System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting and analyzing AI related to a brand name using a generative data model; means for calculating brand popularity, awareness, and reputation based on the collected information; means for providing the calculated knowledge to a user in real-time; and means for dynamic pricing on demand.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's market, when companies formulate promotional strategies, they need to quickly obtain detailed data on brand awareness, reputation, user attributes, and more. However, traditional methods require time to collect and analyze information, and lack real-time capabilities. Furthermore, they are unable to set dynamic pricing based on demand, which can result in low cost-effectiveness. Furthermore, it is difficult to obtain detailed attribute information on target audiences, making it difficult to differentiate from competitors. [Means for solving the problem]

[0005] This invention provides a system that uses a generative AI model to collect and analyze data related to brand names. First, the AI ​​model calculates the brand's name recognition, recognition, and reputation, and provides this information to users in real time. It also uses external data sources and APIs to obtain information related to the brand, and uses that data to analyze detailed demographic information such as the target audience's age, gender, hobbies, preferences, and purchasing behavior. Furthermore, it incorporates a means for dynamic pricing based on demand, allowing clients to pay according to the depth of research they require. This allows companies to perform fast and accurate market analysis and develop cost-effective marketing and sales strategies.

[0006] A "generative AI model" is an artificial intelligence model that uses machine learning technology to learn patterns in data and make predictions and analyses on new data.

[0007] A "brand name" is a name used to identify a particular product or service and distinguish it from other products or services.

[0008] "Data collection" refers to the process of gathering information for a specific purpose, and in this context specifically refers to the collection of brand-related information.

[0009] "Awareness" refers to the degree to which a particular brand is known to the general consumer or target audience.

[0010] "Awareness" refers to the degree to which consumers can recognize a brand and distinguish it from other brands.

[0011] "Reputation" refers to the evaluation and trust of a brand among consumers and the market.

[0012] "Users" refer to companies and individuals who use this system to conduct brand research and analysis.

[0013] "Real-time" refers to the ability to acquire, process, and provide information almost instantaneously, with minimal time delay.

[0014] "Dynamic pricing" refers to changing prices based on demand and other market conditions, allowing you to flexibly adjust the prices of the services you offer.

[0015] A "target audience" is a consumer group that a brand is specifically targeting, and is defined by attribute information such as age, gender, hobbies, preferences, and purchasing behavior.

[0016] "External Data Source" means a source of data provided from outside the System and used primarily to obtain information related to the Brand.

[0017] "API" is an abbreviation for Application Programming Interface, an interface that allows software programs to exchange information with each other. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention relates to a system for collecting and analyzing brand data using a generative AI model. An embodiment of this system is described below.

[0040] First, when the program launches, the server loads a pre-trained generative AI model, which uses machine learning techniques to learn patterns in data relevant to the brand.

[0041] The user accesses the web application through the browser on their device, enters the brand name they want to research, and clicks the submit button. The device then sends the entered brand name to the server. This brand name is sent in JSON format.

[0042] When the server receives the brand name sent from the device, it uses external data sources and APIs to obtain information related to the brand. This information includes brand awareness, recognition, reputation, etc. Specifically, the server sends a request to the external API using the brand name to obtain the required data. This data is obtained in JSON format.

[0043] Next, the server uses an AI model to calculate the brand's name recognition, recognition, and reputation based on the acquired data. For example, it calculates the name recognition, recognition, and reputation of "Brand A" as scores. These scores are calculated by the AI ​​model based on past data and are highly accurate.

[0044] The analyzed results are sent back to the user's device in real time from the server, where the user can view the results and gain detailed insights into the brand.

[0045] In addition, if the user selects the depth and detail of the search, the server performs dynamic pricing. This is a mechanism that calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the corresponding price (e.g., 3,000 yen) and presents it to the user.

[0046] As a concrete example, consider the case where a user wants to conduct a survey on "Brand A." The user enters "Brand A" in the browser and clicks the submit button. The device sends the brand name to the server, which then uses external data sources and APIs to obtain information related to "Brand A." The server uses an AI model to calculate scores such as 0.85 for name recognition, 0.78 for awareness, and 0.92 for reputation, and sends these back to the user. If the user then requests a survey on rank 3, the server calculates the price for rank 3 and presents it to the user.

[0047] In this way, the present invention becomes a useful tool for companies to carry out rapid and highly accurate market analysis and to formulate efficient marketing and sales strategies.

[0048] The processing flow will be explained below.

[0049] Step 1:

[0050] The server loads the pre-trained generative AI model when the program starts, deploying it in memory and making it available for subsequent data analysis.

[0051] Step 2:

[0052] A user accesses the web application using a browser on a device, enters the name of the brand for which the user wishes to conduct a survey, for example, "BrandA," and clicks the submit button.

[0053] Step 3:

[0054] The terminal sends the entered brand name in JSON format to the server, which then receives the brand name specified by the user.

[0055] Step 4:

[0056] The server reads the brand name received from the device and retrieves related data using an external API, by sending a request to the external API with the brand name as a query to collect information about the brand.

[0057] Step 5:

[0058] The server analyzes the data received from the external API and extracts the necessary information (such as popularity, recognition, and reputation). Based on this data, an AI model is used to calculate the scores for each evaluation index.

[0059] Step 6:

[0060] The server creates the calculated scores for popularity, recognition, and reputation in JSON format and sends them to the user's device in real time, allowing the user to check the results immediately.

[0061] Step 7:

[0062] Users can select a rank to specify the level of detail and depth of the investigation. For example, to select rank 3, select an option on the screen.

[0063] Step 8:

[0064] The terminal transmits the designated rank information to the server, which then sets prices based on the rank.

[0065] Step 9:

[0066] The server calculates the price corresponding to the specified rank and returns it to the user's terminal. For example, for rank 3, the price is calculated as 3,000 yen and presented to the user.

[0067] Step 10:

[0068] Develop appropriate marketing and sales strategies based on the analytics and pricing information you receive, and use this information to execute effective promotions to your target audience.

[0069] Example 1

[0070] 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."

[0071] There is a lack of methods to quickly and accurately analyze a brand's market situation and reputation, and to develop efficient marketing and sales strategies. There is also the issue of difficulty in setting dynamic pricing according to the depth and level of detail of the research.

[0072] 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.

[0073] In this invention, the server includes: means for loading a pre-trained generative AI model when the program is launched; means for a user to access the web application through a browser on the terminal and input and submit a brand name; means for the terminal to transmit the input brand name to the server in JSON format; means for the server to acquire data related to the brand using an external data source and an API; means for calculating the brand's name recognition, recognition, and reputation using the generative AI model based on the acquired data; means for returning the calculated score to the user's terminal in real time; and means for the server to perform dynamic pricing when the user selects the depth and level of detail of the research. This enables rapid and accurate analysis of the brand's market situation and reputation, the formulation of efficient marketing and sales strategies, and dynamic pricing according to the depth and level of detail of the research.

[0074] A "generative AI model" is a model trained using machine learning techniques to learn specific data patterns and make predictions or classifications.

[0075] A "server" is a device that has computing capabilities and sends and receives data over a network.

[0076] A "terminal" is a device operated by a user, and typically refers to a computer device such as a PC or smartphone.

[0077] A "browser" is software for viewing web pages and is used to obtain information via the Internet.

[0078] A "web application" is a program that runs on the Internet and is software that users can access and operate through a browser.

[0079] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format for structuring and sending and receiving data.

[0080] "External data sources" refers to data providing systems or databases that exist outside the server and are used to obtain information related to the brand.

[0081] "API" stands for Application Programming Interface, and is an interface for exchanging functions and data between software programs.

[0082] "Name recognition" is an indicator of how well known a particular brand is in the market and among consumers.

[0083] "Awareness" is an indicator of the degree to which a particular brand is recognized by consumers.

[0084] "Reputation" refers to the consumer and market evaluation and opinion of a particular brand.

[0085] "Dynamic pricing" is a system that changes prices depending on user choices and circumstances.

[0086] This invention relates to a system that uses a generative AI model to collect and analyze data related to a specific brand. This system operates among three parties: a server, a terminal, and a user. Detailed procedures and modes for implementing this invention are specifically described below.

[0087] Server Operation

[0088] When the program starts, the server first initializes and loads a pre-trained generative AI model. This AI model is trained using machine learning techniques based on past data and learns patterns related to brands. The required library is the Python TensorFlow library. The server loads the libraries and configuration files and loads the model into memory.

[0089] User operations

[0090] Users access the dedicated web application using their device's browser. Common web browsers such as Google Chrome and Mozilla Firefox can be used. The user enters the brand name they wish to research and clicks the submit button. This action activates JavaScript on the user's device, converting the brand name into JSON format.

[0091] Device behavior

[0092] The device sends the entered brand name to the server in JSON format. Network communication is performed using an HTTP POST request. For example, when a user searches for information about a brand called "BrandA," the device sends the following JSON data to the server:

[0093] json

[0094] {

[0095] "brand_name": "BrandA"

[0096] }

[0097] Data acquisition and analysis by the server

[0098] The server parses the JSON data received from the device and retrieves brand-related information using external data sources and APIs. Common external data sources include Google Trends, Twitter API, Brandwatch, etc. Using the Python Requests library, the server accesses these external APIs and retrieves brand-related data.

[0099] Based on the acquired information, the server uses a generative AI model to calculate brand awareness, recognition, and reputation scores. For example, "Brand A" might have a recognition score of 0.85, a recognition score of 0.78, and a reputation score of 0.92. These scores are then converted back to JSON format and sent back to the user's device in real time.

[0100] User review of results and request further investigation

[0101] The user checks the analysis results on their device. For example, the score for "Brand A" is displayed. If they want to conduct a more detailed investigation, they select the depth and level of detail of the investigation and send the request again. This request is also sent to the server in JSON format.

[0102] Server-driven dynamic pricing

[0103] The server receives a request for additional research from the user and dynamically sets the price according to the specified rank. For example, if a user requests a research of rank 3, the server calculates the price corresponding to rank 3 (e.g., 3,000 yen) and presents it to the user. The specific pricing algorithm is based on the user's selection and the settings in the server.

[0104] Examples of concrete examples and prompts

[0105] For example, if a user wants to research brand information for "Brand A," they enter "Brand A" into the browser's input form and click the submit button. The server uses external data sources and APIs to collect information related to "Brand A," and calculates the recognition, awareness, and reputation scores using a generative AI model. These scores can be viewed in real time. If a user requests more detailed research, a price will be displayed according to the desired ranking.

[0106] Example prompt sentence:

[0107] To research brand information for "Brand A," enter the brand name in the browser's input form and click the submit button. The server uses external data sources and APIs to collect information related to "Brand A," and uses a generative AI model to calculate scores for name recognition, awareness, and reputation. You can view the results in real time. If you would like a more detailed investigation, a price will be displayed based on your desired rank.

[0108] As described above, this invention is a useful tool for companies to conduct rapid and accurate market analysis and formulate efficient marketing and sales strategies. Furthermore, by using a generative AI model, it can provide highly accurate results.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1:

[0111] The server launches the program and loads the generative AI model. Specifically, the server uses Python's TensorFlow library to load the trained generative AI model into memory, and the server is then ready to analyze data related to the brand.

[0112] Input: Server start command

[0113] Output: Generative AI model loaded in memory

[0114] Step 2:

[0115] A user accesses a web application using a browser on their device. They enter a brand name in the browser's input form and click the submit button. For example, the user enters "BrandA."

[0116] Input: Brand name (e.g. "BrandA")

[0117] Output: Submit button click event

[0118] Step 3:

[0119] The device receives the click event of the submit button, converts the brand name entered by the user into JSON format, constructs the brand name as a JSON object using JavaScript, and then sends this JSON data to the server using an HTTP POST request.

[0120] Input: Submit button click event from browser

[0121] Output: Brand information in JSON format (e.g. "{'brand_name': 'BrandA'}")

[0122] Step 4:

[0123] The server parses the JSON data received from the device, extracts the brand name, and then calls an external data source API to retrieve information related to the specified brand. It uses the Python Requests library to collect data from external APIs, such as Google Trends, Twitter API, and Brandwatch.

[0124] Input: Brand information in JSON format (e.g. "{'brand_name': 'BrandA'}")

[0125] Output: Brand information retrieved from an external data source

[0126] Step 5:

[0127] The server inputs the acquired data into a generative AI model to calculate brand awareness, recognition, and reputation. The analyzed data is converted into a new JSON format and an evaluation score is calculated. For example, specific values ​​such as awareness of 0.85, recognition of 0.78, and reputation of 0.92 are output.

[0128] Input: Brand information retrieved from an external data source

[0129] Output: Prominence, awareness, and reputation scores (e.g., "{'brand_name': 'BrandA', 'Prominence': 0.85, 'Awareness': 0.78, 'Reputation': 0.92}")

[0130] Step 6:

[0131] The server converts the calculated score back into JSON format and sends it back to the user's device in real time over the network. The user's device receives this JSON data, parses it using JavaScript, and displays the analysis results in the browser.

[0132] Input: Prominence, awareness, and reputation scores (e.g., "{'brand_name': 'BrandA', 'Prominence': 0.85, 'Awareness': 0.78, 'Reputation': 0.92}")

[0133] Output: Analysis result JSON data returned to the user's device

[0134] Step 7:

[0135] If the user checks the analysis results on the device and wishes to conduct a more detailed investigation, they can select the depth and level of detail of the investigation and send the request again. The detailed investigation request is also sent to the server in JSON format.

[0136] Input: JSON format analysis results and user's detailed investigation request (e.g., "{'brand_name': 'BrandA', 'Request Detail': 'Rank 3'}")

[0137] Output: Detailed survey request JSON data sent to the server

[0138] Step 8:

[0139] The server receives detailed survey requests from users and dynamically sets prices according to the specified rank. For example, if a survey with rank 3 is requested, the server calculates the price corresponding to rank 3 (e.g., 3,000 yen) and presents it to the user. Prices are dynamically set using a Python calculation algorithm.

[0140] Input: User's detailed survey request JSON data

[0141] Output: Dynamically set price information (e.g., "{'brand_name': 'BrandA', 'Price for Rank 3': 3000}")

[0142] (Application example 1)

[0143] 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."

[0144] Traditional brand data collection and analysis systems struggled to accurately predict the effectiveness of advertising campaigns and provide detailed insights for formulating optimal strategies for target audiences. Furthermore, they lacked the ability for users to dynamically set prices based on demand, limiting the ability to develop flexible marketing strategies. This resulted in issues that reduced the effectiveness and cost-effectiveness of advertising campaigns.

[0145] 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.

[0146] In this invention, the server includes means for collecting and analyzing data related to brand names using a generative AI model, means for calculating brand awareness, recognition, and reputation based on the collected data, means for providing the calculated insights to users in real time, means for providing effectiveness predictions based on the target demographic and budget of the advertising campaign, and means for dynamic pricing according to demand. This enables rapid and accurate understanding of market conditions in advertising campaigns, enabling the formulation of effective marketing strategies and achieving high cost efficiency.

