s." The device then uses an emotion engine to analyze the user's emotional state in real time. For example, the device may return a result such as, "The user is feeling anxious."

[0647] 2. Data reception and preprocessing by the server

[0648] The server receives the business idea data and sentiment data sent from the device. The server preprocesses the received data, normalizing and encoding it as necessary. For example, the server converts the input "The target market is health-conscious people in their 30s" into "target_market: 30s health-conscious consumers."

[0649] 3. Case extraction and analysis by the server

[0650] After the preprocessing is complete, the server extracts similar past failures and successes from the database. The server also takes into account emotional data to find the most relevant cases. For example, it searches for "protein bars for health-conscious people in their 30s" and "anxiety."

[0651] 4. Server-generated recommendations

[0652] The server analyzes the cases extracted from the database using a generative AI model. The generative AI model identifies the causes of failure and factors of success and generates recommendations that best fit the user's emotional state. For example, specific advice is provided, such as "conduct thorough market research" or "emphasize low-carb and limit the target to people in their 30s."

[0653] 5. Feedback from the server to the device

[0654] The generated strategic recommendations are sent from the server to the terminal, which displays them to the user as concrete action plans, allowing the user to reevaluate their business strategies based on them.

[0655] Prompt Sentence Examples

[0656] "I'm starting a new health food business and would like some advice on how to succeed in a crowded market. I need advice on using specific ingredients to differentiate my product and developing targeted marketing campaigns."

[0657] In this way, this system provides advanced analysis and recommendations of business ideas that take into account the user's emotional state, thereby supporting more accurate strategic decision-making than conventional methods.

[0658] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0659] Step 1:

[0660] The user enters the details.

[0661] Specifically, the user inputs information about their business idea (e.g., target market, product characteristics, competitor information, etc.) into the terminal. Once the input is complete, the emotion engine analyzes the user's emotional state in real time.

[0662] Input: Business idea details and the user's emotional state.

[0663] Output: Sentiment data parsed by the emotion engine.

[0664] Specific operation: When a user enters "I want to sell a new protein bar to people in their 30s," the device records this and simultaneously sends emotional data such as the user's anxieties and expectations to the emotion engine for analysis.

[0665] Step 2:

[0666] Send data from the terminal to the server.

[0667] The terminal transmits the business idea data entered by the user and the emotion data analyzed by the emotion engine to the server.

[0668] Input: Business idea details, sentiment data.

[0669] Output: Business idea data and emotion data received by the server.

[0670] Specific operation: The device compiles data such as "The target market is health-conscious people in their 30s" and "The user is feeling anxious" and sends it to the server.

[0671] Step 3:

[0672] The server receives and preprocesses the data.

[0673] The server preprocesses the received business idea data and sentiment data, normalizing and encoding them as necessary.

[0674] Input: Received business idea data, sentiment data.

[0675] Output: Preprocessed data.

[0676] Specific operation: The server converts the data into a format suitable for analysis, such as "target_market: 30s health-conscious consumers" or "users are anxious."

[0677] Step 4:

[0678] The server performs data integration and case extraction.

[0679] Based on the pre-processed data, the server extracts similar past failures and successes from a database, and searches the database, taking into account the sentiment data, to find the most relevant cases.

[0680] Input: Preprocessed business idea data, sentiment data.

[0681] Output: Extracted historical case data.

[0682] Specific operation: The server searches the database and extracts past cases related to "protein bars for health-conscious people in their 30s" and "anxiety."

[0683] Step 5:

[0684] The server performs case analysis and recommendation generation.

[0685] Based on the extracted cases, the server uses a generative AI model to analyze them, identify the causes of failure and the factors behind success, and generate recommendations that best fit the user's emotional state.

[0686] Input: extracted case data, generative AI model.

[0687] Output: The generated recommendations.

[0688] Specific operation: The generative AI model generates recommendations such as "You should conduct thorough market research" and "Emphasis on low-carb and narrow the target to people in their 30s."

[0689] Step 6:

[0690] The server sends the recommendations to the device.

[0691] The generated recommendations are sent from the server to the device, which displays this information to the user.

[0692] Input: The generated recommendations.

[0693] Output: The recommendations that are served to the user.

[0694] Specific operation: The server sends a recommendation to the device, such as "Low-sugar, high-protein protein bars are in high demand. Marketing should be strengthened, especially for health-conscious people in their 30s," and the device displays it to the user.

[0695] (Application example 2)

[0696] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0697] The present invention aims to solve the problem that, when users realize their business ideas, conventional systems provide general advice without considering the user's emotional state, making it difficult to generate accurate recommendations that correspond to the individual situation and emotional state of the user.In particular, the present invention aims to reduce the stress and anxiety felt by operators who operate and maintain robots in factories and other workplaces, thereby achieving safe and efficient operation.

[0698] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0699] In this invention, the server includes: a means for a user to input detailed information about a business idea; a means for receiving and preprocessing the input business idea data; a means for combining the preprocessed data with an emotion engine that analyzes the user's emotional state in real time; a means for extracting similar past failures and successes from a database along with the emotion engine data; a means for analyzing the extracted cases and identifying causes of failure and factors of success; a means for generating strategic recommendations that take the user's emotional state into account from the identified causes and factors; and a means for providing the generated recommendations to the user. This makes it possible to provide advanced recommendations tailored to the user's emotional state when implementing the business idea. Furthermore, in a factory, analyzing the stress levels experienced by operators when operating or maintaining robots and providing maintenance procedures and solutions tailored to those levels enables safe and efficient operation.

[0700] "User" refers to the entity that uses the system to input business ideas and detailed information on the operation and maintenance of the robot.

[0701] A "business idea" is detailed information about a specific business or project, including market analysis, product characteristics, and competitive information.

[0702] "Emotion engine" is a general term for software and hardware that analyzes a user's emotional state in real time.

[0703] The "database" is a data storage system that accumulates information on past failures and successes associated with business ideas and emotional data.

[0704] "Preprocessing" is the process of converting data received from a user into a form suitable for analysis, including text normalization and encoding.

[0705] "Similar past failures and successes" refers to past cases extracted from the database that are similar to the current business idea or on-site situation.

[0706] "Generated recommendations" are strategic advice and specific action plans provided by generative AI models based on the results of data and sentiment analysis.

[0707] "Strategic recommendations" refer to specific advice and suggestions tailored to the user's emotional state and situation to improve the chances of business success.

[0708] This invention relates to a system that analyzes a user's emotional state and generates accurate recommendations for business ideas and on-site operations. This system mainly consists of an emotion engine, a generative AI model, a database, and a user interface.

[0709] Hardware and Software Configuration

[0710] The hardware required includes a user terminal (tablet or PC) and a wearable device for emotion analysis (such as a smartwatch), while the software includes an emotion engine, a database management system, a generative AI model, and a user interface application.

[0711] Specific processing of the system

[0712] 1. Acquiring emotion data:

[0713] A user wears a wearable device (e.g., a smartwatch) for emotion analysis, and emotion-related data such as heart rate and skin galvanic response are acquired in real time. These data are then transmitted to the user's device.

[0714] 2. Enter your business idea:

[0715] The user uses the interface of the user terminal to input detailed information about the business idea, including the target market, product characteristics, and competitor information.

[0716] 3. Data preprocessing and integration:

[0717] The data sent from the user's device is received by the server and preprocessed. The text data is normalized and encoded to convert it into a format suitable for analysis. The data is then integrated with the emotion engine data and prepared for analysis.

[0718] 4. Extraction of similar cases:

[0719] Based on the preprocessed data and the emotion data, the server extracts similar failure and success cases from a database of past cases, which stores past cases and their associated emotion data.

[0720] 5. Generating recommendations:

[0721] For each case drawn from the database, the generative AI model identifies the causes of failure and the factors behind success. By incorporating emotional data, the system generates targeted recommendations based on the user's emotional state, such as adjusting marketing strategies to take into account stress and anxiety levels.

[0722] 6. User Feedback:

[0723] The generated recommendations are sent from the server to the user's device and presented to the user through a user interface. Based on this feedback, the user can reevaluate and adjust their business strategy and on-site operations.

[0724] Specific examples

[0725] For example, if a user inputs a business idea for a new health food product (e.g., a protein bar), the emotion engine will sense the user's concerns. This information is then combined with the competitive intensity of the market through a generative AI model to provide specific recommendations, such as using specific ingredients to differentiate the product and developing a targeted marketing campaign.

[0726] Prompt Sentence Examples

[0727] "An operator is performing maintenance on a robot under high stress. Based on past cases, what smooth maintenance procedures and solutions would you recommend?"

[0728] This allows the system to perform complex information analysis, including the user's emotional state, and provide more accurate strategic advice.In factories, the system supports a safe and efficient work environment by providing maintenance procedures and solutions that take into account the operator's stress level.

[0729] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0730] Step 1:

[0731] The user wears a wearable device (e.g., a smartwatch) for emotion analysis, and physiological data such as heart rate and skin galvanic response are collected in real time.

[0732] Input: User physiological data (heart rate, galvanic skin response, etc.)

[0733] Output: Physiological data is sent to the device

[0734] How it works: The wearable device sends the data it senses to the user's device via Bluetooth or Wi-Fi.

[0735] Step 2:

[0736] The user enters detailed information about the business idea using the terminal interface, including target market, product characteristics, and competitor information.

[0737] Input: Detailed information about your business idea (text data)

[0738] Output: Detailed information is logged to the terminal

[0739] Operation: Accepts input from the keyboard or touch screen through the user device's UI.

[0740] Step 3:

[0741] The server receives the business idea data and emotion data transmitted from the terminal.

[0742] Input: Business idea data, physiological data

[0743] Output: Received data is saved on the server

[0744] Operation: The device sends the business idea and emotion data to the server as an HTTP request.

[0745] Step 4:

[0746] The server pre-processes the received data, which includes normalizing and encoding the text data and analyzing sentiment data in real time.

[0747] Input: Business idea data, physiological data

[0748] Output: Preprocessed text data and analysis results

[0749] How it works: Data is processed on the server side using a text normalizer and sentiment engine (sentiment analysis software).

[0750] Step 5:

[0751] Based on the preprocessed data, the server extracts similar past failures and successes from the database.

[0752] Input: Preprocessed text data and sentiment analysis results

[0753] Output: Extracted similar cases

[0754] How it works: The server uses a database management system (DBMS) to run queries and extract similar past cases.

[0755] Step 6:

[0756] The generative AI model analyzes the extracted cases to identify causes of failure and factors of success, and then generates strategic recommendations that take into account the user's emotional state.

[0757] Input: Extracted similar cases, sentiment analysis results

[0758] Output: Generated recommendations

[0759] How it works: A generative AI model (e.g., a GPT-based model) analyzes data and generates specific advice that reflects the user's emotional state.

[0760] Step 7:

[0761] The server transmits the generated recommendations to the user terminal and presents them to the user through a user interface.

[0762] Input: Generated recommendations

[0763] Output: Recommendations served to the user

[0764] How it works: The server sends recommendations as an HTTP response, which the device's UI application displays.