[0147] A "generative AI model" is an algorithm trained using machine learning techniques that has the ability to identify and analyze specific data patterns.

[0148] "Data related to a brand name" refers to information about a specific brand, including a wide range of data such as name recognition, awareness, and reputation.

[0149] "Brand awareness" refers to an indicator that shows how well a particular brand is recognized in the market and among consumers.

[0150] "Brand awareness" refers to an indicator that shows the degree of identifiable knowledge and image that consumers have of a particular brand.

[0151] "Brand reputation" refers to an indicator that shows the degree of evaluation and trustworthiness of a particular brand among consumers and the market.

[0152] A "target audience" is a group of consumers that is specifically targeted by advertising or marketing efforts.

[0153] "Advertising campaign effectiveness forecasting" refers to a prediction that evaluates in advance the impact and results of a specific advertising activity on the target audience.

[0154] "Dynamic pricing" refers to the practice of adjusting prices in real time based on demand and market conditions.

[0155] This invention relates to a system for collecting and analyzing data related to brand names using a generative AI model. This system uses a cloud server, user terminals, and external APIs to quickly and accurately predict the effectiveness of advertising campaigns. An embodiment of this system is described below in detail.

[0156] System Configuration

[0157] The server uses a pre-trained generative AI model to collect and analyze data related to the brand name entered by the user. Specifically, the server uses a cloud server (e.g., AWS EC2) to load the generative AI model (e.g., GPT-4) and perform analysis.

[0158] User Interface

[0159] The user inputs the brand name using a mobile application (using React Native for example) on their smartphone. When the user inputs the brand name and submits it, the data is sent to the server in JSON format.

[0160] Data collection

[0161] The server uses external data sources and APIs (e.g., Twitter API, Google Trends API) to obtain information related to the brand name, including brand awareness, recognition, reputation, etc. The server sends an API request and receives the results in JSON format.

[0162] Data analysis

[0163] The server uses the generative AI model to calculate brand awareness, recognition, and reputation based on the received data. For example, it generates scores such as 0.85 for brand awareness, 0.78 for recognition, and 0.92 for reputation. The calculation results are returned to the user in real time in JSON format.

[0164] Effect prediction

[0165] Additionally, the server provides forecasts based on the target audience and budget of the ad campaign, including the impact on the target audience and return on investment. Users can use these insights to plan effective ad campaigns.

[0166] Dynamic Pricing

[0167] If the user requests a detailed analysis, the server will dynamically set prices for each rank. For example, if the user selects rank 3, the server will calculate and present a specific price, such as 3,000 yen.

[0168] Specific examples

[0169] As a specific use case, consider a situation where a marketing professional at an advertising agency wants to predict the effectiveness of a new advertising campaign for "Brand A." The user opens the smartphone application and enters the following prompt:

[0170] "I would like to predict the effectiveness of Brand A's advertising campaign. I would like you to analyze the scores of name recognition, awareness, and reputation, and then predict and present the effectiveness for the target demographic."

[0171] As a result, the server calculates a brand awareness score of 0.85, an awareness score of 0.78, and a reputation score of 0.92 for "Brand A," and returns these to the user in real time. The server also provides detailed advertising effectiveness predictions and dynamic pricing, allowing users to create highly accurate marketing strategies.

[0172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0173] Step 1:

[0174] The user opens the mobile application on their smartphone, enters the brand name and a prompt message related to the advertising campaign in the application's input fields, and clicks the submit button. At this time, the entered brand name and prompt message are sent from the device to the server in JSON format.

[0175] Step 2:

[0176] The server parses the received JSON data, extracts the brand name and prompt, and sends a request to external data sources and APIs (e.g., Twitter API, Google Trends API) that includes the brand name and collects related data.

[0177] Step 3:

[0178] The data received from the external API is stored in JSON format on the server. The server then uses a generative AI model based on this collected data to calculate brand awareness, recognition, and reputation. For example, a generative AI model (GPT-4) performs pattern recognition based on past data. Specifically, the following values ​​are calculated: awareness score 0.85, recognition score 0.78, and reputation score 0.92.

[0179] Step 4:

[0180] The server then organizes the calculation results in JSON format and sends them back to the user's smartphone in real time, where the user can view the results, including the insight information.

[0181] Step 5:

[0182] If a user wants more detailed analysis or a prediction of the effectiveness of their advertising campaign, they select a rank for detailed analysis. The server will dynamically set a price based on the selected rank. This price is calculated based on a pre-set fee structure, and a specific price such as 3,000 yen is set for rank 3.

[0183] Step 6:

[0184] This dynamic pricing information is presented to users, who can then review it and access detailed analytics and performance forecasts, providing specific insights into their ad campaigns based on their target demographic and budget.

[0185] Step 7:

[0186] All processing results are displayed on the user's smartphone, ultimately enabling the user to create highly accurate marketing strategies based on detailed data.

[0187] 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.

[0188] This invention relates to a system that uses a generative AI model and an emotion engine to collect and analyze brand data and provide insights to users in real time. An embodiment of this system is described below.

[0189] First, when the program starts, the server loads a pre-trained generative AI model and emotion engine. The model uses machine learning techniques to learn patterns in data related to the brand, and the emotion engine is used to recognize and analyze user emotions.

[0190] The user accesses the web application through the browser on their device, enters the brand name they wish to survey, for example, "BrandA," and clicks the submit button. The device then sends the entered brand name in JSON format to the server.

[0191] When the server receives the brand name sent from the device, it uses external data sources and APIs to obtain information related to the brand. At this time, it sends a request to the external API using the brand name as a query and collects information about the brand in JSON format.

[0192] Next, the server uses the generative AI model to calculate the brand's name recognition, recognition, and reputation based on the acquired data. Specifically, it analyzes information related to the brand name and calculates scores for each evaluation index. For example, it calculates the name recognition, recognition, and reputation scores for "Brand A."

[0193] Additionally, to take user emotional data into account, an emotion engine is used to recognize and analyze emotions from user input. Through text input and other interactions provided by the user, the emotion engine evaluates the user's emotional state. This can yield emotional data such as "the user has positive feelings toward the brand."

[0194] The analyzed findings and sentiment data are sent back to the user's device in real time from the server. Users can view these results on their device and obtain detailed brand insights and sentiment information about their target audience. For example, in addition to numerical data such as awareness of 0.85, recognition of 0.78, and reputation of 0.92, the user's sentiment score is also provided.

[0195] In addition, if the user selects the level of detail or depth of the search, the server performs dynamic pricing. It calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the price based on rank 3 (e.g., 3,000 yen) and presents it to the user.

[0196] As a concrete example, if a user wants to conduct a survey on "Brand A," the user enters "Brand A" in the browser and clicks the submit button. The device sends the brand name to the server, which then uses external data sources and APIs to obtain information related to "Brand A." The server then uses a generative AI model to calculate scores for name recognition, awareness, and reputation. It also uses an emotion engine to obtain the user's emotional data and adds it to the analysis results. These results are then provided to the user in JSON format. If the user then requests a survey at rank 3, the server sets the price for rank 3, calculating it to be 3,000 yen and presenting it to the user.

[0197] In this way, the invention will enable businesses to gain detailed insights into their brands quickly and with high accuracy, and will be a useful tool for developing more meaningful marketing and sales strategies that incorporate user sentiment data.

[0198] The processing flow will be explained below.

[0199] Step 1:

[0200] When the program starts, the server loads the pre-trained generative AI model and emotion engine, deploying them in memory and making them available for subsequent data collection and analysis.

[0201] Step 2:

[0202] A user accesses the web application using a browser on a device, enters the name of the brand for which the user wishes to conduct a survey, for example, "BrandA," and clicks the submit button.

[0203] Step 3:

[0204] The terminal sends the entered brand name in JSON format to the server, which then receives the brand name specified by the user.

[0205] Step 4:

[0206] The server reads the brand name received from the device and retrieves related data using an external API, by sending a request to the external API with the brand name as a query to collect information about the brand.

[0207] Step 5:

[0208] The server analyzes the data received from the external API and extracts the necessary information (e.g., popularity, recognition, reputation). Based on this data, a generative AI model is used to calculate the scores for each evaluation index.

[0209] Step 6:

[0210] The server uses an emotion engine to obtain emotion data based on user input and interactions, including emotion recognition from user text input and other interactions.

[0211] Step 7:

[0212] The server combines the calculated popularity, recognition, and reputation scores with user sentiment data to generate a comprehensive analysis that provides detailed insights, including sentiment scores.

[0213] Step 8:

[0214] The server creates the analysis results in JSON format and sends them back to the user's device in real time, allowing the user to check the results immediately.

[0215] Step 9:

[0216] Users can further specify the level of detail and depth of the investigation by selecting a rank. For example, to select rank 3, select the appropriate option on the screen.

[0217] Step 10:

[0218] The terminal transmits the designated rank information to the server, which then receives a request for detailed investigation based on the rank.

[0219] Step 11:

[0220] The server calculates the price based on the specified rank and returns it to the user's terminal. For example, it calculates the price corresponding to rank 3 (e.g., 3,000 yen) and presents it to the user.

[0221] Step 12:

[0222] Develop appropriate marketing and sales strategies based on the analytics and pricing information you receive, and use this information to effectively promote your products to your target audience.

[0223] This series of processes allows companies to quickly gain highly accurate insights about their brand, and by incorporating emotional data, they can improve the accuracy of their marketing strategies.

[0224] Example 2

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

[0226] In modern marketing and brand management, it is extremely important to quickly and accurately obtain detailed brand-related insights and user sentiment data. However, conventional systems have struggled to objectively measure brand awareness, recognition, and reputation, or analyze user sentiment data in real time. This has left companies struggling to obtain sufficient information when formulating effective marketing strategies for their target audiences.

[0227] 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.

[0228] In this invention, the server includes means for collecting and analyzing data related to brand names using a generative AI model, means for recognizing and analyzing user emotions using an emotion engine, means for calculating brand awareness, recognition, and reputation based on the collected data, means for providing analyzed insights and emotion data to users in real time, and means for dynamic pricing according to demand, thereby enabling companies to quickly and accurately obtain detailed insights about their brands and emotion data of their target audiences.

[0229] A "generative AI model" is a machine learning model that learns, collects, and analyzes patterns in data related to brand names.

[0230] The "emotion engine" is a software component that recognizes and analyzes a user's emotions based on the user's text input and interactions.

[0231] "Brand awareness" is an evaluation indicator that indicates how widely a brand is recognized.

[0232] "Brand awareness" is an evaluation index that indicates the degree to which consumers or users recognize a particular brand and understand its characteristics.

[0233] "Brand reputation" is a score that indicates the evaluation and trust that consumers and users have of a brand.

[0234] "Means of providing in real time" refers to a method of instantly returning and providing analyzed data and knowledge to users.

[0235] "Dynamic pricing" is a method of varying prices depending on the level of detail and depth of research selected by the user.

[0236] "External Data Sources" refers to various sources on the Internet that provide information related to the brand.

[0237] "API" stands for Application Program Interface and refers to a mechanism that enables data communication between different software programs.

[0238] This invention relates to a system that uses a generative AI model and an emotion engine to collect and analyze brand data and provide insights to users in real time. An embodiment of this system is described below.

[0239] Hardware and Software Use:

[0240] Server: Collects and analyzes data, runs generative AI models and emotion engines.

[0241] User terminal: Uses a browser to receive input from the user.

[0242] Browser: Use any web browser (e.g., Google Chrome, Mozilla Firefox).

[0243] Generative AI models: Use machine learning models such as OpenAI GPT-4.

[0244] Sentiment Engine: Uses the Sentiment Analysis API (e.g., Google Cloud Natural Language API).

[0245] External data sources and APIs: Providing information relevant to your brand (e.g., Twitter API, Google News API).

[0246] Specific operation steps:

[0247] 1. Start the program:

[0248] When the program starts, the server loads a pre-trained generative AI model and an emotion engine. The generative AI model learns patterns in data related to the brand, and the emotion engine recognizes and analyzes user emotions.

[0249] 2. Enter your brand name:

[0250] The user opens a browser on their device and accesses the web application. The user enters the name of the brand they wish to survey. For example, they enter "BrandA" and clicks the submit button.

[0251] 3. Submit your brand name:

[0252] The device sends the brand name entered by the user in JSON format to the server, securely transmitting the data using the HTTPS protocol.

[0253] 4. Brand Data Collection:

[0254] The server retrieves information related to the brand using external data sources and APIs based on the brand name received from the device. Specifically, it sends a request to an external API (e.g., Twitter API, Google News API) using the brand name as a query, and collects information about the brand in JSON format.

[0255] 5. Brand Data Analysis:

[0256] The server uses a generative AI model to calculate brand awareness, recognition, and reputation based on the collected brand data. For example, the server calculates scores for "Brand A" such as awareness of 0.85, recognition of 0.78, and reputation of 0.92.

[0257] 6. Emotional Data Analysis:

[0258] The server uses an emotion engine to recognize and analyze emotions from user input. It evaluates whether the user has positive emotions about the brand. For example, it extracts "positive" emotion from the user input.

[0259] 7. Returning analysis results and emotion data:

[0260] The server sends the analyzed findings and sentiment data back to the user's device in real time in JSON format, where the user can view the results and get detailed brand insights and sentiment information about the target audience.

[0261] 8. Dynamic Pricing:

[0262] The server performs dynamic pricing when the user selects the level of detail and depth of the investigation. It calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the price for rank 3 as 3,000 yen and presents it to the user.

[0263] Examples:

[0264] If a user wants to research "BrandA", the system works as follows:

[0265] 1. The user enters "BrandA" in the browser and clicks the submit button.

[0266] 2. After receiving the brand name, the server uses the generative AI model to collect and analyze data about "BrandA."

[0267] 3. The server uses the emotion engine to recognize and analyze emotion data from the user's input.

[0268] 4. The server returns numerical data such as popularity 0.85, recognition 0.78, and reputation 0.92 to the user, as well as emotional data of "positive."

[0269] 5. If the user requests an additional detailed investigation of rank 3, the server calculates a price of 3,000 yen and presents it to the user.

[0270] Examples of prompts for generative AI models:

[0271] Calculate the familiarity, recognition, and reputation scores for brand "BrandA," and also rate the positivity of users based on their sentiment data.

[0272] In this way, the specific actions of the server, terminal and user make this system a useful tool for companies to gain detailed insights about their brand.

[0273] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0274] Step 1:

[0275] When the program starts, the server loads a pre-trained generative AI model and emotion engine, which prepares the system for analyzing brand data. The input is the configuration data for the generative AI model and emotion engine, and the output is a system ready for analysis.