[0765] Step 8:

[0766] Example prompt: "An operator is performing maintenance on a robot under high stress. Based on past experience, what smooth maintenance procedures and solutions would you recommend?"

[0767] In this way, the system can analyze complex information, including the user's emotional state, and provide more accurate strategic recommendations.

[0768] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0769] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0770] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0771] [Third embodiment]

[0772] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0773] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0774] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0775] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0776] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0777] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0778] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0779] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0780] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0781] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0782] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0783] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0784] This invention relates to a system that utilizes generative AI and a historical database to identify the causes of failure of business ideas and provide strategic recommendations for success.

[0785] User operations

[0786] A user enters detailed information about a business idea (e.g., target market, product characteristics, competitor information, etc.) into a terminal, possibly via a web form or a mobile application. Once the user has completed the input and pressed the submit button, this data is sent to a server.

[0787] Data reception and preprocessing on the server

[0788] The server receives the business idea data sent from the device, and then preprocesses it, removing special characters and encoding the text data to make it easier to analyze.

[0789] Extraction and analysis of similar cases

[0790] After the preprocessing is complete, the server extracts similar failures and successes from a database of past cases. At this stage, a generative AI model is used to automatically identify the causes of failures and factors behind successes from past cases. The AI ​​model uses specific algorithms to analyze patterns and trends in the data.

[0791] Generating strategic recommendations

[0792] Based on the extracted causes of failure and factors of success, the generative AI model generates specific strategic recommendations, which may include revising marketing strategies, changing product features, and implementing specific action plans to improve competitive advantage.

[0793] User Feedback

[0794] The generated recommendations are sent from the server to the device for the user to review. Feedback is presented as a concrete action plan through data visualization. Based on this information, users can adjust their business strategies and take concrete measures to increase their chances of success.

[0795] Specific examples

[0796] For example, if a user inputs a business idea for a new health food (e.g., a protein bar), previous failures may identify "unplanned entry into a highly competitive market" as the cause of failure. On the other hand, successes may identify "differentiation through the incorporation of unique ingredients" as the key to success. Based on this information, the generative AI model will provide recommendations such as "use specific ingredients and conduct a marketing campaign with a narrow target market."

[0797] In this way, the system of the present invention can provide specific and effective improvement measures for business ideas provided by users, thereby increasing the probability of business success.

[0798] The processing flow will be explained below.

[0799] Step 1:

[0800] The user enters detailed information about the business idea, including the target market, product characteristics, competitor information, etc. Once the information is complete, the user presses the submit button.

[0801] Step 2:

[0802] The terminal receives the data entered by the user and sends it to the server, where the data is encoded in a standard format such as JSON.

[0803] Step 3:

[0804] The server receives the data sent from the terminal, stores it temporarily, and passes it on to the next process.

[0805] Step 4:

[0806] The server pre-processes the received data by removing special characters and encoding the text data into a format suitable for analysis.

[0807] Step 5:

[0808] The server uses the preprocessed data to run queries to extract past failures and successes from a database of similar business ideas.

[0809] Step 6:

[0810] The server then passes the failure and success cases extracted from the database to a generative AI model for analysis, which analyzes the data for patterns and trends to identify the causes of failure and the factors behind success.

[0811] Step 7:

[0812] The server generates strategic recommendations based on the analysis results obtained from the generative AI model, which may include reviewing marketing strategies or changing product characteristics.

[0813] Step 8:

[0814] The server encodes the generated recommendations and sends them to the device in a standard format such as JSON.

[0815] Step 9:

[0816] The device decodes the recommendations received from the server and displays them in an easy-to-read format for the user, who can then review them and use them to adjust their business strategies.

[0817] Through this series of processes, the system can provide users with specific and effective strategic recommendations, increasing the probability of business success.

[0818] Example 1

[0819] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0820] Conventional business strategy formulation systems often rely on manual analysis of past case data, resulting in a lack of accuracy and efficiency. They also face the problem of difficulty in monitoring market changes and competitive situations in real time and updating strategies immediately. This makes it difficult for users to quickly and accurately evaluate business ideas and receive strategic recommendations.

[0821] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0822] In this invention, the server includes means for a user to input detailed information about a business idea, means for receiving and preprocessing the input business idea data, means for extracting similar past failures and successes from a database based on the preprocessed data, means for analyzing the extracted cases using a generative AI model and identifying causes of failure and factors of success, means for generating strategic recommendations from the identified causes and factors, and means for providing the generated recommendations to the user, thereby enabling the user to receive a quick and accurate evaluation of their business idea and receive specific strategic recommendations in real time.

[0823] "User" means a person or organization that provides information about a business idea and uses the system to receive ratings and recommendations.

[0824] A "business idea" is a specific plan or concept for business activities, such as a new product or service offering method or market development strategy.

[0825] A "terminal" is an electronic device, such as a personal computer or smartphone, that a user uses to input information about a business idea.

[0826] A "server" is a computer system or software that receives business idea data sent by users, analyzes it, and generates recommendations.

[0827] "Preprocessing" refers to processes such as data cleaning and encoding to convert received data into a format that is easier to analyze.

[0828] A "database" is an information management system that systematically stores related information, such as past failures and successes, and allows for searching and extraction.

[0829] A "generative AI model" is an algorithm or model used to analyze patterns and trends in data using artificial intelligence to generate specific recommendations.

[0830] "Recommendations" are advice and guidelines provided to users by the system with the aim of proposing strategies and specific action plans for business success.

[0831] "Preprocessed data" means data that has been received, cleaned, encoded, and converted into a form suitable for analysis.

[0832] "Real-time" refers to processing and feedback that immediately reflects the current state without delay.

[0833] This invention is a system that allows users to input detailed information about a business idea, analyzes past case data using a generative AI model based on that information, and provides specific strategic recommendations. Next, a specific embodiment of this system will be described.

[0834] User operations

[0835] A user inputs detailed information about their business idea (such as the target market, product characteristics, and competitor information) into a terminal. This is typically done using a web form or a mobile application. For example, if a user inputs a business idea for a "new protein bar," they might enter specific information such as "fitness enthusiasts" as the target market, "high protein, low sugar" as the product characteristics, and "a product from a well-known health food company" as the competitor information.

[0836] Data reception and preprocessing on the server

[0837] The server receives the business idea data sent from the device. After receiving the data, the server preprocesses it. This preprocessing includes removing special characters and insignificant spaces. The server also converts the data into a format that is easier to analyze. For example, it normalizes and encodes text data. Specifically, it is common to use Python libraries (such as pandas or numpy) to format the data.

[0838] Extraction and analysis of similar cases

[0839] After the preprocessing is complete, the server extracts similar business ideas from a past database. For example, it uses an SQL query to search for past failures and successes. The extracted case data is fed into a generative AI model, which then identifies the causes of failure and factors behind success. Generative AI models are built using deep learning frameworks such as TensorFlow and PyTorch, and may use supervised learning and reinforcement learning algorithms.

[0840] Generating strategic recommendations

[0841] The causes of failure and factors of success identified by the AI ​​model are used to generate specific strategic recommendations, such as using specific ingredients and conducting targeted marketing campaigns. The recommendations are then analyzed through algorithms developed using tools such as Jupyter Notebook and Google Colab.

[0842] User Feedback

[0843] The generated recommendations are sent from the server to the device, where the user can review them. Feedback is presented as a concrete action plan through data visualization, for example, using data visualization tools such as Grafana or Tableau, which can be easily understood by the user.

[0844] Specific examples

[0845] As a concrete example, let's consider the case where a user inputs a business idea for a new health food product (e.g., a protein bar). Based on past failures, the cause of failure was identified as "unplanned entry into a highly competitive market." On the other hand, based on successful cases, the key to success was identified as "differentiation through the incorporation of unique ingredients." Based on this information, the generative AI model provides recommendations such as "use specific ingredients and conduct a marketing campaign with a narrow target market."

[0846] Prompt Sentence Examples

[0847] Below are some examples of prompts for generative AI models:

[0848] "A user is considering launching a new protein bar into the market. They have entered their target market and product characteristics. Based on past similar cases, please analyze the possible causes of failure and factors for success and provide specific strategic recommendations."

[0849] In this way, users can adjust their business strategies based on the specific improvements provided and increase their chances of success.

[0850] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0851] Step 1: User Input and Data Submission

[0852] The user enters detailed information about their business idea into the device, including the target market, product characteristics, and competitor information. For example, when a user enters a business idea for a "new protein bar," they enter data such as the target market (fitness enthusiasts), product characteristics (high protein, low sugar), and competitor information (product from a health food company). Once this data is entered, the user presses the submit button, and the entered data is sent from the device to the server. Input is made into a text field, and after submission, the data is encoded in JSON format and sent to the server.

[0853] Input: Details of your business idea entered by the user

[0854] Output: JSON encoded data

[0855] Step 2: Data reception and preprocessing

[0856] The server receives business idea data sent from the device. The received data is logged and preprocessing begins. Preprocessing involves removing special characters, deleting meaningless spaces, and normalizing the data. For example, text data such as "high protein, low sugar" is converted to lowercase and encoded into a numeric vector or TF-IDF format. Python libraries (e.g., pandas, numpy) are used for preprocessing.

[0857] Input: Business idea data in JSON format

[0858] Output: Normalized and encoded data

[0859] Step 3: Extracting similar cases

[0860] After the preprocessing is complete, the server extracts similar failure and success cases from the past database. It uses an SQL query to search for past cases related to, for example, "protein bars." The extracted cases are used to classify the factors behind success and failure based on past training data.

[0861] Input: Normalized and encoded data

[0862] Output: Similar past failures and successes

[0863] Step 4: Analysis by generative AI model

[0864] The server analyzes the extracted cases using a generative AI model (e.g., a deep learning model) that analyzes patterns and trends based on past data to identify causes of failure and factors of success. The model is built using frameworks such as TensorFlow and PyTorch.

[0865] Input: Similar past failures and successes

[0866] Output: Identified causes of failure and factors of success

[0867] Step 5: Generate strategic recommendations

[0868] Based on the identified causes of failure and factors of success, the server uses a generative AI model to generate strategic recommendations, such as a specific action plan such as "use specific ingredients and conduct a marketing campaign targeting the target market." This process is typically carried out using tools such as Jupyter Notebook or Google Colab.

[0869] Input: Identified causes of failure and factors of success

[0870] Output: Specific strategic recommendations

[0871] Step 6: User feedback

[0872] The generated recommendations are sent from the server to the device, and the feedback is presented as a concrete action plan through data visualization, for example, using tools such as Grafana or Tableau, in a visually easy-to-understand format.

[0873] Input: Specific strategic recommendations

[0874] Output: Feedback via data visualization

[0875] Prompt Sentence Examples

[0876] Below are some examples of prompts for generative AI models:

[0877] "A user is considering launching a new protein bar into the market. They have entered their target market and product characteristics. Based on past similar cases, please analyze the possible causes of failure and factors for success and provide specific strategic recommendations."