[0276] Step 2:

[0277] The user opens a browser on their device and accesses the web application. They enter the name of the brand they want to survey and click the submit button. For example, they enter "BrandA." The input is a string of the brand name, and the output is JSON-formatted data sent from the device to the server.

[0278] Step 3:

[0279] The terminal sends the brand name entered by the user to the server in JSON format. The data is sent securely using the HTTPS protocol. The input is the brand name entered by the user, and the output is the request data sent to the server.

[0280] Step 4:

[0281] The server retrieves brand-related information using external data sources and APIs based on the brand name received from the device. Specifically, it sends a request to an external API (e.g., Twitter API, Google News API) using the brand name as a query, and collects brand-related information in JSON format. The input is the brand name query, and the output is the collected brand-related information.

[0282] Step 5:

[0283] The server uses a generative AI model based on the collected brand data to calculate brand awareness, recognition, and reputation. For example, it calculates scores such as 0.85 for awareness, 0.78 for recognition, and 0.92 for reputation for "Brand A." The input is the collected brand data, and the output is the score for each brand evaluation indicator.

[0284] Step 6:

[0285] The server uses an emotion engine to recognize and analyze emotions from user input. It evaluates whether the user has positive emotions about the brand. For example, it extracts the "positive" emotion from the user's input. The input is the user's text input, and the output is the user's emotion data.

[0286] Step 7:

[0287] The server sends the analyzed findings and sentiment data in JSON format back to the user's device in real time. The user can view these results on their device and obtain detailed brand insights and sentiment information about the target audience. The input is the analysis results and sentiment data, and the output is real-time information provided to the user.

[0288] Step 8:

[0289] The server performs dynamic pricing when the user selects the level of detail and depth of the search. It calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the price for rank 3 as 3,000 yen and presents it to the user. The input is the rank selected by the user, and the output is the calculated price information.

[0290] Examples:

[0291] If a user wants to research "BrandA":

[0292] 1. The user enters "BrandA" in the browser and clicks the submit button.

[0293] 2. After receiving the brand name, the server uses the generative AI model to collect and analyze data about "BrandA."

[0294] 3. The server uses the emotion engine to recognize and analyze emotion data from the user's input.

[0295] 4. The server returns numerical data such as popularity 0.85, recognition 0.78, and reputation 0.92 to the user, as well as emotional data of "positive."

[0296] 5. If the user requests an additional detailed investigation of rank 3, the server calculates a price of 3,000 yen and presents it to the user.

[0297] (Application example 2)

[0298] 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."

[0299] Conventional advertising systems simply collect and analyze brand-related information, making it difficult to provide personalized advertising that takes into account user emotional data and real-time interactions. The present invention aims to solve this problem and provide more accurate advertising.

[0300] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing data related to brand names using a generative AI model, means for calculating brand awareness, recognition, and reputation based on the collected data, means for providing the calculated insights to users in real time, means for recognizing and analyzing the emotional state of users using an emotion engine, means for displaying personalized advertisements based on the user's emotional data and brand analysis results, and means for dynamic pricing according to demand. This enables personalized display of advertisements based on the user's emotional state and brand evaluation.

[0301] A "generative AI model" is a model that uses machine learning techniques to learn patterns in data relevant to a brand and is useful for data collection and analysis.

[0302] An "emotion engine" is a technology for recognizing and analyzing emotional states through user input and interaction.

[0303] "Name recognition" is an indicator that indicates how widely known a particular brand is.

[0304] "Awareness" is an evaluation indicator that indicates the depth of knowledge and understanding of a particular brand.

[0305] "Reputation" is an evaluation index that indicates the degree of evaluation and trust for a particular brand.

[0306] "Personalized advertising" is advertising that is customized based on a user's individual interests and emotional state.

[0307] "Dynamic pricing" is a method of flexibly changing prices based on demand and other conditions.

[0308] A "target audience" is a specific group of consumers targeted by advertising and marketing activities.

[0309] An "external data source" is a data provider used to obtain information from outside the system.

[0310] "API" stands for Application Program Interface, a set of rules and tools that allow different software systems to communicate with each other.

[0311] This invention relates to a system that uses generative AI models and emotion engines to collect and analyze brand-related data, provide real-time insights to users, and even display personalized advertisements based on user emotion data.

[0312] First, when the program starts up, the server loads a pre-trained generative AI model and emotion engine. The generative AI model uses machine learning techniques to learn patterns in data related to the brand, and the emotion engine is used to recognize and analyze the user's emotional state.

[0313] The user accesses the application on their device and enters the name of the brand they wish to research. For example, if they enter "Brand A" and click the submit button, the device will send the entered brand name to the server in JSON format. After receiving the brand name sent from the device, the server uses external data sources and APIs to obtain information related to the brand. In this case, a request is sent to the external API using the brand name as a query, and information about the brand is collected in JSON format.

[0314] Next, the server uses the generative AI model based on the acquired data to calculate the brand's name recognition, recognition, and reputation. Specifically, it analyzes information related to the brand name and calculates scores for each evaluation index. For example, it calculates the name recognition, recognition, and reputation scores for "Brand A."

[0315] In addition, the server also takes into account the user's emotional data, using an emotion engine to recognize and analyze emotions from the user's input. Through the text input and other interactions provided by the user, the emotion engine evaluates the user's emotional state. Based on this evaluation, emotion data can be obtained, such as "the user has positive emotions toward the brand."

[0316] The analyzed findings and sentiment data are sent back to the user's device in real time from the server. Users can view these results on their device and obtain detailed brand insights and sentiment information about their target audience. For example, in addition to numerical data such as awareness of 0.85, recognition of 0.78, and reputation of 0.92, the user's sentiment score is also provided.

[0317] Furthermore, the analysis results can be used to display personalized advertisements to users. These advertisements are selected based on the user's emotional state and brand evaluation data, so they can more effectively capture the user's attention. For example, an advertisement message such as "Check out the special sale on a highly rated brand!" can be displayed.

[0318] The hardware used includes servers and user devices (smartphones and PCs), and the software used includes generative AI models, emotion engines, and external APIs, allowing users to gain detailed insights about any brand and see personalized ads based on those insights.

[0319] As a concrete example, a user enters "Brand A" in a browser and clicks the submit button. The device sends the brand name to the server, which then uses external data sources and APIs to obtain information related to "Brand A." The server then uses a generative AI model to calculate scores for familiarity, recognition, and reputation. It also uses an emotion engine to obtain the user's emotional data and adds it to the analysis results. These results are then provided to the user in JSON format. If the user subsequently requests a survey at rank 3, the server sets the price for rank 3, calculating it to be 3,000 yen and presenting it to the user.

[0320] Example prompts for generative AI models:

[0321] "Please tell me about the name recognition, recognition, and reputation of Brand A."

[0322] Example prompts in the Emotion Engine:

[0323] I think this brand is high quality.

[0324] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0325] Step 1:

[0326] The server loads pre-trained generative AI models and emotion engines when the program starts. This loads the necessary models and engines into memory and makes them available for use. The input is the trained model and emotion engine data, and the output is the loaded model and engine.

[0327] Step 2:

[0328] The user accesses the application on their device and enters the brand name they wish to investigate. For example, they enter "Brand A" and click the submit button. This entered brand name is sent from the device to the server in JSON format. The input is the brand name entered by the user, and the output is brand name data in JSON format.

[0329] Step 3:

[0330] When the server receives the brand name sent from the device, it uses external data sources and APIs to obtain information related to the brand. At this time, it sends a request to the external API using the brand name as a query and collects information about the brand in JSON format. The input is brand name data in JSON format, and the output is brand information data in JSON format.

[0331] Step 4:

[0332] The server uses a generative AI model based on the acquired brand information data to calculate brand awareness, recognition, and reputation. Specifically, it analyzes various data related to the brand name and calculates scores for each evaluation indicator. The input is brand information data in JSON format, and the output is scores for awareness, recognition, and reputation.

[0333] Step 5:

[0334] The server also takes into account the user's emotional data, and therefore uses an emotion engine to recognize and analyze emotions from the user's input. Through text input and other interactions provided by the user, the emotion engine evaluates the user's emotional state. The input is the user's text input data, and the output is the analyzed emotional data.

[0335] Step 6:

[0336] The server transmits the analyzed findings and sentiment data to the user's device in real time, allowing the user to view the results on their device and obtain detailed brand insights and sentiment information. The inputs are recognition, awareness, and reputation scores and sentiment data, and the output is insights and sentiment information displayed on the user's device.

[0337] Step 7:

[0338] The server generates a personalized advertisement based on the analysis results and displays it to the user. The advertisement is selected based on the user's emotional state and brand evaluation data. The input is the emotional data and brand evaluation data, and the output is a personalized advertising message displayed on the user's device.

[0339] 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.

[0340] 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.

[0341] 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.

[0342] [Second embodiment]

[0343] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0344] 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.

[0345] 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).

[0346] 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.

[0347] 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.

[0348] 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).

[0349] 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.

[0350] 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.

[0351] 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.

[0352] 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.

[0353] 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.

[0354] 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."

[0355] The present invention relates to a system for collecting and analyzing brand data using a generative AI model. An embodiment of this system is described below.

[0356] First, when the program launches, the server loads a pre-trained generative AI model, which uses machine learning techniques to learn patterns in data relevant to the brand.

[0357] The user accesses the web application through the browser on their device, enters the brand name they want to research, and clicks the submit button. The device then sends the entered brand name to the server. This brand name is sent in JSON format.

[0358] When the server receives the brand name sent from the device, it uses external data sources and APIs to obtain information related to the brand. This information includes brand awareness, recognition, reputation, etc. Specifically, the server sends a request to the external API using the brand name to obtain the required data. This data is obtained in JSON format.

[0359] Next, the server uses an AI model to calculate the brand's name recognition, recognition, and reputation based on the acquired data. For example, it calculates the name recognition, recognition, and reputation of "Brand A" as scores. These scores are calculated by the AI ​​model based on past data and are highly accurate.

[0360] The analyzed results are sent back to the user's device in real time from the server, where the user can view the results and gain detailed insights into the brand.

[0361] In addition, if the user selects the depth and detail of the search, the server performs dynamic pricing. This is a mechanism that calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the corresponding price (e.g., 3,000 yen) and presents it to the user.

[0362] As a concrete example, consider the case where a user wants to conduct a survey on "Brand A." The user enters "Brand A" in the browser and clicks the submit button. The device sends the brand name to the server, which then uses external data sources and APIs to obtain information related to "Brand A." The server uses an AI model to calculate scores such as 0.85 for name recognition, 0.78 for awareness, and 0.92 for reputation, and sends these back to the user. If the user then requests a survey on rank 3, the server calculates the price for rank 3 and presents it to the user.

[0363] In this way, the present invention becomes a useful tool for companies to carry out rapid and highly accurate market analysis and to formulate efficient marketing and sales strategies.

[0364] The processing flow will be explained below.

[0365] Step 1:

[0366] The server loads the pre-trained generative AI model when the program starts, deploying it in memory and making it available for subsequent data analysis.

[0367] Step 2:

[0368] A user accesses the web application using a browser on a device, enters the name of the brand for which the user wishes to conduct a survey, for example, "BrandA," and clicks the submit button.

[0369] Step 3:

[0370] The terminal sends the entered brand name in JSON format to the server, which then receives the brand name specified by the user.

[0371] Step 4:

[0372] The server reads the brand name received from the device and retrieves related data using an external API, by sending a request to the external API with the brand name as a query to collect information about the brand.

[0373] Step 5:

[0374] The server analyzes the data received from the external API and extracts the necessary information (such as popularity, recognition, and reputation). Based on this data, an AI model is used to calculate the scores for each evaluation index.

[0375] Step 6:

[0376] The server creates the calculated scores for popularity, recognition, and reputation in JSON format and sends them to the user's device in real time, allowing the user to check the results immediately.

[0377] Step 7:

[0378] Users can select a rank to specify the level of detail and depth of the investigation. For example, to select rank 3, select an option on the screen.

[0379] Step 8:

[0380] The terminal transmits the designated rank information to the server, which then sets prices based on the rank.

[0381] Step 9:

[0382] The server calculates the price corresponding to the specified rank and returns it to the user's terminal. For example, for rank 3, the price is calculated as 3,000 yen and presented to the user.

[0383] Step 10:

[0384] Develop appropriate marketing and sales strategies based on the analytics and pricing information you receive, and use this information to execute effective promotions to your target audience.

[0385] Example 1

[0386] 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."

[0387] There is a lack of methods to quickly and accurately analyze a brand's market situation and reputation, and to develop efficient marketing and sales strategies. There is also the issue of difficulty in setting dynamic pricing according to the depth and level of detail of the research.

[0388] 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.

[0389] In this invention, the server includes: means for loading a pre-trained generative AI model when the program is launched; means for a user to access the web application through a browser on the terminal and input and submit a brand name; means for the terminal to transmit the input brand name to the server in JSON format; means for the server to acquire data related to the brand using an external data source and an API; means for calculating the brand's name recognition, recognition, and reputation using the generative AI model based on the acquired data; means for returning the calculated score to the user's terminal in real time; and means for the server to perform dynamic pricing when the user selects the depth and level of detail of the research. This enables rapid and accurate analysis of the brand's market situation and reputation, the formulation of efficient marketing and sales strategies, and dynamic pricing according to the depth and level of detail of the research.

[0390] A "generative AI model" is a model trained using machine learning techniques to learn specific data patterns and make predictions or classifications.

[0391] A "server" is a device that has computing capabilities and sends and receives data over a network.

[0392] A "terminal" is a device operated by a user, and typically refers to a computer device such as a PC or smartphone.

[0393] A "browser" is software for viewing web pages and is used to obtain information via the Internet.

[0394] A "web application" is a program that runs on the Internet and is software that users can access and operate through a browser.

[0395] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format for structuring and sending and receiving data.

[0396] "External data sources" refers to data providing systems or databases that exist outside the server and are used to obtain information related to the brand.

[0397] "API" stands for Application Programming Interface, and is an interface for exchanging functions and data between software programs.

[0398] "Name recognition" is an indicator of how well known a particular brand is in the market and among consumers.

[0399] "Awareness" is an indicator of the degree to which a particular brand is recognized by consumers.

[0400] "Reputation" refers to the consumer and market evaluation and opinion of a particular brand.

[0401] "Dynamic pricing" is a system that changes prices depending on user choices and circumstances.

[0402] This invention relates to a system that uses a generative AI model to collect and analyze data related to a specific brand. This system operates among three parties: a server, a terminal, and a user. Detailed procedures and modes for implementing this invention are specifically described below.

[0403] Server Operation

[0404] When the program starts, the server first initializes and loads a pre-trained generative AI model. This AI model is trained using machine learning techniques based on past data and learns patterns related to brands. The required library is the Python TensorFlow library. The server loads the libraries and configuration files and loads the model into memory.