[0878] (Application example 1)

[0879] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0880] Conventional business idea evaluation systems struggle to identify the causes of failure and factors for success from past cases, making it impossible to provide effective strategic recommendations. Furthermore, they are unable to reflect market changes and competitive situations in real time, making it impossible to provide users with practical feedback. Furthermore, the data entered by users comes in a variety of formats, and if proper preprocessing is not performed, the accuracy of analysis can decrease. This makes it difficult to increase the success rate of businesses.

[0881] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0882] In this invention, the server includes: a means for a user to input detailed information about a business idea; a means for receiving and preprocessing the input business idea data; a means for extracting similar past failures and successes from a database based on the preprocessed data; a means for analyzing the extracted cases and identifying causes of failure and factors of success; a means for generating strategic recommendations from the identified causes and factors; a means for providing the generated recommendations to the user; a means for using a generative AI model to generate recommendations and performing analysis based on prompt statements; and a means for updating and displaying the generated recommendations in real time. This allows the generative AI model to provide effective recommendations for business ideas based on past cases, enabling real-time feedback that reflects market changes and competitive conditions. Furthermore, by normalizing and encoding the format of the data entered by the user, the accuracy of analysis can be improved, making it possible to provide specific strategies for business success.

[0883] A "user" is someone who inputs detailed information about a business idea and receives evaluation results and recommendations.

[0884] A "business idea" is a concept or detailed information about a new product, service, or business model.

[0885] "Detailed information" refers to specific data related to the business idea, such as the target market, product characteristics, and competitor information.

[0886] A "database" is an information collection that stores data such as past failures and successes.

[0887] "Causes of failure" are the reasons or factors that led to businesses not being successful in past cases.

[0888] "Factors for success" are the reasons and factors that led to business success in past cases.

[0889] "Strategic recommendations" refer to specific strategies and action plans to increase the success rate of a business idea.

[0890] A "generative AI model" is an algorithm that uses artificial intelligence to analyze patterns and trends in data and generate recommendations.

[0891] A "prompt sentence" is text data input into a generative AI model, and is an instruction sentence that the model uses to analyze and generate.

[0892] "Real-time" is a time concept that means data processing and information updates are instantaneous.

[0893] "Normalization" is the process of standardizing data into a certain format.

[0894] "Encoding" is the process of converting data into a format that is easy to analyze.

[0895] The present invention is a system that utilizes a generative AI model to identify causes of failure and factors for success of business ideas from a past database and provides strategic recommendations. The system includes the following means.

[0896] User data entry

[0897] Users use a terminal to input detailed information about new product ideas and business strategies, including target markets, product characteristics, and competitor information.

[0898] Data transmission and preprocessing

[0899] The entered data is sent from the terminal to the server, which preprocesses the received data, removing special characters and encoding the text data.

[0900] Extraction and analysis of similar cases

[0901] Based on the pre-processed data, the server extracts similar past failures and successes from the database. A generative AI model is then used to analyze the extracted cases and identify the causes of failures and factors behind successes. Specific algorithms are used to analyze the data for patterns and trends.

[0902] Generating strategic recommendations

[0903] From the identified causes and factors, the generative AI model generates specific strategic recommendations, such as revising marketing strategies, changing product features, and providing specific action plans to improve competitive advantage.

[0904] Providing real-time recommendations

[0905] The generated recommendations are sent from the server to the device and provided to the user, where the generative AI model has the ability to update the recommendations in real time based on market changes and competitive conditions.

[0906] Hardware and software used

[0907] Cloud servers (e.g., Amazon AWS, Google Cloud Platform)

[0908] Local PC or mobile device

[0909] Software: Flask (Python Web Framework), OpenAI GPT-3 API (generative AI model)

[0910] Specific example explanation

[0911] For example, if a user is entering a business idea for a new eco-friendly detergent, the following information may be entered:

[0912] Idea: Eco-friendly detergent

[0913] Target market: Environmentally conscious young families

[0914] Product Features: Natural ingredients, reusable packaging

[0915] Competitive Intelligence: Leading Eco-Friendly Detergents on the Market Today

[0916] Based on this, the server processes the data and the generative AI model provides recommendations as follows:

[0917] The causes of failure were identified as "barriers to purchase due to high price range" and "lack of name recognition in the market," while the factors for success were identified as "better ingredients than competitors" and "implementation of a unique marketing campaign." As a result, specific action plans were proposed as strategic recommendations, including "adjusting the price range by taking cost-reduction measures to lower the barrier to purchase," "developing a marketing campaign using social media and influencers to increase name recognition," and "providing empirical data proving the effectiveness of the product to gain consumer trust."

[0918] Prompt Sentence Examples

[0919] New Product Idea: Eco-Friendly Detergent

[0920] Target market: Environmentally conscious young families

[0921] Product Features: Natural ingredients, reusable packaging

[0922] Competitive Intelligence: Leading Eco-Friendly Detergents on the Market Today

[0923] Identify causes of failure and factors of success and provide strategic recommendations.

[0924] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0925] Step 1: User Data Entry

[0926] Users input detailed information about new product ideas and business strategies into the device, including specific information about the target market, product characteristics, and competitor information. The input information is stored on the device as structured data and prepared for transmission to the server.

[0927] Input: Business idea, target market, product characteristics, competitor information

[0928] Output: Structured data ready to send

[0929] Step 2: Data transmission and preprocessing

[0930] The terminal sends the entered data to the server, which preprocesses the received data. Preprocessing includes removing special characters and encoding text data, converting the data into a format that can be analyzed.

[0931] Input: Structured data sent from the device

[0932] Output: Preprocessed, analyzable data

[0933] Step 3: Extracting similar cases

[0934] Based on the preprocessed data, the server extracts similar past failures and successes from the database and uses a generative AI model to select cases with high similarity.

[0935] Input: Preprocessed data, database of past cases

[0936] Output: Extracted similar past cases

[0937] Step 4: Case analysis

[0938] The server analyzes the extracted past cases to identify the causes of failure and the factors behind success. The generative AI model detects patterns and trends in the data and outputs the causes and factors as analysis results.

[0939] Input: Extracted similar cases

[0940] Output: Identified causes of failure and factors of success

[0941] Step 5: Generate strategic recommendations

[0942] The server uses generative AI models to generate strategic recommendations based on the identified causes of failure and factors of success, and prompts are used to create detailed recommendations.

[0943] Input: Identified causes of failure and factors of success

[0944] Output: Strategic recommendations

[0945] Step 6: Providing and updating recommendations

[0946] The generated recommendations are sent from the server to the device and provided to the user. The server monitors market changes and competitive conditions in real time and updates the recommendations using the generative AI model.

[0947] Inputs: Strategic recommendations, real-time market data

[0948] Output: Updated and served latest recommendations

[0949] Through the above processing steps, users can obtain specific strategies and feedback for new business ideas in real time.

[0950] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0951] The present invention relates to a system that combines an emotion engine that recognizes user emotions in order to perform more advanced analysis of business ideas. Specific embodiments for carrying out the present invention will be described in detail below.

[0952] User operations

[0953] Users input detailed information about their business idea (such as target market, product characteristics, competitor information, etc.) into the terminal. As they input information, the user's emotional state is also analyzed in real time by the emotion engine.

[0954] Data reception and preprocessing on the server

[0955] The server receives the business idea data sent from the device and the user's emotion data recognized by the emotion engine. The received data is preprocessed and converted into a format suitable for analysis. This conversion includes normalizing and encoding the text data.

[0956] Emotion data integration and similar case extraction

[0957] Based on the preprocessed data and emotional data, the server extracts similar failure and success cases from the database. In particular, it is possible to perform analysis taking emotional data into consideration. The database stores information on past cases associated with emotional data.

[0958] Generative AI model analysis and recommendation generation

[0959] For each case drawn from the database, the generative AI model identifies the causes of failure and the factors behind success. By incorporating emotional data, the model generates recommendations tailored to the user's emotional state, such as adjusting marketing strategies to take into account stress and anxiety levels.

[0960] User Feedback

[0961] The generated strategic recommendations are sent from the server to the device, which then displays them to the user. The information is presented as a concrete action plan that also reflects the user's emotional state. Based on this, the user can reevaluate their business strategy and make adjustments to increase the probability of success.

[0962] Specific examples

[0963] For example, when a user inputs a business idea for a new health food product (e.g., a protein bar), the emotion engine may sense the user's anxiety. This information is then linked to the cause of failure, such as intense market competition, by the generative AI model, and specific advice is provided, such as "use specific ingredients, differentiate the product, and develop a targeted marketing campaign." In this way, this system can provide more accurate strategic advice by analyzing complex information, including emotion data.

[0964] By introducing a new approach that takes into account the user's emotional state, the system of the present invention is able to provide more advanced analysis and recommendations than conventional business consulting methods.

[0965] The processing flow will be explained below.

[0966] Step 1:

[0967] Users input detailed information about their business idea, including target markets, product characteristics, competitor information, etc. As they input information, the emotion engine also captures the user's emotions in real time via the camera and microphone.

[0968] Step 2:

[0969] The device receives data entered by the user and emotion data recognized by the emotion engine, and temporarily stores the received data.

[0970] Step 3:

[0971] The device encodes the stored data into a format that can be parsed and sends it to the server in a standard format such as JSON.

[0972] Step 4:

[0973] The server receives the data sent from the terminal and stores the received data for preprocessing.

[0974] Step 5:

[0975] The server preprocesses the received data, removing special characters and converting text data into a format suitable for analysis by normalizing and encoding it. Emotion data is also formatted for analysis.

[0976] Step 6:

[0977] The server uses the preprocessed data to execute queries to extract past failures and successes from the database. Since past cases also contain similar emotional data, extraction based on emotional data is possible.

[0978] Step 7:

[0979] The server uses a generative AI model to analyze the failure and success cases extracted from the database. The AI ​​model analyzes data patterns and trends to identify causes of failure and factors for success. By incorporating emotional data into the analysis, it can provide accurate recommendations based on the user's emotional state.

[0980] Step 8:

[0981] Based on the analysis results of the generative AI model, the server generates strategic recommendations that take into account emotional data, including recommendations for reviewing marketing strategies, changing product characteristics, and specific action plans.

[0982] Step 9:

[0983] The server encodes the generated recommendations in a standard format such as JSON and sends them to the device.

[0984] Step 10:

[0985] The device decodes the recommendations received from the server and displays them to the user in an easy-to-read format, including a specific action plan tailored based on the user's emotional data.

[0986] Step 11:

[0987] Users can review the displayed recommendations and adjust or improve their business strategies. By taking into account advice based on emotion data, they can create more accurate business plans.

[0988] Through this series of processes, the system can provide users with specific and effective strategic recommendations, increasing the probability of business success. The incorporation of an emotion engine enables advanced business consulting that adapts to the user's psychological state.

[0989] Example 2

[0990] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0991] Conventional business idea analysis systems do not take into account the user's emotional state, making it difficult to provide optimal recommendations. Furthermore, they ignore the impact of the user's emotional state on the success or failure of a business, making them inadequate for strategic decision-making. Furthermore, there is no method for analyzing detailed business idea information and emotional data in an integrated manner, so more accurate analysis is needed.

[0992] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0993] In this invention, the server includes means for analyzing the user's emotional state in real time at the time of input, means for receiving and preprocessing the input business idea data and emotional data, means for extracting similar past failures and successes from a database based on the preprocessed data, means for analyzing the extracted cases and identifying the causes of failure and factors of success, means for generating strategic recommendations based on the identified causes and factors in accordance with the user's emotional state, and means for providing the generated recommendations to the user. This enables advanced analysis and recommendation of business ideas that take the user's emotions into consideration.

[0994] "User" refers to a person who enters details about a business idea into the system.

[0995] "Business Idea" means a plan or strategy for a particular product or service that a User devises and enters into the System.

[0996] "Detailed information" refers to specific data entered by the user regarding the business idea, including target markets, product characteristics, competitor information, and the like.

[0997] "Terminal" refers to the electronic device used by a user to input business ideas and receive recommendations.

[0998] "Emotional state" refers to the psychological state that is analyzed by the emotion engine when a user inputs a business idea.

[0999] An "emotion engine" refers to an algorithm or software that analyzes a user's emotional state from input text or voice information.

[1000] "Data" refers to information about business ideas and emotional states that is received, pre-processed and analyzed by the System.

[1001] "Preprocessing" refers to the process of normalizing and encoding input data into a format that is easy to analyze.

[1002] A "database" refers to a collection of information that stores past success stories and failure stories.

[1003] The "similar past failures and successes" are past cases related to the input business idea, and are extracted from the database.

[1004] A "generative AI model" refers to an artificial intelligence algorithm that identifies causes of failure and factors of success based on input data and emotional data, and generates recommendations.

[1005] "Recommendations" refers to strategic advice or suggestions provided based on the results of analysis by a generative AI model.

[1006] "Normalization" refers to the process of converting input data into a uniform format.

[1007] "Encoding" refers to the process of converting data into a format that is easier to analyze.

[1008] The present invention relates to an advanced business idea analysis system that takes into account the user's emotional state. Specifically, the system generates highly accurate recommendations using an emotion engine that analyzes the user's emotional state in real time when the user inputs a business idea. Specific embodiments of the present invention are described in detail below.

[1009] Hardware and software used

[1010] Hardware

[1011] Server: Use a dedicated server with a high-performance processor and sufficient memory to smoothly receive data, preprocess it, search the database, and run the generative AI model.

[1012] Terminal: A PC, tablet, or smartphone is used for user input. The terminal communicates with the emotion engine to obtain the user's emotion data.

[1013] software

[1014] Emotion engine: Software that analyzes the user's emotional state from input data, for example, using Azure's Emotion API.

[1015] Database: Use MySQL or another relational database system to manage historical case information.

[1016] Generative AI model: Uses OpenAI's GPT-4 and other models to generate recommendations based on business ideas and emotional data.

[1017] Specific operation example

[1018] 1. User operations

[1019] The user inputs detailed information about their business idea into the device. For example, the user might input, "I want to sell a new protein bar to people in their 30s." The device then uses an emotion engine to analyze the user's emotional state in real time. For example, the device may return a result such as, "The user is feeling anxious."

[1020] 2. Data reception and preprocessing by the server

[1021] The server receives the business idea data and sentiment data sent from the device. The server preprocesses the received data, normalizing and encoding it as necessary. For example, the server converts the input "The target market is health-conscious people in their 30s" into "target_market: 30s health-conscious consumers."

[1022] 3. Case extraction and analysis by the server

[1023] After the preprocessing is complete, the server extracts similar past failures and successes from the database. The server also takes into account emotional data to find the most relevant cases. For example, it searches for "protein bars for health-conscious people in their 30s" and "anxiety."

[1024] 4. Server-generated recommendations

[1025] The server analyzes the cases extracted from the database using a generative AI model. The generative AI model identifies the causes of failure and factors of success and generates recommendations that best fit the user's emotional state. For example, specific advice is provided, such as "conduct thorough market research" or "emphasize low-carb and limit the target to people in their 30s."

[1026] 5. Feedback from the server to the device

[1027] The generated strategic recommendations are sent from the server to the terminal, which displays them to the user as concrete action plans, allowing the user to reevaluate their business strategies based on them.

[1028] Prompt Sentence Examples

[1029] "I'm starting a new health food business and would like some advice on how to succeed in a crowded market. I need advice on using specific ingredients to differentiate my product and developing targeted marketing campaigns."

[1030] In this way, this system provides advanced analysis and recommendations of business ideas that take into account the user's emotional state, thereby supporting more accurate strategic decision-making than conventional methods.

[1031] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1032] Step 1:

[1033] The user enters the details.

[1034] Specifically, the user inputs information about their business idea (e.g., target market, product characteristics, competitor information, etc.) into the terminal. Once the input is complete, the emotion engine analyzes the user's emotional state in real time.

[1035] Input: Business idea details and the user's emotional state.

[1036] Output: Sentiment data parsed by the emotion engine.

[1037] Specific operation: When a user enters "I want to sell a new protein bar to people in their 30s," the device records this and simultaneously sends emotional data such as the user's anxieties and expectations to the emotion engine for analysis.

[1038] Step 2:

[1039] Send data from the terminal to the server.

[1040] The terminal transmits the business idea data entered by the user and the emotion data analyzed by the emotion engine to the server.

[1041] Input: Business idea details, sentiment data.

[1042] Output: Business idea data and emotion data received by the server.

[1043] Specific operation: The device compiles data such as "The target market is health-conscious people in their 30s" and "The user is feeling anxious" and sends it to the server.

[1044] Step 3:

[1045] The server receives and preprocesses the data.

[1046] The server preprocesses the received business idea data and sentiment data, normalizing and encoding them as necessary.

[1047] Input: Received business idea data, sentiment data.

[1048] Output: Preprocessed data.

[1049] Specific operation: The server converts the data into a format suitable for analysis, such as "target_market: 30s health-conscious consumers" or "users are anxious."

[1050] Step 4:

[1051] The server performs data integration and case extraction.

[1052] Based on the pre-processed data, the server extracts similar past failures and successes from a database, and searches the database, taking into account the sentiment data, to find the most relevant cases.

[1053] Input: Preprocessed business idea data, sentiment data.

[1054] Output: Extracted historical case data.

[1055] Specific operation: The server searches the database and extracts past cases related to "protein bars for health-conscious people in their 30s" and "anxiety."

[1056] Step 5:

[1057] The server performs case analysis and recommendation generation.

[1058] Based on the extracted cases, the server uses a generative AI model to analyze them, identify the causes of failure and the factors behind success, and generate recommendations that best fit the user's emotional state.

[1059] Input: extracted case data, generative AI model.

[1060] Output: The generated recommendations.

[1061] Specific operation: The generative AI model generates recommendations such as "You should conduct thorough market research" and "Emphasis on low-carb and narrow the target to people in their 30s."

[1062] Step 6:

[1063] The server sends the recommendations to the device.

[1064] The generated recommendations are sent from the server to the device, which displays this information to the user.

[1065] Input: The generated recommendations.

[1066] Output: The recommendations that are served to the user.

[1067] Specific operation: The server sends a recommendation to the device, such as "Low-sugar, high-protein protein bars are in high demand. Marketing should be strengthened, especially for health-conscious people in their 30s," and the device displays it to the user.

[1068] (Application example 2)

[1069] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1070] The present invention aims to solve the problem that, when users realize their business ideas, conventional systems provide general advice without considering the user's emotional state, making it difficult to generate accurate recommendations that correspond to the individual situation and emotional state of the user.In particular, the present invention aims to reduce the stress and anxiety felt by operators who operate and maintain robots in factories and other workplaces, thereby achieving safe and efficient operation.

[1071] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1072] In this invention, the server includes: a means for a user to input detailed information about a business idea; a means for receiving and preprocessing the input business idea data; a means for combining the preprocessed data with an emotion engine that analyzes the user's emotional state in real time; a means for extracting similar past failures and successes from a database along with the emotion engine data; a means for analyzing the extracted cases and identifying causes of failure and factors of success; a means for generating strategic recommendations that take the user's emotional state into account from the identified causes and factors; and a means for providing the generated recommendations to the user. This makes it possible to provide advanced recommendations tailored to the user's emotional state when implementing the business idea. Furthermore, in a factory, analyzing the stress levels experienced by operators when operating or maintaining robots and providing maintenance procedures and solutions tailored to those levels enables safe and efficient operation.

[1073] "User" refers to the entity that uses the system to input business ideas and detailed information on the operation and maintenance of the robot.

[1074] A "business idea" is detailed information about a specific business or project, including market analysis, product characteristics, and competitive information.

[1075] "Emotion engine" is a general term for software and hardware that analyzes a user's emotional state in real time.

[1076] The "database" is a data storage system that accumulates information on past failures and successes associated with business ideas and emotional data.

[1077] "Preprocessing" is the process of converting data received from a user into a form suitable for analysis, including text normalization and encoding.

[1078] "Similar past failures and successes" refers to past cases extracted from the database that are similar to the current business idea or on-site situation.

[1079] "Generated recommendations" are strategic advice and specific action plans provided by generative AI models based on the results of data and sentiment analysis.

[1080] "Strategic recommendations" refer to specific advice and suggestions tailored to the user's emotional state and situation to improve the chances of business success.

[1081] This invention relates to a system that analyzes a user's emotional state and generates accurate recommendations for business ideas and on-site operations. This system mainly consists of an emotion engine, a generative AI model, a database, and a user interface.

[1082] Hardware and Software Configuration

[1083] The hardware required includes a user terminal (tablet or PC) and a wearable device for emotion analysis (such as a smartwatch), while the software includes an emotion engine, a database management system, a generative AI model, and a user interface application.

[1084] Specific processing of the system

[1085] 1. Acquiring emotion data:

[1086] A user wears a wearable device (e.g., a smartwatch) for emotion analysis, and emotion-related data such as heart rate and skin galvanic response are acquired in real time. These data are then transmitted to the user's device.

[1087] 2. Enter your business idea:

[1088] The user uses the interface of the user terminal to input detailed information about the business idea, including the target market, product characteristics, and competitor information.

[1089] 3. Data preprocessing and integration:

[1090] The data sent from the user's device is received by the server and preprocessed. The text data is normalized and encoded to convert it into a format suitable for analysis. The data is then integrated with the emotion engine data and prepared for analysis.

[1091] 4. Extraction of similar cases:

[1092] Based on the preprocessed data and the emotion data, the server extracts similar failure and success cases from a database of past cases, which stores past cases and their associated emotion data.

[1093] 5. Generating recommendations:

[1094] For each case drawn from the database, the generative AI model identifies the causes of failure and the factors behind success. By incorporating emotional data, the system generates targeted recommendations based on the user's emotional state, such as adjusting marketing strategies to take into account stress and anxiety levels.

[1095] 6. User Feedback:

[1096] The generated recommendations are sent from the server to the user's device and presented to the user through a user interface. Based on this feedback, the user can reevaluate and adjust their business strategy and on-site operations.

[1097] Specific examples

[1098] For example, if a user inputs a business idea for a new health food product (e.g., a protein bar), the emotion engine will sense the user's concerns. This information is then combined with the competitive intensity of the market through a generative AI model to provide specific recommendations, such as using specific ingredients to differentiate the product and developing a targeted marketing campaign.