[0405] User operations

[0406] Users access the dedicated web application using their device's browser. Common web browsers such as Google Chrome and Mozilla Firefox can be used. The user enters the brand name they wish to research and clicks the submit button. This action activates JavaScript on the user's device, converting the brand name into JSON format.

[0407] Device behavior

[0408] The device sends the entered brand name to the server in JSON format. Network communication is performed using an HTTP POST request. For example, when a user searches for information about a brand called "BrandA," the device sends the following JSON data to the server:

[0409] json

[0410] {

[0411] "brand_name": "BrandA"

[0412] }

[0413] Data acquisition and analysis by the server

[0414] The server parses the JSON data received from the device and retrieves brand-related information using external data sources and APIs. Common external data sources include Google Trends, Twitter API, Brandwatch, etc. Using the Python Requests library, the server accesses these external APIs and retrieves brand-related data.

[0415] Based on the acquired information, the server uses a generative AI model to calculate brand awareness, recognition, and reputation scores. For example, "Brand A" might have a recognition score of 0.85, a recognition score of 0.78, and a reputation score of 0.92. These scores are then converted back to JSON format and sent back to the user's device in real time.

[0416] User review of results and request further investigation

[0417] The user checks the analysis results on their device. For example, the score for "Brand A" is displayed. If they want to conduct a more detailed investigation, they select the depth and level of detail of the investigation and send the request again. This request is also sent to the server in JSON format.

[0418] Server-driven dynamic pricing

[0419] The server receives a request for additional research from the user and dynamically sets the price according to the specified rank. For example, if a user requests a research of rank 3, the server calculates the price corresponding to rank 3 (e.g., 3,000 yen) and presents it to the user. The specific pricing algorithm is based on the user's selection and the settings in the server.

[0420] Examples of concrete examples and prompts

[0421] For example, if a user wants to research brand information for "Brand A," they enter "Brand A" into the browser's input form and click the submit button. The server uses external data sources and APIs to collect information related to "Brand A," and calculates the recognition, awareness, and reputation scores using a generative AI model. These scores can be viewed in real time. If a user requests more detailed research, a price will be displayed according to the desired ranking.

[0422] Example prompt sentence:

[0423] To research brand information for "Brand A," enter the brand name in the browser's input form and click the submit button. The server uses external data sources and APIs to collect information related to "Brand A," and uses a generative AI model to calculate scores for name recognition, awareness, and reputation. You can view the results in real time. If you would like a more detailed investigation, a price will be displayed based on your desired rank.

[0424] As described above, this invention is a useful tool for companies to conduct rapid and accurate market analysis and formulate efficient marketing and sales strategies. Furthermore, by using a generative AI model, it can provide highly accurate results.

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

[0426] Step 1:

[0427] The server launches the program and loads the generative AI model. Specifically, the server uses Python's TensorFlow library to load the trained generative AI model into memory, and the server is then ready to analyze data related to the brand.

[0428] Input: Server start command

[0429] Output: Generative AI model loaded in memory

[0430] Step 2:

[0431] A user accesses a web application using a browser on their device. They enter a brand name in the browser's input form and click the submit button. For example, the user enters "BrandA."

[0432] Input: Brand name (e.g. "BrandA")

[0433] Output: Submit button click event

[0434] Step 3:

[0435] The device receives the click event of the submit button, converts the brand name entered by the user into JSON format, constructs the brand name as a JSON object using JavaScript, and then sends this JSON data to the server using an HTTP POST request.

[0436] Input: Submit button click event from browser

[0437] Output: Brand information in JSON format (e.g. "{'brand_name': 'BrandA'}")

[0438] Step 4:

[0439] The server parses the JSON data received from the device, extracts the brand name, and then calls an external data source API to retrieve information related to the specified brand. It uses the Python Requests library to collect data from external APIs, such as Google Trends, Twitter API, and Brandwatch.

[0440] Input: Brand information in JSON format (e.g. "{'brand_name': 'BrandA'}")

[0441] Output: Brand information retrieved from an external data source

[0442] Step 5:

[0443] The server inputs the acquired data into a generative AI model to calculate brand awareness, recognition, and reputation. The analyzed data is converted into a new JSON format and an evaluation score is calculated. For example, specific values ​​such as awareness of 0.85, recognition of 0.78, and reputation of 0.92 are output.

[0444] Input: Brand information retrieved from an external data source

[0445] Output: Prominence, awareness, and reputation scores (e.g., "{'brand_name': 'BrandA', 'Prominence': 0.85, 'Awareness': 0.78, 'Reputation': 0.92}")

[0446] Step 6:

[0447] The server converts the calculated score back into JSON format and sends it back to the user's device in real time over the network. The user's device receives this JSON data, parses it using JavaScript, and displays the analysis results in the browser.

[0448] Input: Prominence, awareness, and reputation scores (e.g., "{'brand_name': 'BrandA', 'Prominence': 0.85, 'Awareness': 0.78, 'Reputation': 0.92}")

[0449] Output: Analysis result JSON data returned to the user's device

[0450] Step 7:

[0451] If the user checks the analysis results on the device and wishes to conduct a more detailed investigation, they can select the depth and level of detail of the investigation and send the request again. The detailed investigation request is also sent to the server in JSON format.

[0452] Input: JSON format analysis results and user's detailed investigation request (e.g., "{'brand_name': 'BrandA', 'Request Detail': 'Rank 3'}")

[0453] Output: Detailed survey request JSON data sent to the server

[0454] Step 8:

[0455] The server receives detailed survey requests from users and dynamically sets prices according to the specified rank. For example, if a survey with rank 3 is requested, the server calculates the price corresponding to rank 3 (e.g., 3,000 yen) and presents it to the user. Prices are dynamically set using a Python calculation algorithm.

[0456] Input: User's detailed survey request JSON data

[0457] Output: Dynamically set price information (e.g., "{'brand_name': 'BrandA', 'Price for Rank 3': 3000}")

[0458] (Application example 1)

[0459] 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."

[0460] Traditional brand data collection and analysis systems struggled to accurately predict the effectiveness of advertising campaigns and provide detailed insights for formulating optimal strategies for target audiences. Furthermore, they lacked the ability for users to dynamically set prices based on demand, limiting the ability to develop flexible marketing strategies. This resulted in issues that reduced the effectiveness and cost-effectiveness of advertising campaigns.

[0461] 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.

[0462] In this invention, the server includes means for collecting and analyzing data related to brand names using a generative AI model, means for calculating brand awareness, recognition, and reputation based on the collected data, means for providing the calculated insights to users in real time, means for providing effectiveness predictions based on the target demographic and budget of the advertising campaign, and means for dynamic pricing according to demand. This enables rapid and accurate understanding of market conditions in advertising campaigns, enabling the formulation of effective marketing strategies and achieving high cost efficiency.

[0463] A "generative AI model" is an algorithm trained using machine learning techniques that has the ability to identify and analyze specific data patterns.

[0464] "Data related to a brand name" refers to information about a specific brand, including a wide range of data such as name recognition, awareness, and reputation.

[0465] "Brand awareness" refers to an indicator that shows how well a particular brand is recognized in the market and among consumers.

[0466] "Brand awareness" refers to an indicator that shows the degree of identifiable knowledge and image that consumers have of a particular brand.

[0467] "Brand reputation" refers to an indicator that shows the degree of evaluation and trustworthiness of a particular brand among consumers and the market.

[0468] A "target audience" is a group of consumers that is specifically targeted by advertising or marketing efforts.

[0469] "Advertising campaign effectiveness forecasting" refers to a prediction that evaluates in advance the impact and results of a specific advertising activity on the target audience.

[0470] "Dynamic pricing" refers to the practice of adjusting prices in real time based on demand and market conditions.

[0471] This invention relates to a system for collecting and analyzing data related to brand names using a generative AI model. This system uses a cloud server, user terminals, and external APIs to quickly and accurately predict the effectiveness of advertising campaigns. An embodiment of this system is described below in detail.

[0472] System Configuration

[0473] The server uses a pre-trained generative AI model to collect and analyze data related to the brand name entered by the user. Specifically, the server uses a cloud server (e.g., AWS EC2) to load the generative AI model (e.g., GPT-4) and perform analysis.

[0474] User Interface

[0475] The user inputs the brand name using a mobile application (using React Native for example) on their smartphone. When the user inputs the brand name and submits it, the data is sent to the server in JSON format.

[0476] Data collection

[0477] The server uses external data sources and APIs (e.g., Twitter API, Google Trends API) to obtain information related to the brand name, including brand awareness, recognition, reputation, etc. The server sends an API request and receives the results in JSON format.

[0478] Data analysis

[0479] The server uses the generative AI model to calculate brand awareness, recognition, and reputation based on the received data. For example, it generates scores such as 0.85 for brand awareness, 0.78 for recognition, and 0.92 for reputation. The calculation results are returned to the user in real time in JSON format.

[0480] Effect prediction

[0481] Additionally, the server provides forecasts based on the target audience and budget of the ad campaign, including the impact on the target audience and return on investment. Users can use these insights to plan effective ad campaigns.

[0482] Dynamic Pricing

[0483] If the user requests a detailed analysis, the server will dynamically set prices for each rank. For example, if the user selects rank 3, the server will calculate and present a specific price, such as 3,000 yen.

[0484] Specific examples

[0485] As a specific use case, consider a situation where a marketing professional at an advertising agency wants to predict the effectiveness of a new advertising campaign for "Brand A." The user opens the smartphone application and enters the following prompt:

[0486] "I would like to predict the effectiveness of Brand A's advertising campaign. I would like you to analyze the scores of name recognition, awareness, and reputation, and then predict and present the effectiveness for the target demographic."

[0487] As a result, the server calculates a brand awareness score of 0.85, an awareness score of 0.78, and a reputation score of 0.92 for "Brand A," and returns these to the user in real time. The server also provides detailed advertising effectiveness predictions and dynamic pricing, allowing users to create highly accurate marketing strategies.

[0488] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0489] Step 1:

[0490] The user opens the mobile application on their smartphone, enters the brand name and a prompt message related to the advertising campaign in the application's input fields, and clicks the submit button. At this time, the entered brand name and prompt message are sent from the device to the server in JSON format.

[0491] Step 2:

[0492] The server parses the received JSON data, extracts the brand name and prompt, and sends a request to external data sources and APIs (e.g., Twitter API, Google Trends API) that includes the brand name and collects related data.

[0493] Step 3:

[0494] The data received from the external API is stored in JSON format on the server. The server then uses a generative AI model based on this collected data to calculate brand awareness, recognition, and reputation. For example, a generative AI model (GPT-4) performs pattern recognition based on past data. Specifically, the following values ​​are calculated: awareness score 0.85, recognition score 0.78, and reputation score 0.92.

[0495] Step 4:

[0496] The server then organizes the calculation results in JSON format and sends them back to the user's smartphone in real time, where the user can view the results, including the insight information.

[0497] Step 5:

[0498] If a user wants more detailed analysis or a prediction of the effectiveness of their advertising campaign, they select a rank for detailed analysis. The server will dynamically set a price based on the selected rank. This price is calculated based on a pre-set fee structure, and a specific price such as 3,000 yen is set for rank 3.

[0499] Step 6:

[0500] This dynamic pricing information is presented to users, who can then review it and access detailed analytics and performance forecasts, providing specific insights into their ad campaigns based on their target demographic and budget.

[0501] Step 7:

[0502] All processing results are displayed on the user's smartphone, ultimately enabling the user to create highly accurate marketing strategies based on detailed data.

[0503] 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.

[0504] This invention relates to a system that uses a generative AI model and an emotion engine to collect and analyze brand data and provide insights to users in real time. An embodiment of this system is described below.

[0505] First, when the program starts, the server loads a pre-trained generative AI model and emotion engine. The model uses machine learning techniques to learn patterns in data related to the brand, and the emotion engine is used to recognize and analyze user emotions.

[0506] The user accesses the web application through the browser on their device, enters the brand name they wish to survey, for example, "BrandA," and clicks the submit button. The device then sends the entered brand name in JSON format to the server.

[0507] When the server receives the brand name sent from the device, it uses external data sources and APIs to obtain information related to the brand. At this time, it sends a request to the external API using the brand name as a query and collects information about the brand in JSON format.

[0508] Next, the server uses the generative AI model to calculate the brand's name recognition, recognition, and reputation based on the acquired data. Specifically, it analyzes information related to the brand name and calculates scores for each evaluation index. For example, it calculates the name recognition, recognition, and reputation scores for "Brand A."

[0509] Additionally, to take user emotional data into account, an emotion engine is used to recognize and analyze emotions from user input. Through text input and other interactions provided by the user, the emotion engine evaluates the user's emotional state. This can yield emotional data such as "the user has positive feelings toward the brand."

[0510] The analyzed findings and sentiment data are sent back to the user's device in real time from the server. Users can view these results on their device and obtain detailed brand insights and sentiment information about their target audience. For example, in addition to numerical data such as awareness of 0.85, recognition of 0.78, and reputation of 0.92, the user's sentiment score is also provided.

[0511] In addition, if the user selects the level of detail or depth of the search, the server performs dynamic pricing. It calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the price based on rank 3 (e.g., 3,000 yen) and presents it to the user.

[0512] As a concrete example, if a user wants to conduct a survey on "Brand A," the user enters "Brand A" in the browser and clicks the submit button. The device sends the brand name to the server, which then uses external data sources and APIs to obtain information related to "Brand A." The server then uses a generative AI model to calculate scores for name recognition, awareness, and reputation. It also uses an emotion engine to obtain the user's emotional data and adds it to the analysis results. These results are then provided to the user in JSON format. If the user then requests a survey at rank 3, the server sets the price for rank 3, calculating it to be 3,000 yen and presenting it to the user.

[0513] In this way, the invention will enable businesses to gain detailed insights into their brands quickly and with high accuracy, and will be a useful tool for developing more meaningful marketing and sales strategies that incorporate user sentiment data.

[0514] The processing flow will be explained below.

[0515] Step 1:

[0516] When the program starts, the server loads the pre-trained generative AI model and emotion engine, deploying them in memory and making them available for subsequent data collection and analysis.

[0517] Step 2:

[0518] A user accesses the web application using a browser on a device, enters the name of the brand for which the user wishes to conduct a survey, for example, "BrandA," and clicks the submit button.

[0519] Step 3:

[0520] The terminal sends the entered brand name in JSON format to the server, which then receives the brand name specified by the user.

[0521] Step 4:

[0522] The server reads the brand name received from the device and retrieves related data using an external API, by sending a request to the external API with the brand name as a query to collect information about the brand.

[0523] Step 5:

[0524] The server analyzes the data received from the external API and extracts the necessary information (e.g., popularity, recognition, reputation). Based on this data, a generative AI model is used to calculate the scores for each evaluation index.