[1099] Prompt Sentence Examples

[1100] "An operator is performing maintenance on a robot under high stress. Based on past cases, what smooth maintenance procedures and solutions would you recommend?"

[1101] This allows the system to perform complex information analysis, including the user's emotional state, and provide more accurate strategic advice.In factories, the system supports a safe and efficient work environment by providing maintenance procedures and solutions that take into account the operator's stress level.

[1102] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1103] Step 1:

[1104] The user wears a wearable device (e.g., a smartwatch) for emotion analysis, and physiological data such as heart rate and skin galvanic response are collected in real time.

[1105] Input: User physiological data (heart rate, galvanic skin response, etc.)

[1106] Output: Physiological data is sent to the device

[1107] How it works: The wearable device sends the data it senses to the user's device via Bluetooth or Wi-Fi.

[1108] Step 2:

[1109] The user enters detailed information about the business idea using the terminal interface, including target market, product characteristics, and competitor information.

[1110] Input: Detailed information about your business idea (text data)

[1111] Output: Detailed information is logged to the terminal

[1112] Operation: Accepts input from the keyboard or touch screen through the user device's UI.

[1113] Step 3:

[1114] The server receives the business idea data and emotion data transmitted from the terminal.

[1115] Input: Business idea data, physiological data

[1116] Output: Received data is saved on the server

[1117] Operation: The device sends the business idea and emotion data to the server as an HTTP request.

[1118] Step 4:

[1119] The server pre-processes the received data, which includes normalizing and encoding the text data and analyzing sentiment data in real time.

[1120] Input: Business idea data, physiological data

[1121] Output: Preprocessed text data and analysis results

[1122] How it works: Data is processed on the server side using a text normalizer and sentiment engine (sentiment analysis software).

[1123] Step 5:

[1124] Based on the preprocessed data, the server extracts similar past failures and successes from the database.

[1125] Input: Preprocessed text data and sentiment analysis results

[1126] Output: Extracted similar cases

[1127] How it works: The server uses a database management system (DBMS) to run queries and extract similar past cases.

[1128] Step 6:

[1129] The generative AI model analyzes the extracted cases to identify causes of failure and factors of success, and then generates strategic recommendations that take into account the user's emotional state.

[1130] Input: Extracted similar cases, sentiment analysis results

[1131] Output: Generated recommendations

[1132] How it works: A generative AI model (e.g., a GPT-based model) analyzes data and generates specific advice that reflects the user's emotional state.

[1133] Step 7:

[1134] The server transmits the generated recommendations to the user terminal and presents them to the user through a user interface.

[1135] Input: Generated recommendations

[1136] Output: Recommendations served to the user

[1137] How it works: The server sends recommendations as an HTTP response, which the device's UI application displays.

[1138] Step 8:

[1139] Example prompt: "An operator is performing maintenance on a robot under high stress. Based on past experience, what smooth maintenance procedures and solutions would you recommend?"

[1140] In this way, the system can analyze complex information, including the user's emotional state, and provide more accurate strategic recommendations.

[1141] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1142] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1143] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1144] [Fourth embodiment]

[1145] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1146] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1147] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1148] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1149] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1151] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1152] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1153] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1154] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1155] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1156] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1157] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1158] This invention relates to a system that utilizes generative AI and a historical database to identify the causes of failure of business ideas and provide strategic recommendations for success.

[1159] User operations

[1160] A user enters detailed information about a business idea (e.g., target market, product characteristics, competitor information, etc.) into a terminal, possibly via a web form or a mobile application. Once the user has completed the input and pressed the submit button, this data is sent to a server.

[1161] Data reception and preprocessing on the server

[1162] The server receives the business idea data sent from the device, and then preprocesses it, removing special characters and encoding the text data to make it easier to analyze.

[1163] Extraction and analysis of similar cases

[1164] After the preprocessing is complete, the server extracts similar failures and successes from a database of past cases. At this stage, a generative AI model is used to automatically identify the causes of failures and factors behind successes from past cases. The AI ​​model uses specific algorithms to analyze patterns and trends in the data.

[1165] Generating strategic recommendations

[1166] Based on the extracted causes of failure and factors of success, the generative AI model generates specific strategic recommendations, which may include revising marketing strategies, changing product features, and implementing specific action plans to improve competitive advantage.

[1167] User Feedback

[1168] The generated recommendations are sent from the server to the device for the user to review. Feedback is presented as a concrete action plan through data visualization. Based on this information, users can adjust their business strategies and take concrete measures to increase their chances of success.

[1169] Specific examples

[1170] For example, if a user inputs a business idea for a new health food (e.g., a protein bar), previous failures may identify "unplanned entry into a highly competitive market" as the cause of failure. On the other hand, successes may identify "differentiation through the incorporation of unique ingredients" as the key to success. Based on this information, the generative AI model will provide recommendations such as "use specific ingredients and conduct a marketing campaign with a narrow target market."

[1171] In this way, the system of the present invention can provide specific and effective improvement measures for business ideas provided by users, thereby increasing the probability of business success.

[1172] The processing flow will be explained below.

[1173] Step 1:

[1174] The user enters detailed information about the business idea, including the target market, product characteristics, competitor information, etc. Once the information is complete, the user presses the submit button.

[1175] Step 2:

[1176] The terminal receives the data entered by the user and sends it to the server, where the data is encoded in a standard format such as JSON.

[1177] Step 3:

[1178] The server receives the data sent from the terminal, stores it temporarily, and passes it on to the next process.

[1179] Step 4:

[1180] The server pre-processes the received data by removing special characters and encoding the text data into a format suitable for analysis.

[1181] Step 5:

[1182] The server uses the preprocessed data to run queries to extract past failures and successes from a database of similar business ideas.

[1183] Step 6:

[1184] The server then passes the failure and success cases extracted from the database to a generative AI model for analysis, which analyzes the data for patterns and trends to identify the causes of failure and the factors behind success.

[1185] Step 7:

[1186] The server generates strategic recommendations based on the analysis results obtained from the generative AI model, which may include reviewing marketing strategies or changing product characteristics.

[1187] Step 8:

[1188] The server encodes the generated recommendations and sends them to the device in a standard format such as JSON.

[1189] Step 9:

[1190] The device decodes the recommendations received from the server and displays them in an easy-to-read format for the user, who can then review them and use them to adjust their business strategies.

[1191] Through this series of processes, the system can provide users with specific and effective strategic recommendations, increasing the probability of business success.

[1192] Example 1

[1193] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1194] Conventional business strategy formulation systems often rely on manual analysis of past case data, resulting in a lack of accuracy and efficiency. They also face the problem of difficulty in monitoring market changes and competitive situations in real time and updating strategies immediately. This makes it difficult for users to quickly and accurately evaluate business ideas and receive strategic recommendations.

[1195] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1196] In this invention, the server includes means for a user to input detailed information about a business idea, means for receiving and preprocessing the input business idea data, means for extracting similar past failures and successes from a database based on the preprocessed data, means for analyzing the extracted cases using a generative AI model and identifying causes of failure and factors of success, means for generating strategic recommendations from the identified causes and factors, and means for providing the generated recommendations to the user, thereby enabling the user to receive a quick and accurate evaluation of their business idea and receive specific strategic recommendations in real time.

[1197] "User" means a person or organization that provides information about a business idea and uses the system to receive ratings and recommendations.

[1198] A "business idea" is a specific plan or concept for business activities, such as a new product or service offering method or market development strategy.

[1199] A "terminal" is an electronic device, such as a personal computer or smartphone, that a user uses to input information about a business idea.

[1200] A "server" is a computer system or software that receives business idea data sent by users, analyzes it, and generates recommendations.

[1201] "Preprocessing" refers to processes such as data cleaning and encoding to convert received data into a format that is easier to analyze.

[1202] A "database" is an information management system that systematically stores related information, such as past failures and successes, and allows for searching and extraction.

[1203] A "generative AI model" is an algorithm or model used to analyze patterns and trends in data using artificial intelligence to generate specific recommendations.

[1204] "Recommendations" are advice and guidelines provided to users by the system with the aim of proposing strategies and specific action plans for business success.

[1205] "Preprocessed data" means data that has been received, cleaned, encoded, and converted into a form suitable for analysis.

[1206] "Real-time" refers to processing and feedback that immediately reflects the current state without delay.

[1207] This invention is a system that allows users to input detailed information about a business idea, analyzes past case data using a generative AI model based on that information, and provides specific strategic recommendations. Next, a specific embodiment of this system will be described.

[1208] User operations

[1209] A user inputs detailed information about their business idea (such as the target market, product characteristics, and competitor information) into a terminal. This is typically done using a web form or a mobile application. For example, if a user inputs a business idea for a "new protein bar," they might enter specific information such as "fitness enthusiasts" as the target market, "high protein, low sugar" as the product characteristics, and "a product from a well-known health food company" as the competitor information.

[1210] Data reception and preprocessing on the server

[1211] The server receives the business idea data sent from the device. After receiving the data, the server preprocesses it. This preprocessing includes removing special characters and insignificant spaces. The server also converts the data into a format that is easier to analyze. For example, it normalizes and encodes text data. Specifically, it is common to use Python libraries (such as pandas or numpy) to format the data.

[1212] Extraction and analysis of similar cases

[1213] After the preprocessing is complete, the server extracts similar business ideas from a past database. For example, it uses an SQL query to search for past failures and successes. The extracted case data is fed into a generative AI model, which then identifies the causes of failure and factors behind success. Generative AI models are built using deep learning frameworks such as TensorFlow and PyTorch, and may use supervised learning and reinforcement learning algorithms.

[1214] Generating strategic recommendations

[1215] The causes of failure and factors of success identified by the AI ​​model are used to generate specific strategic recommendations, such as using specific ingredients and conducting targeted marketing campaigns. The recommendations are then analyzed through algorithms developed using tools such as Jupyter Notebook and Google Colab.

[1216] User Feedback

[1217] The generated recommendations are sent from the server to the device, where the user can review them. Feedback is presented as a concrete action plan through data visualization, for example, using data visualization tools such as Grafana or Tableau, which can be easily understood by the user.

[1218] Specific examples

[1219] As a concrete example, let's consider the case where a user inputs a business idea for a new health food product (e.g., a protein bar). Based on past failures, the cause of failure was identified as "unplanned entry into a highly competitive market." On the other hand, based on successful cases, the key to success was identified as "differentiation through the incorporation of unique ingredients." Based on this information, the generative AI model provides recommendations such as "use specific ingredients and conduct a marketing campaign with a narrow target market."

[1220] Prompt Sentence Examples

[1221] Below are some examples of prompts for generative AI models:

[1222] "A user is considering launching a new protein bar into the market. They have entered their target market and product characteristics. Based on past similar cases, please analyze the possible causes of failure and factors for success and provide specific strategic recommendations."

[1223] In this way, users can adjust their business strategies based on the specific improvements provided and increase their chances of success.