[0525] Step 6:

[0526] The server uses an emotion engine to obtain emotion data based on user input and interactions, including emotion recognition from user text input and other interactions.

[0527] Step 7:

[0528] The server combines the calculated popularity, recognition, and reputation scores with user sentiment data to generate a comprehensive analysis that provides detailed insights, including sentiment scores.

[0529] Step 8:

[0530] The server creates the analysis results in JSON format and sends them back to the user's device in real time, allowing the user to check the results immediately.

[0531] Step 9:

[0532] Users can further specify the level of detail and depth of the investigation by selecting a rank. For example, to select rank 3, select the appropriate option on the screen.

[0533] Step 10:

[0534] The terminal transmits the designated rank information to the server, which then receives a request for detailed investigation based on the rank.

[0535] Step 11:

[0536] The server calculates the price based on the specified rank and returns it to the user's terminal. For example, it calculates the price corresponding to rank 3 (e.g., 3,000 yen) and presents it to the user.

[0537] Step 12:

[0538] Develop appropriate marketing and sales strategies based on the analytics and pricing information you receive, and use this information to effectively promote your products to your target audience.

[0539] This series of processes allows companies to quickly gain highly accurate insights about their brand, and by incorporating emotional data, they can improve the accuracy of their marketing strategies.

[0540] Example 2

[0541] 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."

[0542] In modern marketing and brand management, it is extremely important to quickly and accurately obtain detailed brand-related insights and user sentiment data. However, conventional systems have struggled to objectively measure brand awareness, recognition, and reputation, or analyze user sentiment data in real time. This has left companies struggling to obtain sufficient information when formulating effective marketing strategies for their target audiences.

[0543] 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.

[0544] In this invention, the server includes means for collecting and analyzing data related to brand names using a generative AI model, means for recognizing and analyzing user emotions using an emotion engine, means for calculating brand awareness, recognition, and reputation based on the collected data, means for providing analyzed insights and emotion data to users in real time, and means for dynamic pricing according to demand, thereby enabling companies to quickly and accurately obtain detailed insights about their brands and emotion data of their target audiences.

[0545] A "generative AI model" is a machine learning model that learns, collects, and analyzes patterns in data related to brand names.

[0546] The "emotion engine" is a software component that recognizes and analyzes a user's emotions based on the user's text input and interactions.

[0547] "Brand awareness" is an evaluation indicator that indicates how widely a brand is recognized.

[0548] "Brand awareness" is an evaluation index that indicates the degree to which consumers or users recognize a particular brand and understand its characteristics.

[0549] "Brand reputation" is a score that indicates the evaluation and trust that consumers and users have of a brand.

[0550] "Means of providing in real time" refers to a method of instantly returning and providing analyzed data and knowledge to users.

[0551] "Dynamic pricing" is a method of varying prices depending on the level of detail and depth of research selected by the user.

[0552] "External Data Sources" refers to various sources on the Internet that provide information related to the brand.

[0553] "API" stands for Application Program Interface and refers to a mechanism that enables data communication between different software programs.

[0554] This invention relates to a system that uses a generative AI model and an emotion engine to collect and analyze brand data and provide insights to users in real time. An embodiment of this system is described below.

[0555] Hardware and Software Use:

[0556] Server: Collects and analyzes data, runs generative AI models and emotion engines.

[0557] User terminal: Uses a browser to receive input from the user.

[0558] Browser: Use any web browser (e.g., Google Chrome, Mozilla Firefox).

[0559] Generative AI models: Use machine learning models such as OpenAI GPT-4.

[0560] Sentiment Engine: Uses the Sentiment Analysis API (e.g., Google Cloud Natural Language API).

[0561] External data sources and APIs: Providing information relevant to your brand (e.g., Twitter API, Google News API).

[0562] Specific operation steps:

[0563] 1. Start the program:

[0564] When the program starts, the server loads a pre-trained generative AI model and an emotion engine. The generative AI model learns patterns in data related to the brand, and the emotion engine recognizes and analyzes user emotions.

[0565] 2. Enter your brand name:

[0566] The user opens a browser on their device and accesses the web application. The user enters the name of the brand they wish to survey. For example, they enter "BrandA" and clicks the submit button.

[0567] 3. Submit your brand name:

[0568] The device sends the brand name entered by the user in JSON format to the server, securely transmitting the data using the HTTPS protocol.

[0569] 4. Brand Data Collection:

[0570] The server retrieves information related to the brand using external data sources and APIs based on the brand name received from the device. Specifically, it sends a request to an external API (e.g., Twitter API, Google News API) using the brand name as a query, and collects information about the brand in JSON format.

[0571] 5. Brand Data Analysis:

[0572] The server uses a generative AI model to calculate brand awareness, recognition, and reputation based on the collected brand data. For example, the server calculates scores for "Brand A" such as awareness of 0.85, recognition of 0.78, and reputation of 0.92.

[0573] 6. Emotional Data Analysis:

[0574] The server uses an emotion engine to recognize and analyze emotions from user input. It evaluates whether the user has positive emotions about the brand. For example, it extracts "positive" emotion from the user input.

[0575] 7. Returning analysis results and emotion data:

[0576] The server sends the analyzed findings and sentiment data back to the user's device in real time in JSON format, where the user can view the results and get detailed brand insights and sentiment information about the target audience.

[0577] 8. Dynamic Pricing:

[0578] The server performs dynamic pricing when the user selects the level of detail and depth of the investigation. It calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the price for rank 3 as 3,000 yen and presents it to the user.

[0579] Examples:

[0580] If a user wants to research "BrandA", the system works as follows:

[0581] 1. The user enters "BrandA" in the browser and clicks the submit button.

[0582] 2. After receiving the brand name, the server uses the generative AI model to collect and analyze data about "BrandA."

[0583] 3. The server uses the emotion engine to recognize and analyze emotion data from the user's input.

[0584] 4. The server returns numerical data such as popularity 0.85, recognition 0.78, and reputation 0.92 to the user, as well as emotional data of "positive."

[0585] 5. If the user requests an additional detailed investigation of rank 3, the server calculates a price of 3,000 yen and presents it to the user.

[0586] Examples of prompts for generative AI models:

[0587] Calculate the familiarity, recognition, and reputation scores for brand "BrandA," and also rate the positivity of users based on their sentiment data.

[0588] In this way, the specific actions of the server, terminal and user make this system a useful tool for companies to gain detailed insights about their brand.

[0589] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0590] Step 1:

[0591] When the program starts, the server loads a pre-trained generative AI model and emotion engine, which prepares the system for analyzing brand data. The input is the configuration data for the generative AI model and emotion engine, and the output is a system ready for analysis.

[0592] Step 2:

[0593] The user opens a browser on their device and accesses the web application. They enter the name of the brand they want to survey and click the submit button. For example, they enter "BrandA." The input is a string of the brand name, and the output is JSON-formatted data sent from the device to the server.

[0594] Step 3:

[0595] The terminal sends the brand name entered by the user to the server in JSON format. The data is sent securely using the HTTPS protocol. The input is the brand name entered by the user, and the output is the request data sent to the server.

[0596] Step 4:

[0597] The server retrieves brand-related information using external data sources and APIs based on the brand name received from the device. Specifically, it sends a request to an external API (e.g., Twitter API, Google News API) using the brand name as a query, and collects brand-related information in JSON format. The input is the brand name query, and the output is the collected brand-related information.

[0598] Step 5:

[0599] The server uses a generative AI model based on the collected brand data to calculate brand awareness, recognition, and reputation. For example, it calculates scores such as 0.85 for awareness, 0.78 for recognition, and 0.92 for reputation for "Brand A." The input is the collected brand data, and the output is the score for each brand evaluation indicator.

[0600] Step 6:

[0601] The server uses an emotion engine to recognize and analyze emotions from user input. It evaluates whether the user has positive emotions about the brand. For example, it extracts the "positive" emotion from the user's input. The input is the user's text input, and the output is the user's emotion data.

[0602] Step 7:

[0603] The server sends the analyzed findings and sentiment data in JSON format back to the user's device in real time. The user can view these results on their device and obtain detailed brand insights and sentiment information about the target audience. The input is the analysis results and sentiment data, and the output is real-time information provided to the user.

[0604] Step 8:

[0605] The server performs dynamic pricing when the user selects the level of detail and depth of the search. It calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the price for rank 3 as 3,000 yen and presents it to the user. The input is the rank selected by the user, and the output is the calculated price information.

[0606] Examples:

[0607] If a user wants to research "BrandA":

[0608] 1. The user enters "BrandA" in the browser and clicks the submit button.

[0609] 2. After receiving the brand name, the server uses the generative AI model to collect and analyze data about "BrandA."

[0610] 3. The server uses the emotion engine to recognize and analyze emotion data from the user's input.

[0611] 4. The server returns numerical data such as popularity 0.85, recognition 0.78, and reputation 0.92 to the user, as well as emotional data of "positive."

[0612] 5. If the user requests an additional detailed investigation of rank 3, the server calculates a price of 3,000 yen and presents it to the user.

[0613] (Application example 2)

[0614] 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."

[0615] Conventional advertising systems simply collect and analyze brand-related information, making it difficult to provide personalized advertising that takes into account user emotional data and real-time interactions. The present invention aims to solve this problem and provide more accurate advertising.

[0616] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing data related to brand names using a generative AI model, means for calculating brand awareness, recognition, and reputation based on the collected data, means for providing the calculated insights to users in real time, means for recognizing and analyzing the emotional state of users using an emotion engine, means for displaying personalized advertisements based on the user's emotional data and brand analysis results, and means for dynamic pricing according to demand. This enables personalized display of advertisements based on the user's emotional state and brand evaluation.

[0617] A "generative AI model" is a model that uses machine learning techniques to learn patterns in data relevant to a brand and is useful for data collection and analysis.

[0618] An "emotion engine" is a technology for recognizing and analyzing emotional states through user input and interaction.

[0619] "Name recognition" is an indicator that indicates how widely known a particular brand is.

[0620] "Awareness" is an evaluation indicator that indicates the depth of knowledge and understanding of a particular brand.

[0621] "Reputation" is an evaluation index that indicates the degree of evaluation and trust for a particular brand.

[0622] "Personalized advertising" is advertising that is customized based on a user's individual interests and emotional state.

[0623] "Dynamic pricing" is a method of flexibly changing prices based on demand and other conditions.

[0624] A "target audience" is a specific group of consumers targeted by advertising and marketing activities.

[0625] An "external data source" is a data provider used to obtain information from outside the system.

[0626] "API" stands for Application Program Interface, a set of rules and tools that allow different software systems to communicate with each other.

[0627] This invention relates to a system that uses generative AI models and emotion engines to collect and analyze brand-related data, provide real-time insights to users, and even display personalized advertisements based on user emotion data.

[0628] First, when the program starts up, the server loads a pre-trained generative AI model and emotion engine. The generative AI model uses machine learning techniques to learn patterns in data related to the brand, and the emotion engine is used to recognize and analyze the user's emotional state.

[0629] The user accesses the application on their device and enters the name of the brand they wish to research. For example, if they enter "Brand A" and click the submit button, the device will send the entered brand name to the server in JSON format. After receiving the brand name sent from the device, the server uses external data sources and APIs to obtain information related to the brand. In this case, a request is sent to the external API using the brand name as a query, and information about the brand is collected in JSON format.

[0630] Next, the server uses the generative AI model based on the acquired data to calculate the brand's name recognition, recognition, and reputation. Specifically, it analyzes information related to the brand name and calculates scores for each evaluation index. For example, it calculates the name recognition, recognition, and reputation scores for "Brand A."

[0631] In addition, the server also takes into account the user's emotional data, using an emotion engine to recognize and analyze emotions from the user's input. Through the text input and other interactions provided by the user, the emotion engine evaluates the user's emotional state. Based on this evaluation, emotion data can be obtained, such as "the user has positive emotions toward the brand."

[0632] The analyzed findings and sentiment data are sent back to the user's device in real time from the server. Users can view these results on their device and obtain detailed brand insights and sentiment information about their target audience. For example, in addition to numerical data such as awareness of 0.85, recognition of 0.78, and reputation of 0.92, the user's sentiment score is also provided.

[0633] Furthermore, the analysis results can be used to display personalized advertisements to users. These advertisements are selected based on the user's emotional state and brand evaluation data, so they can more effectively capture the user's attention. For example, an advertisement message such as "Check out the special sale on a highly rated brand!" can be displayed.

[0634] The hardware used includes servers and user devices (smartphones and PCs), and the software used includes generative AI models, emotion engines, and external APIs, allowing users to gain detailed insights about any brand and see personalized ads based on those insights.

[0635] As a concrete example, a user enters "Brand A" in a browser and clicks the submit button. The device sends the brand name to the server, which then uses external data sources and APIs to obtain information related to "Brand A." The server then uses a generative AI model to calculate scores for familiarity, recognition, and reputation. It also uses an emotion engine to obtain the user's emotional data and adds it to the analysis results. These results are then provided to the user in JSON format. If the user subsequently requests a survey at rank 3, the server sets the price for rank 3, calculating it to be 3,000 yen and presenting it to the user.

[0636] Example prompts for generative AI models:

[0637] "Please tell me about the name recognition, recognition, and reputation of Brand A."

[0638] Example prompts in the Emotion Engine:

[0639] I think this brand is high quality.

[0640] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0641] Step 1:

[0642] The server loads pre-trained generative AI models and emotion engines when the program starts. This loads the necessary models and engines into memory and makes them available for use. The input is the trained model and emotion engine data, and the output is the loaded model and engine.

[0643] Step 2:

[0644] The user accesses the application on their device and enters the brand name they wish to investigate. For example, they enter "Brand A" and click the submit button. This entered brand name is sent from the device to the server in JSON format. The input is the brand name entered by the user, and the output is brand name data in JSON format.

[0645] Step 3:

[0646] When the server receives the brand name sent from the device, it uses external data sources and APIs to obtain information related to the brand. At this time, it sends a request to the external API using the brand name as a query and collects information about the brand in JSON format. The input is brand name data in JSON format, and the output is brand information data in JSON format.

[0647] Step 4:

[0648] The server uses a generative AI model based on the acquired brand information data to calculate brand awareness, recognition, and reputation. Specifically, it analyzes various data related to the brand name and calculates scores for each evaluation indicator. The input is brand information data in JSON format, and the output is scores for awareness, recognition, and reputation.

[0649] Step 5:

[0650] The server also takes into account the user's emotional data, and therefore uses an emotion engine to recognize and analyze emotions from the user's input. Through text input and other interactions provided by the user, the emotion engine evaluates the user's emotional state. The input is the user's text input data, and the output is the analyzed emotional data.