[1224] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1225] Step 1: User Input and Data Submission

[1226] The user enters detailed information about their business idea into the device, including the target market, product characteristics, and competitor information. For example, when a user enters a business idea for a "new protein bar," they enter data such as the target market (fitness enthusiasts), product characteristics (high protein, low sugar), and competitor information (product from a health food company). Once this data is entered, the user presses the submit button, and the entered data is sent from the device to the server. Input is made into a text field, and after submission, the data is encoded in JSON format and sent to the server.

[1227] Input: Details of your business idea entered by the user

[1228] Output: JSON encoded data

[1229] Step 2: Data reception and preprocessing

[1230] The server receives business idea data sent from the device. The received data is logged and preprocessing begins. Preprocessing involves removing special characters, deleting meaningless spaces, and normalizing the data. For example, text data such as "high protein, low sugar" is converted to lowercase and encoded into a numeric vector or TF-IDF format. Python libraries (e.g., pandas, numpy) are used for preprocessing.

[1231] Input: Business idea data in JSON format

[1232] Output: Normalized and encoded data

[1233] Step 3: Extracting similar cases

[1234] After the preprocessing is complete, the server extracts similar failure and success cases from the past database. It uses an SQL query to search for past cases related to, for example, "protein bars." The extracted cases are used to classify the factors behind success and failure based on past training data.

[1235] Input: Normalized and encoded data

[1236] Output: Similar past failures and successes

[1237] Step 4: Analysis by generative AI model

[1238] The server analyzes the extracted cases using a generative AI model (e.g., a deep learning model) that analyzes patterns and trends based on past data to identify causes of failure and factors of success. The model is built using frameworks such as TensorFlow and PyTorch.

[1239] Input: Similar past failures and successes

[1240] Output: Identified causes of failure and factors of success

[1241] Step 5: Generate strategic recommendations

[1242] Based on the identified causes of failure and factors of success, the server uses a generative AI model to generate strategic recommendations, such as a specific action plan such as "use specific ingredients and conduct a marketing campaign targeting the target market." This process is typically carried out using tools such as Jupyter Notebook or Google Colab.

[1243] Input: Identified causes of failure and factors of success

[1244] Output: Specific strategic recommendations

[1245] Step 6: User feedback

[1246] The generated recommendations are sent from the server to the device, and the feedback is presented as a concrete action plan through data visualization, for example, using tools such as Grafana or Tableau, in a visually easy-to-understand format.

[1247] Input: Specific strategic recommendations

[1248] Output: Feedback via data visualization

[1249] Prompt Sentence Examples

[1250] Below are some examples of prompts for generative AI models:

[1251] "A user is considering launching a new protein bar into the market. They have entered their target market and product characteristics. Based on past similar cases, please analyze the possible causes of failure and factors for success and provide specific strategic recommendations."

[1252] (Application example 1)

[1253] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1254] Conventional business idea evaluation systems struggle to identify the causes of failure and factors for success from past cases, making it impossible to provide effective strategic recommendations. Furthermore, they are unable to reflect market changes and competitive situations in real time, making it impossible to provide users with practical feedback. Furthermore, the data entered by users comes in a variety of formats, and if proper preprocessing is not performed, the accuracy of analysis can decrease. This makes it difficult to increase the success rate of businesses.

[1255] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1256] In this invention, the server includes: a means for a user to input detailed information about a business idea; a means for receiving and preprocessing the input business idea data; a means for extracting similar past failures and successes from a database based on the preprocessed data; a means for analyzing the extracted cases and identifying causes of failure and factors of success; a means for generating strategic recommendations from the identified causes and factors; a means for providing the generated recommendations to the user; a means for using a generative AI model to generate recommendations and performing analysis based on prompt statements; and a means for updating and displaying the generated recommendations in real time. This allows the generative AI model to provide effective recommendations for business ideas based on past cases, enabling real-time feedback that reflects market changes and competitive conditions. Furthermore, by normalizing and encoding the format of the data entered by the user, the accuracy of analysis can be improved, making it possible to provide specific strategies for business success.

[1257] A "user" is someone who inputs detailed information about a business idea and receives evaluation results and recommendations.

[1258] A "business idea" is a concept or detailed information about a new product, service, or business model.

[1259] "Detailed information" refers to specific data related to the business idea, such as the target market, product characteristics, and competitor information.

[1260] A "database" is an information collection that stores data such as past failures and successes.

[1261] "Causes of failure" are the reasons or factors that led to businesses not being successful in past cases.

[1262] "Factors for success" are the reasons and factors that led to business success in past cases.

[1263] "Strategic recommendations" refer to specific strategies and action plans to increase the success rate of a business idea.

[1264] A "generative AI model" is an algorithm that uses artificial intelligence to analyze patterns and trends in data and generate recommendations.

[1265] A "prompt sentence" is text data input into a generative AI model, and is an instruction sentence that the model uses to analyze and generate.

[1266] "Real-time" is a time concept that means data processing and information updates are instantaneous.

[1267] "Normalization" is the process of standardizing data into a certain format.

[1268] "Encoding" is the process of converting data into a format that is easy to analyze.

[1269] The present invention is a system that utilizes a generative AI model to identify causes of failure and factors for success of business ideas from a past database and provides strategic recommendations. The system includes the following means.

[1270] User data entry

[1271] Users use a terminal to input detailed information about new product ideas and business strategies, including target markets, product characteristics, and competitor information.

[1272] Data transmission and preprocessing

[1273] The entered data is sent from the terminal to the server, which preprocesses the received data, removing special characters and encoding the text data.

[1274] Extraction and analysis of similar cases

[1275] Based on the pre-processed data, the server extracts similar past failures and successes from the database. A generative AI model is then used to analyze the extracted cases and identify the causes of failures and factors behind successes. Specific algorithms are used to analyze the data for patterns and trends.

[1276] Generating strategic recommendations

[1277] From the identified causes and factors, the generative AI model generates specific strategic recommendations, such as revising marketing strategies, changing product features, and providing specific action plans to improve competitive advantage.

[1278] Providing real-time recommendations

[1279] The generated recommendations are sent from the server to the device and provided to the user, where the generative AI model has the ability to update the recommendations in real time based on market changes and competitive conditions.

[1280] Hardware and software used

[1281] Cloud servers (e.g., Amazon AWS, Google Cloud Platform)

[1282] Local PC or mobile device

[1283] Software: Flask (Python Web Framework), OpenAI GPT-3 API (generative AI model)

[1284] Specific example explanation

[1285] For example, if a user is entering a business idea for a new eco-friendly detergent, the following information may be entered:

[1286] Idea: Eco-friendly detergent

[1287] Target market: Environmentally conscious young families

[1288] Product Features: Natural ingredients, reusable packaging

[1289] Competitive Intelligence: Leading Eco-Friendly Detergents on the Market Today

[1290] Based on this, the server processes the data and the generative AI model provides recommendations as follows:

[1291] The causes of failure were identified as "barriers to purchase due to high price range" and "lack of name recognition in the market," while the factors for success were identified as "better ingredients than competitors" and "implementation of a unique marketing campaign." As a result, specific action plans were proposed as strategic recommendations, including "adjusting the price range by taking cost-reduction measures to lower the barrier to purchase," "developing a marketing campaign using social media and influencers to increase name recognition," and "providing empirical data proving the effectiveness of the product to gain consumer trust."

[1292] Prompt Sentence Examples

[1293] New Product Idea: Eco-Friendly Detergent

[1294] Target market: Environmentally conscious young families

[1295] Product Features: Natural ingredients, reusable packaging

[1296] Competitive Intelligence: Leading Eco-Friendly Detergents on the Market Today

[1297] Identify causes of failure and factors of success and provide strategic recommendations.

[1298] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1299] Step 1: User Data Entry

[1300] Users input detailed information about new product ideas and business strategies into the device, including specific information about the target market, product characteristics, and competitor information. The input information is stored on the device as structured data and prepared for transmission to the server.

[1301] Input: Business idea, target market, product characteristics, competitor information

[1302] Output: Structured data ready to send

[1303] Step 2: Data transmission and preprocessing

[1304] The terminal sends the entered data to the server, which preprocesses the received data. Preprocessing includes removing special characters and encoding text data, converting the data into a format that can be analyzed.

[1305] Input: Structured data sent from the device

[1306] Output: Preprocessed, analyzable data

[1307] Step 3: Extracting similar cases

[1308] Based on the preprocessed data, the server extracts similar past failures and successes from the database and uses a generative AI model to select cases with high similarity.

[1309] Input: Preprocessed data, database of past cases

[1310] Output: Extracted similar past cases

[1311] Step 4: Case analysis

[1312] The server analyzes the extracted past cases to identify the causes of failure and the factors behind success. The generative AI model detects patterns and trends in the data and outputs the causes and factors as analysis results.

[1313] Input: Extracted similar cases

[1314] Output: Identified causes of failure and factors of success

[1315] Step 5: Generate strategic recommendations

[1316] The server uses generative AI models to generate strategic recommendations based on the identified causes of failure and factors of success, and prompts are used to create detailed recommendations.

[1317] Input: Identified causes of failure and factors of success

[1318] Output: Strategic recommendations

[1319] Step 6: Providing and updating recommendations

[1320] The generated recommendations are sent from the server to the device and provided to the user. The server monitors market changes and competitive conditions in real time and updates the recommendations using the generative AI model.

[1321] Inputs: Strategic recommendations, real-time market data

[1322] Output: Updated and served latest recommendations

[1323] Through the above processing steps, users can obtain specific strategies and feedback for new business ideas in real time.

[1324] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1325] The present invention relates to a system that combines an emotion engine that recognizes user emotions in order to perform more advanced analysis of business ideas. Specific embodiments for carrying out the present invention will be described in detail below.

[1326] User operations

[1327] Users input detailed information about their business idea (such as target market, product characteristics, competitor information, etc.) into the terminal. As they input information, the user's emotional state is also analyzed in real time by the emotion engine.

[1328] Data reception and preprocessing on the server

[1329] The server receives the business idea data sent from the device and the user's emotion data recognized by the emotion engine. The received data is preprocessed and converted into a format suitable for analysis. This conversion includes normalizing and encoding the text data.

[1330] Emotion data integration and similar case extraction

[1331] Based on the preprocessed data and emotional data, the server extracts similar failure and success cases from the database. In particular, it is possible to perform analysis taking emotional data into consideration. The database stores information on past cases associated with emotional data.

[1332] Generative AI model analysis and recommendation generation

[1333] For each case drawn from the database, the generative AI model identifies the causes of failure and the factors behind success. By incorporating emotional data, the model generates recommendations tailored to the user's emotional state, such as adjusting marketing strategies to take into account stress and anxiety levels.

[1334] User Feedback

[1335] The generated strategic recommendations are sent from the server to the device, which then displays them to the user. The information is presented as a concrete action plan that also reflects the user's emotional state. Based on this, the user can reevaluate their business strategy and make adjustments to increase the probability of success.

[1336] Specific examples

[1337] For example, when a user inputs a business idea for a new health food product (e.g., a protein bar), the emotion engine may sense the user's anxiety. This information is then linked to the cause of failure, such as intense market competition, by the generative AI model, and specific advice is provided, such as "use specific ingredients, differentiate the product, and develop a targeted marketing campaign." In this way, this system can provide more accurate strategic advice by analyzing complex information, including emotion data.