[0651] Step 6:

[0652] The server transmits the analyzed findings and sentiment data to the user's device in real time, allowing the user to view the results on their device and obtain detailed brand insights and sentiment information. The inputs are recognition, awareness, and reputation scores and sentiment data, and the output is insights and sentiment information displayed on the user's device.

[0653] Step 7:

[0654] The server generates a personalized advertisement based on the analysis results and displays it to the user. The advertisement is selected based on the user's emotional state and brand evaluation data. The input is the emotional data and brand evaluation data, and the output is a personalized advertising message displayed on the user's device.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] [Third embodiment]

[0659] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0660] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0661] 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).

[0662] 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.

[0663] 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.

[0664] 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).

[0665] 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.

[0666] 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.

[0667] 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.

[0668] 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.

[0669] 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.

[0670] 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."

[0671] The present invention relates to a system for collecting and analyzing brand data using a generative AI model. An embodiment of this system is described below.

[0672] First, when the program launches, the server loads a pre-trained generative AI model, which uses machine learning techniques to learn patterns in data relevant to the brand.

[0673] The user accesses the web application through the browser on their device, enters the brand name they want to research, and clicks the submit button. The device then sends the entered brand name to the server. This brand name is sent in JSON format.

[0674] When the server receives the brand name sent from the device, it uses external data sources and APIs to obtain information related to the brand. This information includes brand awareness, recognition, reputation, etc. Specifically, the server sends a request to the external API using the brand name to obtain the required data. This data is obtained in JSON format.

[0675] Next, the server uses an AI model to calculate the brand's name recognition, recognition, and reputation based on the acquired data. For example, it calculates the name recognition, recognition, and reputation of "Brand A" as scores. These scores are calculated by the AI ​​model based on past data and are highly accurate.

[0676] The analyzed results are sent back to the user's device in real time from the server, where the user can view the results and gain detailed insights into the brand.

[0677] In addition, if the user selects the depth and detail of the search, the server performs dynamic pricing. This is a mechanism that calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the corresponding price (e.g., 3,000 yen) and presents it to the user.

[0678] As a concrete example, consider the case where a user wants to conduct a survey on "Brand A." The user enters "Brand A" in the browser and clicks the submit button. The device sends the brand name to the server, which then uses external data sources and APIs to obtain information related to "Brand A." The server uses an AI model to calculate scores such as 0.85 for name recognition, 0.78 for awareness, and 0.92 for reputation, and sends these back to the user. If the user then requests a survey on rank 3, the server calculates the price for rank 3 and presents it to the user.

[0679] In this way, the present invention becomes a useful tool for companies to carry out rapid and highly accurate market analysis and to formulate efficient marketing and sales strategies.

[0680] The processing flow will be explained below.

[0681] Step 1:

[0682] The server loads the pre-trained generative AI model when the program starts, deploying it in memory and making it available for subsequent data analysis.

[0683] Step 2:

[0684] A user accesses the web application using a browser on a device, enters the name of the brand for which the user wishes to conduct a survey, for example, "BrandA," and clicks the submit button.

[0685] Step 3:

[0686] The terminal sends the entered brand name in JSON format to the server, which then receives the brand name specified by the user.

[0687] Step 4:

[0688] The server reads the brand name received from the device and retrieves related data using an external API, by sending a request to the external API with the brand name as a query to collect information about the brand.

[0689] Step 5:

[0690] The server analyzes the data received from the external API and extracts the necessary information (such as popularity, recognition, and reputation). Based on this data, an AI model is used to calculate the scores for each evaluation index.

[0691] Step 6:

[0692] The server creates the calculated scores for popularity, recognition, and reputation in JSON format and sends them to the user's device in real time, allowing the user to check the results immediately.

[0693] Step 7:

[0694] Users can select a rank to specify the level of detail and depth of the investigation. For example, to select rank 3, select an option on the screen.

[0695] Step 8:

[0696] The terminal transmits the designated rank information to the server, which then sets prices based on the rank.

[0697] Step 9:

[0698] The server calculates the price corresponding to the specified rank and returns it to the user's terminal. For example, for rank 3, the price is calculated as 3,000 yen and presented to the user.

[0699] Step 10:

[0700] Develop appropriate marketing and sales strategies based on the analytics and pricing information you receive, and use this information to execute effective promotions to your target audience.

[0701] Example 1

[0702] 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."

[0703] There is a lack of methods to quickly and accurately analyze a brand's market situation and reputation, and to develop efficient marketing and sales strategies. There is also the issue of difficulty in setting dynamic pricing according to the depth and level of detail of the research.

[0704] 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.

[0705] In this invention, the server includes: means for loading a pre-trained generative AI model when the program is launched; means for a user to access the web application through a browser on the terminal and input and submit a brand name; means for the terminal to transmit the input brand name to the server in JSON format; means for the server to acquire data related to the brand using an external data source and an API; means for calculating the brand's name recognition, recognition, and reputation using the generative AI model based on the acquired data; means for returning the calculated score to the user's terminal in real time; and means for the server to perform dynamic pricing when the user selects the depth and level of detail of the research. This enables rapid and accurate analysis of the brand's market situation and reputation, the formulation of efficient marketing and sales strategies, and dynamic pricing according to the depth and level of detail of the research.

[0706] A "generative AI model" is a model trained using machine learning techniques to learn specific data patterns and make predictions or classifications.

[0707] A "server" is a device that has computing capabilities and sends and receives data over a network.

[0708] A "terminal" is a device operated by a user, and typically refers to a computer device such as a PC or smartphone.

[0709] A "browser" is software for viewing web pages and is used to obtain information via the Internet.

[0710] A "web application" is a program that runs on the Internet and is software that users can access and operate through a browser.

[0711] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format for structuring and sending and receiving data.

[0712] "External data sources" refers to data providing systems or databases that exist outside the server and are used to obtain information related to the brand.

[0713] "API" stands for Application Programming Interface, and is an interface for exchanging functions and data between software programs.

[0714] "Name recognition" is an indicator of how well known a particular brand is in the market and among consumers.

[0715] "Awareness" is an indicator of the degree to which a particular brand is recognized by consumers.

[0716] "Reputation" refers to the consumer and market evaluation and opinion of a particular brand.

[0717] "Dynamic pricing" is a system that changes prices depending on user choices and circumstances.

[0718] This invention relates to a system that uses a generative AI model to collect and analyze data related to a specific brand. This system operates among three parties: a server, a terminal, and a user. Detailed procedures and modes for implementing this invention are specifically described below.

[0719] Server Operation

[0720] When the program starts, the server first initializes and loads a pre-trained generative AI model. This AI model is trained using machine learning techniques based on past data and learns patterns related to brands. The required library is the Python TensorFlow library. The server loads the libraries and configuration files and loads the model into memory.

[0721] User operations

[0722] Users access the dedicated web application using their device's browser. Common web browsers such as Google Chrome and Mozilla Firefox can be used. The user enters the brand name they wish to research and clicks the submit button. This action activates JavaScript on the user's device, converting the brand name into JSON format.

[0723] Device behavior

[0724] The device sends the entered brand name to the server in JSON format. Network communication is performed using an HTTP POST request. For example, when a user searches for information about a brand called "BrandA," the device sends the following JSON data to the server:

[0725] json

[0726] {

[0727] "brand_name": "BrandA"

[0728] }

[0729] Data acquisition and analysis by the server

[0730] The server parses the JSON data received from the device and retrieves brand-related information using external data sources and APIs. Common external data sources include Google Trends, Twitter API, Brandwatch, etc. Using the Python Requests library, the server accesses these external APIs and retrieves brand-related data.

[0731] Based on the acquired information, the server uses a generative AI model to calculate brand awareness, recognition, and reputation scores. For example, "Brand A" might have a recognition score of 0.85, a recognition score of 0.78, and a reputation score of 0.92. These scores are then converted back to JSON format and sent back to the user's device in real time.

[0732] User review of results and request further investigation

[0733] The user checks the analysis results on their device. For example, the score for "Brand A" is displayed. If they want to conduct a more detailed investigation, they select the depth and level of detail of the investigation and send the request again. This request is also sent to the server in JSON format.

[0734] Server-driven dynamic pricing

[0735] The server receives a request for additional research from the user and dynamically sets the price according to the specified rank. For example, if a user requests a research of rank 3, the server calculates the price corresponding to rank 3 (e.g., 3,000 yen) and presents it to the user. The specific pricing algorithm is based on the user's selection and the settings in the server.

[0736] Examples of concrete examples and prompts

[0737] For example, if a user wants to research brand information for "Brand A," they enter "Brand A" into the browser's input form and click the submit button. The server uses external data sources and APIs to collect information related to "Brand A," and calculates the recognition, awareness, and reputation scores using a generative AI model. These scores can be viewed in real time. If a user requests more detailed research, a price will be displayed according to the desired ranking.

[0738] Example prompt sentence:

[0739] To research brand information for "Brand A," enter the brand name in the browser's input form and click the submit button. The server uses external data sources and APIs to collect information related to "Brand A," and uses a generative AI model to calculate scores for name recognition, awareness, and reputation. You can view the results in real time. If you would like a more detailed investigation, a price will be displayed based on your desired rank.

[0740] As described above, this invention is a useful tool for companies to conduct rapid and accurate market analysis and formulate efficient marketing and sales strategies. Furthermore, by using a generative AI model, it can provide highly accurate results.

[0741] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0742] Step 1:

[0743] The server launches the program and loads the generative AI model. Specifically, the server uses Python's TensorFlow library to load the trained generative AI model into memory, and the server is then ready to analyze data related to the brand.

[0744] Input: Server start command

[0745] Output: Generative AI model loaded in memory

[0746] Step 2:

[0747] A user accesses a web application using a browser on their device. They enter a brand name in the browser's input form and click the submit button. For example, the user enters "BrandA."

[0748] Input: Brand name (e.g. "BrandA")

[0749] Output: Submit button click event

[0750] Step 3:

[0751] The device receives the click event of the submit button, converts the brand name entered by the user into JSON format, constructs the brand name as a JSON object using JavaScript, and then sends this JSON data to the server using an HTTP POST request.

[0752] Input: Submit button click event from browser

[0753] Output: Brand information in JSON format (e.g. "{'brand_name': 'BrandA'}")

[0754] Step 4:

[0755] The server parses the JSON data received from the device, extracts the brand name, and then calls an external data source API to retrieve information related to the specified brand. It uses the Python Requests library to collect data from external APIs, such as Google Trends, Twitter API, and Brandwatch.

[0756] Input: Brand information in JSON format (e.g. "{'brand_name': 'BrandA'}")

[0757] Output: Brand information retrieved from an external data source

[0758] Step 5:

[0759] The server inputs the acquired data into a generative AI model to calculate brand awareness, recognition, and reputation. The analyzed data is converted into a new JSON format and an evaluation score is calculated. For example, specific values ​​such as awareness of 0.85, recognition of 0.78, and reputation of 0.92 are output.

[0760] Input: Brand information retrieved from an external data source

[0761] Output: Prominence, awareness, and reputation scores (e.g., "{'brand_name': 'BrandA', 'Prominence': 0.85, 'Awareness': 0.78, 'Reputation': 0.92}")

[0762] Step 6:

[0763] The server converts the calculated score back into JSON format and sends it back to the user's device in real time over the network. The user's device receives this JSON data, parses it using JavaScript, and displays the analysis results in the browser.

[0764] Input: Prominence, awareness, and reputation scores (e.g., "{'brand_name': 'BrandA', 'Prominence': 0.85, 'Awareness': 0.78, 'Reputation': 0.92}")

[0765] Output: Analysis result JSON data returned to the user's device

[0766] Step 7:

[0767] If the user checks the analysis results on the device and wishes to conduct a more detailed investigation, they can select the depth and level of detail of the investigation and send the request again. The detailed investigation request is also sent to the server in JSON format.

[0768] Input: JSON format analysis results and user's detailed investigation request (e.g., "{'brand_name': 'BrandA', 'Request Detail': 'Rank 3'}")

[0769] Output: Detailed survey request JSON data sent to the server

[0770] Step 8:

[0771] The server receives detailed survey requests from users and dynamically sets prices according to the specified rank. For example, if a survey with rank 3 is requested, the server calculates the price corresponding to rank 3 (e.g., 3,000 yen) and presents it to the user. Prices are dynamically set using a Python calculation algorithm.

[0772] Input: User's detailed survey request JSON data

[0773] Output: Dynamically set price information (e.g., "{'brand_name': 'BrandA', 'Price for Rank 3': 3000}")

[0774] (Application example 1)

[0775] 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."

[0776] Traditional brand data collection and analysis systems struggled to accurately predict the effectiveness of advertising campaigns and provide detailed insights for formulating optimal strategies for target audiences. Furthermore, they lacked the ability for users to dynamically set prices based on demand, limiting the ability to develop flexible marketing strategies. This resulted in issues that reduced the effectiveness and cost-effectiveness of advertising campaigns.

[0777] 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.

[0778] In this invention, the server includes means for collecting and analyzing data related to brand names using a generative AI model, means for calculating brand awareness, recognition, and reputation based on the collected data, means for providing the calculated insights to users in real time, means for providing effectiveness predictions based on the target demographic and budget of the advertising campaign, and means for dynamic pricing according to demand. This enables rapid and accurate understanding of market conditions in advertising campaigns, enabling the formulation of effective marketing strategies and achieving high cost efficiency.

[0779] A "generative AI model" is an algorithm trained using machine learning techniques that has the ability to identify and analyze specific data patterns.

[0780] "Data related to a brand name" refers to information about a specific brand, including a wide range of data such as name recognition, awareness, and reputation.

[0781] "Brand awareness" refers to an indicator that shows how well a particular brand is recognized in the market and among consumers.

[0782] "Brand awareness" refers to an indicator that shows the degree of identifiable knowledge and image that consumers have of a particular brand.

[0783] "Brand reputation" refers to an indicator that shows the degree of evaluation and trustworthiness of a particular brand among consumers and the market.

[0784] A "target audience" is a group of consumers that is specifically targeted by advertising or marketing efforts.

[0785] "Advertising campaign effectiveness forecasting" refers to a prediction that evaluates in advance the impact and results of a specific advertising activity on the target audience.

[0786] "Dynamic pricing" refers to the practice of adjusting prices in real time based on demand and market conditions.

[0787] This invention relates to a system for collecting and analyzing data related to brand names using a generative AI model. This system uses a cloud server, user terminals, and external APIs to quickly and accurately predict the effectiveness of advertising campaigns. An embodiment of this system is described below in detail.

[0788] System Configuration

[0789] The server uses a pre-trained generative AI model to collect and analyze data related to the brand name entered by the user. Specifically, the server uses a cloud server (e.g., AWS EC2) to load the generative AI model (e.g., GPT-4) and perform analysis.

[0790] User Interface

[0791] The user inputs the brand name using a mobile application (using React Native for example) on their smartphone. When the user inputs the brand name and submits it, the data is sent to the server in JSON format.

[0792] Data collection

[0793] The server uses external data sources and APIs (e.g., Twitter API, Google Trends API) to obtain information related to the brand name, including brand awareness, recognition, reputation, etc. The server sends an API request and receives the results in JSON format.

[0794] Data analysis

[0795] The server uses the generative AI model to calculate brand awareness, recognition, and reputation based on the received data. For example, it generates scores such as 0.85 for brand awareness, 0.78 for recognition, and 0.92 for reputation. The calculation results are returned to the user in real time in JSON format.

[0796] Effect prediction

[0797] Additionally, the server provides forecasts based on the target audience and budget of the ad campaign, including the impact on the target audience and return on investment. Users can use these insights to plan effective ad campaigns.

[0798] Dynamic Pricing

[0799] If the user requests a detailed analysis, the server will dynamically set prices for each rank. For example, if the user selects rank 3, the server will calculate and present a specific price, such as 3,000 yen.

[0800] Specific examples

[0801] As a specific use case, consider a situation where a marketing professional at an advertising agency wants to predict the effectiveness of a new advertising campaign for "Brand A." The user opens the smartphone application and enters the following prompt:

[0802] "I would like to predict the effectiveness of Brand A's advertising campaign. I would like you to analyze the scores of name recognition, awareness, and reputation, and then predict and present the effectiveness for the target demographic."

[0803] As a result, the server calculates a brand awareness score of 0.85, an awareness score of 0.78, and a reputation score of 0.92 for "Brand A," and returns these to the user in real time. The server also provides detailed advertising effectiveness predictions and dynamic pricing, allowing users to create highly accurate marketing strategies.

[0804] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0805] Step 1:

[0806] The user opens the mobile application on their smartphone, enters the brand name and a prompt message related to the advertising campaign in the application's input fields, and clicks the submit button. At this time, the entered brand name and prompt message are sent from the device to the server in JSON format.

[0807] Step 2:

[0808] The server parses the received JSON data, extracts the brand name and prompt, and sends a request to external data sources and APIs (e.g., Twitter API, Google Trends API) that includes the brand name and collects related data.

[0809] Step 3:

[0810] The data received from the external API is stored in JSON format on the server. The server then uses a generative AI model based on this collected data to calculate brand awareness, recognition, and reputation. For example, a generative AI model (GPT-4) performs pattern recognition based on past data. Specifically, the following values ​​are calculated: awareness score 0.85, recognition score 0.78, and reputation score 0.92.

[0811] Step 4:

[0812] The server then organizes the calculation results in JSON format and sends them back to the user's smartphone in real time, where the user can view the results, including the insight information.

[0813] Step 5:

[0814] If a user wants more detailed analysis or a prediction of the effectiveness of their advertising campaign, they select a rank for detailed analysis. The server will dynamically set a price based on the selected rank. This price is calculated based on a pre-set fee structure, and a specific price such as 3,000 yen is set for rank 3.

[0815] Step 6:

[0816] This dynamic pricing information is presented to users, who can then review it and access detailed analytics and performance forecasts, providing specific insights into their ad campaigns based on their target demographic and budget.

[0817] Step 7:

[0818] All processing results are displayed on the user's smartphone, ultimately enabling the user to create highly accurate marketing strategies based on detailed data.

[0819] 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.

[0820] This invention relates to a system that uses a generative AI model and an emotion engine to collect and analyze brand data and provide insights to users in real time. An embodiment of this system is described below.

[0821] First, when the program starts, the server loads a pre-trained generative AI model and emotion engine. The model uses machine learning techniques to learn patterns in data related to the brand, and the emotion engine is used to recognize and analyze user emotions.

[0822] The user accesses the web application through the browser on their device, enters the brand name they wish to survey, for example, "BrandA," and clicks the submit button. The device then sends the entered brand name in JSON format to the server.

[0823] When the server receives the brand name sent from the device, it uses external data sources and APIs to obtain information related to the brand. At this time, it sends a request to the external API using the brand name as a query and collects information about the brand in JSON format.

[0824] Next, the server uses the generative AI model to calculate the brand's name recognition, recognition, and reputation based on the acquired data. Specifically, it analyzes information related to the brand name and calculates scores for each evaluation index. For example, it calculates the name recognition, recognition, and reputation scores for "Brand A."

[0825] Additionally, to take user emotional data into account, an emotion engine is used to recognize and analyze emotions from user input. Through text input and other interactions provided by the user, the emotion engine evaluates the user's emotional state. This can yield emotional data such as "the user has positive feelings toward the brand."

[0826] The analyzed findings and sentiment data are sent back to the user's device in real time from the server. Users can view these results on their device and obtain detailed brand insights and sentiment information about their target audience. For example, in addition to numerical data such as awareness of 0.85, recognition of 0.78, and reputation of 0.92, the user's sentiment score is also provided.

[0827] In addition, if the user selects the level of detail or depth of the search, the server performs dynamic pricing. It calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the price based on rank 3 (e.g., 3,000 yen) and presents it to the user.

[0828] As a concrete example, if a user wants to conduct a survey on "Brand A," the user enters "Brand A" in the browser and clicks the submit button. The device sends the brand name to the server, which then uses external data sources and APIs to obtain information related to "Brand A." The server then uses a generative AI model to calculate scores for name recognition, awareness, and reputation. It also uses an emotion engine to obtain the user's emotional data and adds it to the analysis results. These results are then provided to the user in JSON format. If the user then requests a survey at rank 3, the server sets the price for rank 3, calculating it to be 3,000 yen and presenting it to the user.

[0829] In this way, the invention will enable businesses to gain detailed insights into their brands quickly and with high accuracy, and will be a useful tool for developing more meaningful marketing and sales strategies that incorporate user sentiment data.

[0830] The processing flow will be explained below.

[0831] Step 1:

[0832] When the program starts, the server loads the pre-trained generative AI model and emotion engine, deploying them in memory and making them available for subsequent data collection and analysis.

[0833] Step 2:

[0834] A user accesses the web application using a browser on a device, enters the name of the brand for which the user wishes to conduct a survey, for example, "BrandA," and clicks the submit button.

[0835] Step 3:

[0836] The terminal sends the entered brand name in JSON format to the server, which then receives the brand name specified by the user.

[0837] Step 4:

[0838] The server reads the brand name received from the device and retrieves related data using an external API, by sending a request to the external API with the brand name as a query to collect information about the brand.

[0839] Step 5:

[0840] The server analyzes the data received from the external API and extracts the necessary information (e.g., popularity, recognition, reputation). Based on this data, a generative AI model is used to calculate the scores for each evaluation index.

[0841] Step 6:

[0842] The server uses an emotion engine to obtain emotion data based on user input and interactions, including emotion recognition from user text input and other interactions.

[0843] Step 7:

[0844] The server combines the calculated popularity, recognition, and reputation scores with user sentiment data to generate a comprehensive analysis that provides detailed insights, including sentiment scores.

[0845] Step 8:

[0846] The server creates the analysis results in JSON format and sends them back to the user's device in real time, allowing the user to check the results immediately.

[0847] Step 9:

[0848] Users can further specify the level of detail and depth of the investigation by selecting a rank. For example, to select rank 3, select the appropriate option on the screen.

[0849] Step 10:

[0850] The terminal transmits the designated rank information to the server, which then receives a request for detailed investigation based on the rank.

[0851] Step 11:

[0852] The server calculates the price based on the specified rank and returns it to the user's terminal. For example, it calculates the price corresponding to rank 3 (e.g., 3,000 yen) and presents it to the user.

[0853] Step 12:

[0854] Develop appropriate marketing and sales strategies based on the analytics and pricing information you receive, and use this information to effectively promote your products to your target audience.

[0855] This series of processes allows companies to quickly gain highly accurate insights about their brand, and by incorporating emotional data, they can improve the accuracy of their marketing strategies.

[0856] Example 2

[0857] 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."

[0858] In modern marketing and brand management, it is extremely important to quickly and accurately obtain detailed brand-related insights and user sentiment data. However, conventional systems have struggled to objectively measure brand awareness, recognition, and reputation, or analyze user sentiment data in real time. This has left companies struggling to obtain sufficient information when formulating effective marketing strategies for their target audiences.

[0859] 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.

[0860] In this invention, the server includes means for collecting and analyzing data related to brand names using a generative AI model, means for recognizing and analyzing user emotions using an emotion engine, means for calculating brand awareness, recognition, and reputation based on the collected data, means for providing analyzed insights and emotion data to users in real time, and means for dynamic pricing according to demand, thereby enabling companies to quickly and accurately obtain detailed insights about their brands and emotion data of their target audiences.

[0861] A "generative AI model" is a machine learning model that learns, collects, and analyzes patterns in data related to brand names.

[0862] The "emotion engine" is a software component that recognizes and analyzes a user's emotions based on the user's text input and interactions.

[0863] "Brand awareness" is an evaluation indicator that indicates how widely a brand is recognized.

[0864] "Brand awareness" is an evaluation index that indicates the degree to which consumers or users recognize a particular brand and understand its characteristics.

[0865] "Brand reputation" is a score that indicates the evaluation and trust that consumers and users have of a brand.

[0866] "Means of providing in real time" refers to a method of instantly returning and providing analyzed data and knowledge to users.

[0867] "Dynamic pricing" is a method of varying prices depending on the level of detail and depth of research selected by the user.

[0868] "External Data Sources" refers to various sources on the Internet that provide information related to the brand.

[0869] "API" stands for Application Program Interface and refers to a mechanism that enables data communication between different software programs.

[0870] This invention relates to a system that uses a generative AI model and an emotion engine to collect and analyze brand data and provide insights to users in real time. An embodiment of this system is described below.

[0871] Hardware and Software Use:

[0872] Server: Collects and analyzes data, runs generative AI models and emotion engines.

[0873] User terminal: Uses a browser to receive input from the user.

[0874] Browser: Use any web browser (e.g., Google Chrome, Mozilla Firefox).

[0875] Generative AI models: Use machine learning models such as OpenAI GPT-4.

[0876] Sentiment Engine: Uses the Sentiment Analysis API (e.g., Google Cloud Natural Language API).

[0877] External data sources and APIs: Providing information relevant to your brand (e.g., Twitter API, Google News API).

[0878] Specific operation steps:

[0879] 1. Start the program:

[0880] When the program starts, the server loads a pre-trained generative AI model and an emotion engine. The generative AI model learns patterns in data related to the brand, and the emotion engine recognizes and analyzes user emotions.

[0881] 2. Enter your brand name:

[0882] The user opens a browser on their device and accesses the web application. The user enters the name of the brand they wish to survey. For example, they enter "BrandA" and clicks the submit button.

[0883] 3. Submit your brand name:

[0884] The device sends the brand name entered by the user in JSON format to the server, securely transmitting the data using the HTTPS protocol.

[0885] 4. Brand Data Collection:

[0886] The server retrieves information related to the brand using external data sources and APIs based on the brand name received from the device. Specifically, it sends a request to an external API (e.g., Twitter API, Google News API) using the brand name as a query, and collects information about the brand in JSON format.

[0887] 5. Brand Data Analysis:

[0888] The server uses a generative AI model to calculate brand awareness, recognition, and reputation based on the collected brand data. For example, the server calculates scores for "Brand A" such as awareness of 0.85, recognition of 0.78, and reputation of 0.92.

[0889] 6. Emotional Data Analysis:

[0890] The server uses an emotion engine to recognize and analyze emotions from user input. It evaluates whether the user has positive emotions about the brand. For example, it extracts "positive" emotion from the user input.

[0891] 7. Returning analysis results and emotion data:

[0892] The server sends the analyzed findings and sentiment data back to the user's device in real time in JSON format, where the user can view the results and get detailed brand insights and sentiment information about the target audience.

[0893] 8. Dynamic Pricing:

[0894] The server performs dynamic pricing when the user selects the level of detail and depth of the investigation. It calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the price for rank 3 as 3,000 yen and presents it to the user.

[0895] Examples:

[0896] If a user wants to research "BrandA", the system works as follows:

[0897] 1. The user enters "BrandA" in the browser and clicks the submit button.

[0898] 2. After receiving the brand name, the server uses the generative AI model to collect and analyze data about "BrandA."

[0899] 3. The server uses the emotion engine to recognize and analyze emotion data from the user's input.

[0900] 4. The server returns numerical data such as popularity 0.85, recognition 0.78, and reputation 0.92 to the user, as well as emotional data of "positive."

[0901] 5. If the user requests an additional detailed investigation of rank 3, the server calculates a price of 3,000 yen and presents it to the user.

[0902] Examples of prompts for generative AI models:

[0903] Calculate the familiarity, recognition, and reputation scores for brand "BrandA," and also rate the positivity of users based on their sentiment data.

[0904] In this way, the specific actions of the server, terminal and user make this system a useful tool for companies to gain detailed insights about their brand.

[0905] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0906] Step 1:

[0907] When the program starts, the server loads a pre-trained generative AI model and emotion engine, which prepares the system for analyzing brand data. The input is the configuration data for the generative AI model and emotion engine, and the output is a system ready for analysis.

[0908] Step 2:

[0909] The user opens a browser on their device and accesses the web application. They enter the name of the brand they want to survey and click the submit button. For example, they enter "BrandA." The input is a string of the brand name, and the output is JSON-formatted data sent from the device to the server.

[0910] Step 3:

[0911] The terminal sends the brand name entered by the user to the server in JSON format. The data is sent securely using the HTTPS protocol. The input is the brand name entered by the user, and the output is the request data sent to the server.

[0912] Step 4:

[0913] The server retrieves brand-related information using external data sources and APIs based on the brand name received from the device. Specifically, it sends a request to an external API (e.g., Twitter API, Google News API) using the brand name as a query, and collects brand-related information in JSON format. The input is the brand name query, and the output is the collected brand-related information.

[0914] Step 5:

[0915] The server uses a generative AI model based on the collected brand data to calculate brand awareness, recognition, and reputation. For example, it calculates scores such as 0.85 for awareness, 0.78 for recognition, and 0.92 for reputation for "Brand A." The input is the collected brand data, and the output is the score for each brand evaluation indicator.

[0916] Step 6:

[0917] The server uses an emotion engine to recognize and analyze emotions from user input. It evaluates whether the user has positive emotions about the brand. For example, it extracts the "positive" emotion from the user's input. The input is the user's text input, and the output is the user's emotion data.

[0918] Step 7:

[0919] The server sends the analyzed findings and sentiment data in JSON format back to the user's device in real time. The user can view these results on their device and obtain detailed brand insights and sentiment information about the target audience. The input is the analysis results and sentiment data, and the output is real-time information provided to the user.

[0920] Step 8:

[0921] The server performs dynamic pricing when the user selects the level of detail and depth of the search. It calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the price for rank 3 as 3,000 yen and presents it to the user. The input is the rank selected by the user, and the output is the calculated price information.