[1338] By introducing a new approach that takes into account the user's emotional state, the system of the present invention is able to provide more advanced analysis and recommendations than conventional business consulting methods.

[1339] The processing flow will be explained below.

[1340] Step 1:

[1341] Users input detailed information about their business idea, including target markets, product characteristics, competitor information, etc. As they input information, the emotion engine also captures the user's emotions in real time via the camera and microphone.

[1342] Step 2:

[1343] The device receives data entered by the user and emotion data recognized by the emotion engine, and temporarily stores the received data.

[1344] Step 3:

[1345] The device encodes the stored data into a format that can be parsed and sends it to the server in a standard format such as JSON.

[1346] Step 4:

[1347] The server receives the data sent from the terminal and stores the received data for preprocessing.

[1348] Step 5:

[1349] The server preprocesses the received data, removing special characters and converting text data into a format suitable for analysis by normalizing and encoding it. Emotion data is also formatted for analysis.

[1350] Step 6:

[1351] The server uses the preprocessed data to execute queries to extract past failures and successes from the database. Since past cases also contain similar emotional data, extraction based on emotional data is possible.

[1352] Step 7:

[1353] The server uses a generative AI model to analyze the failure and success cases extracted from the database. The AI ​​model analyzes data patterns and trends to identify causes of failure and factors for success. By incorporating emotional data into the analysis, it can provide accurate recommendations based on the user's emotional state.

[1354] Step 8:

[1355] Based on the analysis results of the generative AI model, the server generates strategic recommendations that take into account emotional data, including recommendations for reviewing marketing strategies, changing product characteristics, and specific action plans.

[1356] Step 9:

[1357] The server encodes the generated recommendations in a standard format such as JSON and sends them to the device.

[1358] Step 10:

[1359] The device decodes the recommendations received from the server and displays them to the user in an easy-to-read format, including a specific action plan tailored based on the user's emotional data.

[1360] Step 11:

[1361] Users can review the displayed recommendations and adjust or improve their business strategies. By taking into account advice based on emotion data, they can create more accurate business plans.

[1362] Through this series of processes, the system can provide users with specific and effective strategic recommendations, increasing the probability of business success. The incorporation of an emotion engine enables advanced business consulting that adapts to the user's psychological state.

[1363] Example 2

[1364] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1365] Conventional business idea analysis systems do not take into account the user's emotional state, making it difficult to provide optimal recommendations. Furthermore, they ignore the impact of the user's emotional state on the success or failure of a business, making them inadequate for strategic decision-making. Furthermore, there is no method for analyzing detailed business idea information and emotional data in an integrated manner, so more accurate analysis is needed.

[1366] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1367] In this invention, the server includes means for analyzing the user's emotional state in real time at the time of input, means for receiving and preprocessing the input business idea data and emotional data, means for extracting similar past failures and successes from a database based on the preprocessed data, means for analyzing the extracted cases and identifying the causes of failure and factors of success, means for generating strategic recommendations based on the identified causes and factors in accordance with the user's emotional state, and means for providing the generated recommendations to the user. This enables advanced analysis and recommendation of business ideas that take the user's emotions into consideration.

[1368] "User" refers to a person who enters details about a business idea into the system.

[1369] "Business Idea" means a plan or strategy for a particular product or service that a User devises and enters into the System.

[1370] "Detailed information" refers to specific data entered by the user regarding the business idea, including target markets, product characteristics, competitor information, and the like.

[1371] "Terminal" refers to the electronic device used by a user to input business ideas and receive recommendations.

[1372] "Emotional state" refers to the psychological state that is analyzed by the emotion engine when a user inputs a business idea.

[1373] An "emotion engine" refers to an algorithm or software that analyzes a user's emotional state from input text or voice information.

[1374] "Data" refers to information about business ideas and emotional states that is received, pre-processed and analyzed by the System.

[1375] "Preprocessing" refers to the process of normalizing and encoding input data into a format that is easy to analyze.

[1376] A "database" refers to a collection of information that stores past success stories and failure stories.

[1377] The "similar past failures and successes" are past cases related to the input business idea, and are extracted from the database.

[1378] A "generative AI model" refers to an artificial intelligence algorithm that identifies causes of failure and factors of success based on input data and emotional data, and generates recommendations.

[1379] "Recommendations" refers to strategic advice or suggestions provided based on the results of analysis by a generative AI model.

[1380] "Normalization" refers to the process of converting input data into a uniform format.

[1381] "Encoding" refers to the process of converting data into a format that is easier to analyze.

[1382] The present invention relates to an advanced business idea analysis system that takes into account the user's emotional state. Specifically, the system generates highly accurate recommendations using an emotion engine that analyzes the user's emotional state in real time when the user inputs a business idea. Specific embodiments of the present invention are described in detail below.

[1383] Hardware and software used

[1384] Hardware

[1385] Server: Use a dedicated server with a high-performance processor and sufficient memory to smoothly receive data, preprocess it, search the database, and run the generative AI model.

[1386] Terminal: A PC, tablet, or smartphone is used for user input. The terminal communicates with the emotion engine to obtain the user's emotion data.

[1387] software

[1388] Emotion engine: Software that analyzes the user's emotional state from input data, for example, using Azure's Emotion API.

[1389] Database: Use MySQL or another relational database system to manage historical case information.

[1390] Generative AI model: Uses OpenAI's GPT-4 and other models to generate recommendations based on business ideas and emotional data.

[1391] Specific operation example

[1392] 1. User operations

[1393] The user inputs detailed information about their business idea into the device. For example, the user might input, "I want to sell a new protein bar to people in their 30s." The device then uses an emotion engine to analyze the user's emotional state in real time. For example, the device may return a result such as, "The user is feeling anxious."

[1394] 2. Data reception and preprocessing by the server

[1395] The server receives the business idea data and sentiment data sent from the device. The server preprocesses the received data, normalizing and encoding it as necessary. For example, the server converts the input "The target market is health-conscious people in their 30s" into "target_market: 30s health-conscious consumers."

[1396] 3. Case extraction and analysis by the server

[1397] After the preprocessing is complete, the server extracts similar past failures and successes from the database. The server also takes into account emotional data to find the most relevant cases. For example, it searches for "protein bars for health-conscious people in their 30s" and "anxiety."

[1398] 4. Server-generated recommendations

[1399] The server analyzes the cases extracted from the database using a generative AI model. The generative AI model identifies the causes of failure and factors of success and generates recommendations that best fit the user's emotional state. For example, specific advice is provided, such as "conduct thorough market research" or "emphasize low-carb and limit the target to people in their 30s."

[1400] 5. Feedback from the server to the device

[1401] The generated strategic recommendations are sent from the server to the terminal, which displays them to the user as concrete action plans, allowing the user to reevaluate their business strategies based on them.

[1402] Prompt Sentence Examples

[1403] "I'm starting a new health food business and would like some advice on how to succeed in a crowded market. I need advice on using specific ingredients to differentiate my product and developing targeted marketing campaigns."

[1404] In this way, this system provides advanced analysis and recommendations of business ideas that take into account the user's emotional state, thereby supporting more accurate strategic decision-making than conventional methods.

[1405] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1406] Step 1:

[1407] The user enters the details.

[1408] Specifically, the user inputs information about their business idea (e.g., target market, product characteristics, competitor information, etc.) into the terminal. Once the input is complete, the emotion engine analyzes the user's emotional state in real time.

[1409] Input: Business idea details and the user's emotional state.

[1410] Output: Sentiment data parsed by the emotion engine.

[1411] Specific operation: When a user enters "I want to sell a new protein bar to people in their 30s," the device records this and simultaneously sends emotional data such as the user's anxieties and expectations to the emotion engine for analysis.

[1412] Step 2:

[1413] Send data from the terminal to the server.

[1414] The terminal transmits the business idea data entered by the user and the emotion data analyzed by the emotion engine to the server.

[1415] Input: Business idea details, sentiment data.

[1416] Output: Business idea data and emotion data received by the server.

[1417] Specific operation: The device compiles data such as "The target market is health-conscious people in their 30s" and "The user is feeling anxious" and sends it to the server.

[1418] Step 3:

[1419] The server receives and preprocesses the data.

[1420] The server preprocesses the received business idea data and sentiment data, normalizing and encoding them as necessary.

[1421] Input: Received business idea data, sentiment data.

[1422] Output: Preprocessed data.

[1423] Specific operation: The server converts the data into a format suitable for analysis, such as "target_market: 30s health-conscious consumers" or "users are anxious."

[1424] Step 4:

[1425] The server performs data integration and case extraction.

[1426] Based on the pre-processed data, the server extracts similar past failures and successes from a database, and searches the database, taking into account the sentiment data, to find the most relevant cases.

[1427] Input: Preprocessed business idea data, sentiment data.

[1428] Output: Extracted historical case data.

[1429] Specific operation: The server searches the database and extracts past cases related to "protein bars for health-conscious people in their 30s" and "anxiety."

[1430] Step 5:

[1431] The server performs case analysis and recommendation generation.

[1432] Based on the extracted cases, the server uses a generative AI model to analyze them, identify the causes of failure and the factors behind success, and generate recommendations that best fit the user's emotional state.

[1433] Input: extracted case data, generative AI model.

[1434] Output: The generated recommendations.

[1435] Specific operation: The generative AI model generates recommendations such as "You should conduct thorough market research" and "Emphasis on low-carb and narrow the target to people in their 30s."

[1436] Step 6:

[1437] The server sends the recommendations to the device.

[1438] The generated recommendations are sent from the server to the device, which displays this information to the user.

[1439] Input: The generated recommendations.

[1440] Output: The recommendations that are served to the user.

[1441] Specific operation: The server sends a recommendation to the device, such as "Low-sugar, high-protein protein bars are in high demand. Marketing should be strengthened, especially for health-conscious people in their 30s," and the device displays it to the user.

[1442] (Application example 2)

[1443] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1444] The present invention aims to solve the problem that, when users realize their business ideas, conventional systems provide general advice without considering the user's emotional state, making it difficult to generate accurate recommendations that correspond to the individual situation and emotional state of the user.In particular, the present invention aims to reduce the stress and anxiety felt by operators who operate and maintain robots in factories and other workplaces, thereby achieving safe and efficient operation.

[1445] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1446] In this invention, the server includes: a means for a user to input detailed information about a business idea; a means for receiving and preprocessing the input business idea data; a means for combining the preprocessed data with an emotion engine that analyzes the user's emotional state in real time; a means for extracting similar past failures and successes from a database along with the emotion engine data; a means for analyzing the extracted cases and identifying causes of failure and factors of success; a means for generating strategic recommendations that take the user's emotional state into account from the identified causes and factors; and a means for providing the generated recommendations to the user. This makes it possible to provide advanced recommendations tailored to the user's emotional state when implementing the business idea. Furthermore, in a factory, analyzing the stress levels experienced by operators when operating or maintaining robots and providing maintenance procedures and solutions tailored to those levels enables safe and efficient operation.

[1447] "User" refers to the entity that uses the system to input business ideas and detailed information on the operation and maintenance of the robot.

[1448] A "business idea" is detailed information about a specific business or project, including market analysis, product characteristics, and competitive information.

[1449] "Emotion engine" is a general term for software and hardware that analyzes a user's emotional state in real time.

[1450] The "database" is a data storage system that accumulates information on past failures and successes associated with business ideas and emotional data.

[1451] "Preprocessing" is the process of converting data received from a user into a form suitable for analysis, including text normalization and encoding.

[1452] "Similar past failures and successes" refers to past cases extracted from the database that are similar to the current business idea or on-site situation.

[1453] "Generated recommendations" are strategic advice and specific action plans provided by generative AI models based on the results of data and sentiment analysis.

[1454] "Strategic recommendations" refer to specific advice and suggestions tailored to the user's emotional state and situation to improve the chances of business success.

[1455] This invention relates to a system that analyzes a user's emotional state and generates accurate recommendations for business ideas and on-site operations. This system mainly consists of an emotion engine, a generative AI model, a database, and a user interface.

[1456] Hardware and Software Configuration

[1457] The hardware required includes a user terminal (tablet or PC) and a wearable device for emotion analysis (such as a smartwatch), while the software includes an emotion engine, a database management system, a generative AI model, and a user interface application.

[1458] Specific processing of the system

[1459] 1. Acquiring emotion data:

[1460] A user wears a wearable device (e.g., a smartwatch) for emotion analysis, and emotion-related data such as heart rate and skin galvanic response are acquired in real time. These data are then transmitted to the user's device.

[1461] 2. Enter your business idea:

[1462] The user uses the interface of the user terminal to input detailed information about the business idea, including the target market, product characteristics, and competitor information.

[1463] 3. Data preprocessing and integration:

[1464] The data sent from the user's device is received by the server and preprocessed. The text data is normalized and encoded to convert it into a format suitable for analysis. The data is then integrated with the emotion engine data and prepared for analysis.

[1465] 4. Extraction of similar cases:

[1466] Based on the preprocessed data and the emotion data, the server extracts similar failure and success cases from a database of past cases, which stores past cases and their associated emotion data.

[1467] 5. Generating recommendations:

[1468] For each case drawn from the database, the generative AI model identifies the causes of failure and the factors behind success. By incorporating emotional data, the system generates targeted recommendations based on the user's emotional state, such as adjusting marketing strategies to take into account stress and anxiety levels.

[1469] 6. User Feedback:

[1470] The generated recommendations are sent from the server to the user's device and presented to the user through a user interface. Based on this feedback, the user can reevaluate and adjust their business strategy and on-site operations.

[1471] Specific examples

[1472] For example, if a user inputs a business idea for a new health food product (e.g., a protein bar), the emotion engine will sense the user's concerns. This information is then combined with the competitive intensity of the market through a generative AI model to provide specific recommendations, such as using specific ingredients to differentiate the product and developing a targeted marketing campaign.

[1473] Prompt Sentence Examples

[1474] "An operator is performing maintenance on a robot under high stress. Based on past cases, what smooth maintenance procedures and solutions would you recommend?"

[1475] This allows the system to perform complex information analysis, including the user's emotional state, and provide more accurate strategic advice.In factories, the system supports a safe and efficient work environment by providing maintenance procedures and solutions that take into account the operator's stress level.

[1476] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1477] Step 1:

[1478] The user wears a wearable device (e.g., a smartwatch) for emotion analysis, and physiological data such as heart rate and skin galvanic response are collected in real time.

[1479] Input: User physiological data (heart rate, galvanic skin response, etc.)

[1480] Output: Physiological data is sent to the device

[1481] How it works: The wearable device sends the data it senses to the user's device via Bluetooth or Wi-Fi.

[1482] Step 2:

[1483] The user enters detailed information about the business idea using the terminal interface, including target market, product characteristics, and competitor information.

[1484] Input: Detailed information about your business idea (text data)

[1485] Output: Detailed information is logged to the terminal

[1486] Operation: Accepts input from the keyboard or touch screen through the user device's UI.

[1487] Step 3:

[1488] The server receives the business idea data and emotion data transmitted from the terminal.

[1489] Input: Business idea data, physiological data

[1490] Output: Received data is saved on the server

[1491] Operation: The device sends the business idea and emotion data to the server as an HTTP request.

[1492] Step 4:

[1493] The server pre-processes the received data, which includes normalizing and encoding the text data and analyzing sentiment data in real time.

[1494] Input: Business idea data, physiological data

[1495] Output: Preprocessed text data and analysis results

[1496] How it works: Data is processed on the server side using a text normalizer and sentiment engine (sentiment analysis software).

[1497] Step 5:

[1498] Based on the preprocessed data, the server extracts similar past failures and successes from the database.

[1499] Input: Preprocessed text data and sentiment analysis results

[1500] Output: Extracted similar cases

[1501] How it works: The server uses a database management system (DBMS) to run queries and extract similar past cases.

[1502] Step 6:

[1503] The generative AI model analyzes the extracted cases to identify causes of failure and factors of success, and then generates strategic recommendations that take into account the user's emotional state.

[1504] Input: Extracted similar cases, sentiment analysis results

[1505] Output: Generated recommendations

[1506] How it works: A generative AI model (e.g., a GPT-based model) analyzes data and generates specific advice that reflects the user's emotional state.

[1507] Step 7:

[1508] The server transmits the generated recommendations to the user terminal and presents them to the user through a user interface.

[1509] Input: Generated recommendations

[1510] Output: Recommendations served to the user

[1511] How it works: The server sends recommendations as an HTTP response, which the device's UI application displays.

[1512] Step 8:

[1513] Example prompt: "An operator is performing maintenance on a robot under high stress. Based on past experience, what smooth maintenance procedures and solutions would you recommend?"

[1514] In this way, the system can analyze complex information, including the user's emotional state, and provide more accurate strategic recommendations.

[1515] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1516] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1517] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1518] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1519] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1520] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1521] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1522] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1523] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1524] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1525] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1526] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1527] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1528] 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.

[1529] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1530] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1531] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1532] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1533] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1534] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1535] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1536] The following is further disclosed regarding the above embodiment.

[1537] (Claim 1)

[1538] a means for a user to input detailed information about a business idea;

[1539] A means for receiving and preprocessing input business idea data;

[1540] A means for extracting similar past failure cases and success cases from a database based on the preprocessed data;

[1541] A means of analyzing the selected cases and identifying the causes of failure and factors of success;

[1542] A means for generating strategic recommendations from the identified causes and factors;

[1543] The system includes a means for providing the generated recommendations to a user.

[1544] (Claim 2)

[1545] 10. The system of claim 1, wherein the format of the preprocessed data is normalized and encoded for successful analysis.

[1546] (Claim 3)

[1547] 2. The system of claim 1, wherein the system monitors market changes and competitive conditions in real time and updates recommendations based on the latest information.

[1548] "Example 1"

[1549] (Claim 1)

[1550] a means for a user to input detailed information about a business idea;

[1551] A means for receiving and preprocessing input business idea data;

[1552] A means for extracting similar past failure cases and success cases from a database based on the preprocessed data;

[1553] A means for analyzing the cases extracted using the generative AI model and identifying the causes of failure and factors of success;

[1554] A means for generating strategic recommendations from the identified causes and factors;

[1555] The system includes a means for providing the generated recommendations to a user.

[1556] (Claim 2)

[1557] 10. The system of claim 1, wherein the format of the preprocessed data is normalized and encoded for successful analysis.

[1558] (Claim 3)

[1559] 2. The system of claim 1, wherein the system monitors market changes and competitive conditions in real time and updates recommendations based on the latest information.

[1560] "Application Example 1"

[1561] (Claim 1)

[1562] a means for a user to input detailed information about a business idea;

[1563] A means for receiving and preprocessing input business idea data;

[1564] A means for extracting similar past failure cases and success cases from a database based on the preprocessed data;

[1565] A means of analyzing the selected cases and identifying the causes of failure and factors of success;

[1566] A means for generating strategic recommendations from the identified causes and factors;

[1567] means for providing the generated recommendations to a user;

[1568] A means of analyzing the prompt using a generative AI model to generate recommendations; and

[1569] The system includes a means for updating and displaying the generated recommendations in real time.

[1570] (Claim 2)

[1571] 10. The system of claim 1, wherein the format of the preprocessed data is normalized and encoded for successful analysis.

[1572] (Claim 3)

[1573] 2. The system of claim 1, wherein the system monitors market changes and competitive conditions in real time and updates recommendations based on the latest information.

[1574] "Example 2: Combining Emotion Engines"

[1575] (Claim 1)

[1576] a means for a user to input detailed information about a business idea;

[1577] a means for analyzing the user's emotional state in real time as they input;

[1578] A means for receiving and preprocessing input business idea data and sentiment data;

[1579] A means for extracting similar past failure cases and success cases from a database based on the preprocessed data;

[1580] A means of analyzing the selected cases and identifying the causes of failure and factors of success;

[1581] A means for generating strategic recommendations according to the user's emotional state from the identified causes and factors;

[1582] The system includes a means for providing the generated recommendations to a user.

[1583] (Claim 2)

[1584] 10. The system of claim 1, wherein the format of the data is normalized and encoded to successfully analyze the preprocessed data and sentiment data.

[1585] (Claim 3)

[1586] 2. The system of claim 1, wherein the system monitors market changes and competitive conditions in real time and updates recommendations based on the latest information.

[1587] "Application example 2 when combining emotion engines"

[1588] (Claim 1)

[1589] a means for a user to input detailed information about a business idea;

[1590] A means for receiving and preprocessing input business idea data;

[1591] a means for combining an emotion engine that analyzes the user's emotional state in real time based on the preprocessed data;

[1592] A means for extracting similar past failure cases and success cases from a database together with the emotion engine data;

[1593] A means of analyzing the selected cases and identifying the causes of failure and factors of success;

[1594] A means for generating strategic recommendations from the identified causes and factors, taking into account the emotional state of the user;

[1595] The system includes a means for providing the generated recommendations to a user.

[1596] (Claim 2)

[1597] 10. The system of claim 1, wherein the format of the preprocessed data is normalized and encoded for successful analysis.

[1598] (Claim 3)

[1599] 2. The system of claim 1, wherein the system monitors market changes and competitive conditions in real time and updates recommendations based on the latest information.

[1600] (Claim 4)

[1601] The system according to claim 1, which analyzes the stress level of the operator when operating the robot based on the user's emotional data, and provides maintenance procedures and solutions according to that level. [Explanation of symbols]

[1602] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to input detailed information about a business idea; A means for receiving and preprocessing input business idea data; A means for extracting similar past failure cases and success cases from a database based on the preprocessed data; A means of analyzing the selected cases and identifying the causes of failure and factors of success; A means for generating strategic recommendations from the identified causes and factors; The system includes a means for providing the generated recommendations to a user.

2. The system of claim 1 , wherein the format of the preprocessed data is normalized and encoded for successful analysis.

3. 10. The system according to claim 1, wherein the system monitors market changes and competitive conditions in real time and updates recommendations based on the latest information.

Images