[0922] Examples:

[0923] If a user wants to research "BrandA":

[0924] 1. The user enters "BrandA" in the browser and clicks the submit button.

[0925] 2. After receiving the brand name, the server uses the generative AI model to collect and analyze data about "BrandA."

[0926] 3. The server uses the emotion engine to recognize and analyze emotion data from the user's input.

[0927] 4. The server returns numerical data such as popularity 0.85, recognition 0.78, and reputation 0.92 to the user, as well as emotional data of "positive."

[0928] 5. If the user requests an additional detailed investigation of rank 3, the server calculates a price of 3,000 yen and presents it to the user.

[0929] (Application example 2)

[0930] 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."

[0931] Conventional advertising systems simply collect and analyze brand-related information, making it difficult to provide personalized advertising that takes into account user emotional data and real-time interactions. The present invention aims to solve this problem and provide more accurate advertising.

[0932] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing data related to brand names using a generative AI model, means for calculating brand awareness, recognition, and reputation based on the collected data, means for providing the calculated insights to users in real time, means for recognizing and analyzing the emotional state of users using an emotion engine, means for displaying personalized advertisements based on the user's emotional data and brand analysis results, and means for dynamic pricing according to demand. This enables personalized display of advertisements based on the user's emotional state and brand evaluation.

[0933] A "generative AI model" is a model that uses machine learning techniques to learn patterns in data relevant to a brand and is useful for data collection and analysis.

[0934] An "emotion engine" is a technology for recognizing and analyzing emotional states through user input and interaction.

[0935] "Name recognition" is an indicator that indicates how widely known a particular brand is.

[0936] "Awareness" is an evaluation indicator that indicates the depth of knowledge and understanding of a particular brand.

[0937] "Reputation" is an evaluation index that indicates the degree of evaluation and trust for a particular brand.

[0938] "Personalized advertising" is advertising that is customized based on a user's individual interests and emotional state.

[0939] "Dynamic pricing" is a method of flexibly changing prices based on demand and other conditions.

[0940] A "target audience" is a specific group of consumers targeted by advertising and marketing activities.

[0941] An "external data source" is a data provider used to obtain information from outside the system.

[0942] "API" stands for Application Program Interface, a set of rules and tools that allow different software systems to communicate with each other.

[0943] This invention relates to a system that uses generative AI models and emotion engines to collect and analyze brand-related data, provide real-time insights to users, and even display personalized advertisements based on user emotion data.

[0944] First, when the program starts up, the server loads a pre-trained generative AI model and emotion engine. The generative AI model uses machine learning techniques to learn patterns in data related to the brand, and the emotion engine is used to recognize and analyze the user's emotional state.

[0945] The user accesses the application on their device and enters the name of the brand they wish to research. For example, if they enter "Brand A" and click the submit button, the device will send the entered brand name to the server in JSON format. After receiving the brand name sent from the device, the server uses external data sources and APIs to obtain information related to the brand. In this case, a request is sent to the external API using the brand name as a query, and information about the brand is collected in JSON format.

[0946] Next, the server uses the generative AI model based on the acquired data to calculate the brand's name recognition, recognition, and reputation. Specifically, it analyzes information related to the brand name and calculates scores for each evaluation index. For example, it calculates the name recognition, recognition, and reputation scores for "Brand A."

[0947] In addition, the server also takes into account the user's emotional data, using an emotion engine to recognize and analyze emotions from the user's input. Through the text input and other interactions provided by the user, the emotion engine evaluates the user's emotional state. Based on this evaluation, emotion data can be obtained, such as "the user has positive emotions toward the brand."

[0948] The analyzed findings and sentiment data are sent back to the user's device in real time from the server. Users can view these results on their device and obtain detailed brand insights and sentiment information about their target audience. For example, in addition to numerical data such as awareness of 0.85, recognition of 0.78, and reputation of 0.92, the user's sentiment score is also provided.

[0949] Furthermore, the analysis results can be used to display personalized advertisements to users. These advertisements are selected based on the user's emotional state and brand evaluation data, so they can more effectively capture the user's attention. For example, an advertisement message such as "Check out the special sale on a highly rated brand!" can be displayed.

[0950] The hardware used includes servers and user devices (smartphones and PCs), and the software used includes generative AI models, emotion engines, and external APIs, allowing users to gain detailed insights about any brand and see personalized ads based on those insights.

[0951] As a concrete example, a user enters "Brand A" in a browser and clicks the submit button. The device sends the brand name to the server, which then uses external data sources and APIs to obtain information related to "Brand A." The server then uses a generative AI model to calculate scores for familiarity, recognition, and reputation. It also uses an emotion engine to obtain the user's emotional data and adds it to the analysis results. These results are then provided to the user in JSON format. If the user subsequently requests a survey at rank 3, the server sets the price for rank 3, calculating it to be 3,000 yen and presenting it to the user.

[0952] Example prompts for generative AI models:

[0953] "Please tell me about the name recognition, recognition, and reputation of Brand A."

[0954] Example prompts in the Emotion Engine:

[0955] I think this brand is high quality.

[0956] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0957] Step 1:

[0958] The server loads pre-trained generative AI models and emotion engines when the program starts. This loads the necessary models and engines into memory and makes them available for use. The input is the trained model and emotion engine data, and the output is the loaded model and engine.

[0959] Step 2:

[0960] The user accesses the application on their device and enters the brand name they wish to investigate. For example, they enter "Brand A" and click the submit button. This entered brand name is sent from the device to the server in JSON format. The input is the brand name entered by the user, and the output is brand name data in JSON format.

[0961] Step 3:

[0962] When the server receives the brand name sent from the device, it uses external data sources and APIs to obtain information related to the brand. At this time, it sends a request to the external API using the brand name as a query and collects information about the brand in JSON format. The input is brand name data in JSON format, and the output is brand information data in JSON format.

[0963] Step 4:

[0964] The server uses a generative AI model based on the acquired brand information data to calculate brand awareness, recognition, and reputation. Specifically, it analyzes various data related to the brand name and calculates scores for each evaluation indicator. The input is brand information data in JSON format, and the output is scores for awareness, recognition, and reputation.

[0965] Step 5:

[0966] The server also takes into account the user's emotional data, and therefore uses an emotion engine to recognize and analyze emotions from the user's input. Through text input and other interactions provided by the user, the emotion engine evaluates the user's emotional state. The input is the user's text input data, and the output is the analyzed emotional data.

[0967] Step 6:

[0968] The server transmits the analyzed findings and sentiment data to the user's device in real time, allowing the user to view the results on their device and obtain detailed brand insights and sentiment information. The inputs are recognition, awareness, and reputation scores and sentiment data, and the output is insights and sentiment information displayed on the user's device.

[0969] Step 7:

[0970] The server generates a personalized advertisement based on the analysis results and displays it to the user. The advertisement is selected based on the user's emotional state and brand evaluation data. The input is the emotional data and brand evaluation data, and the output is a personalized advertising message displayed on the user's device.

[0971] 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.

[0972] 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.

[0973] 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.

[0974] [Fourth embodiment]

[0975] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0976] 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.

[0977] 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).

[0978] 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.

[0979] 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.

[0980] 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).

[0981] 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.

[0982] 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.

[0983] 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.

[0984] 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.

[0985] 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.

[0986] 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.

[0987] 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."

[0988] The present invention relates to a system for collecting and analyzing brand data using a generative AI model. An embodiment of this system is described below.

[0989] First, when the program launches, the server loads a pre-trained generative AI model, which uses machine learning techniques to learn patterns in data relevant to the brand.

[0990] The user accesses the web application through the browser on their device, enters the brand name they want to research, and clicks the submit button. The device then sends the entered brand name to the server. This brand name is sent in JSON format.

[0991] When the server receives the brand name sent from the device, it uses external data sources and APIs to obtain information related to the brand. This information includes brand awareness, recognition, reputation, etc. Specifically, the server sends a request to the external API using the brand name to obtain the required data. This data is obtained in JSON format.

[0992] Next, the server uses an AI model to calculate the brand's name recognition, recognition, and reputation based on the acquired data. For example, it calculates the name recognition, recognition, and reputation of "Brand A" as scores. These scores are calculated by the AI ​​model based on past data and are highly accurate.

[0993] The analyzed results are sent back to the user's device in real time from the server, where the user can view the results and gain detailed insights into the brand.

[0994] In addition, if the user selects the depth and detail of the search, the server performs dynamic pricing. This is a mechanism that calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the corresponding price (e.g., 3,000 yen) and presents it to the user.

[0995] As a concrete example, consider the case where a user wants to conduct a survey on "Brand A." The user enters "Brand A" in the browser and clicks the submit button. The device sends the brand name to the server, which then uses external data sources and APIs to obtain information related to "Brand A." The server uses an AI model to calculate scores such as 0.85 for name recognition, 0.78 for awareness, and 0.92 for reputation, and sends these back to the user. If the user then requests a survey on rank 3, the server calculates the price for rank 3 and presents it to the user.

[0996] In this way, the present invention becomes a useful tool for companies to carry out rapid and highly accurate market analysis and to formulate efficient marketing and sales strategies.

[0997] The processing flow will be explained below.

[0998] Step 1:

[0999] The server loads the pre-trained generative AI model when the program starts, deploying it in memory and making it available for subsequent data analysis.

[1000] Step 2:

[1001] A user accesses the web application using a browser on a device, enters the name of the brand for which the user wishes to conduct a survey, for example, "BrandA," and clicks the submit button.

[1002] Step 3:

[1003] The terminal sends the entered brand name in JSON format to the server, which then receives the brand name specified by the user.

[1004] Step 4:

[1005] The server reads the brand name received from the device and retrieves related data using an external API, by sending a request to the external API with the brand name as a query to collect information about the brand.

[1006] Step 5:

[1007] The server analyzes the data received from the external API and extracts the necessary information (such as popularity, recognition, and reputation). Based on this data, an AI model is used to calculate the scores for each evaluation index.

[1008] Step 6:

[1009] The server creates the calculated scores for popularity, recognition, and reputation in JSON format and sends them to the user's device in real time, allowing the user to check the results immediately.

[1010] Step 7:

[1011] Users can select a rank to specify the level of detail and depth of the investigation. For example, to select rank 3, select an option on the screen.

[1012] Step 8:

[1013] The terminal transmits the designated rank information to the server, which then sets prices based on the rank.

[1014] Step 9:

[1015] The server calculates the price corresponding to the specified rank and returns it to the user's terminal. For example, for rank 3, the price is calculated as 3,000 yen and presented to the user.

[1016] Step 10:

[1017] Develop appropriate marketing and sales strategies based on the analytics and pricing information you receive, and use this information to execute effective promotions to your target audience.

[1018] Example 1

[1019] 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."

[1020] There is a lack of methods to quickly and accurately analyze a brand's market situation and reputation, and to develop efficient marketing and sales strategies. There is also the issue of difficulty in setting dynamic pricing according to the depth and level of detail of the research.

[1021] 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.

[1022] In this invention, the server includes: means for loading a pre-trained generative AI model when the program is launched; means for a user to access the web application through a browser on the terminal and input and submit a brand name; means for the terminal to transmit the input brand name to the server in JSON format; means for the server to acquire data related to the brand using an external data source and an API; means for calculating the brand's name recognition, recognition, and reputation using the generative AI model based on the acquired data; means for returning the calculated score to the user's terminal in real time; and means for the server to perform dynamic pricing when the user selects the depth and level of detail of the research. This enables rapid and accurate analysis of the brand's market situation and reputation, the formulation of efficient marketing and sales strategies, and dynamic pricing according to the depth and level of detail of the research.

[1023] A "generative AI model" is a model trained using machine learning techniques to learn specific data patterns and make predictions or classifications.

[1024] A "server" is a device that has computing capabilities and sends and receives data over a network.

[1025] A "terminal" is a device operated by a user, and typically refers to a computer device such as a PC or smartphone.

[1026] A "browser" is software for viewing web pages and is used to obtain information via the Internet.

[1027] A "web application" is a program that runs on the Internet and is software that users can access and operate through a browser.

[1028] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format for structuring and sending and receiving data.

[1029] "External data sources" refers to data providing systems or databases that exist outside the server and are used to obtain information related to the brand.

[1030] "API" stands for Application Programming Interface, and is an interface for exchanging functions and data between software programs.

[1031] "Name recognition" is an indicator of how well known a particular brand is in the market and among consumers.

[1032] "Awareness" is an indicator of the degree to which a particular brand is recognized by consumers.

[1033] "Reputation" refers to the consumer and market evaluation and opinion of a particular brand.

[1034] "Dynamic pricing" is a system that changes prices depending on user choices and circumstances.

[1035] This invention relates to a system that uses a generative AI model to collect and analyze data related to a specific brand. This system operates among three parties: a server, a terminal, and a user. Detailed procedures and modes for implementing this invention are specifically described below.

[1036] Server Operation

[1037] When the program starts, the server first initializes and loads a pre-trained generative AI model. This AI model is trained using machine learning techniques based on past data and learns patterns related to brands. The required library is the Python TensorFlow library. The server loads the libraries and configuration files and loads the model into memory.

[1038] User operations

[1039] Users access the dedicated web application using their device's browser. Common web browsers such as Google Chrome and Mozilla Firefox can be used. The user enters the brand name they wish to research and clicks the submit button. This action activates JavaScript on the user's device, converting the brand name into JSON format.

[1040] Device behavior

[1041] The device sends the entered brand name to the server in JSON format. Network communication is performed using an HTTP POST request. For example, when a user searches for information about a brand called "BrandA," the device sends the following JSON data to the server:

[1042] json

[1043] {

[1044] "brand_name": "BrandA"

[1045] }

[1046] Data acquisition and analysis by the server

[1047] The server parses the JSON data received from the device and retrieves brand-related information using external data sources and APIs. Common external data sources include Google Trends, Twitter API, Brandwatch, etc. Using the Python Requests library, the server accesses these external APIs and retrieves brand-related data.

[1048] Based on the acquired information, the server uses a generative AI model to calculate brand awareness, recognition, and reputation scores. For example, "Brand A" might have a recognition score of 0.85, a recognition score of 0.78, and a reputation score of 0.92. These scores are then converted back to JSON format and sent back to the user's device in real time.

[1049] User review of results and request further investigation

[1050] The user checks the analysis results on their device. For example, the score for "Brand A" is displayed. If they want to conduct a more detailed investigation, they select the depth and level of detail of the investigation and send the request again. This request is also sent to the server in JSON format.

[1051] Server-driven dynamic pricing

[1052] The server receives a request for additional research from the user and dynamically sets the price according to the specified rank. For example, if a user requests a research of rank 3, the server calculates the price corresponding to rank 3 (e.g., 3,000 yen) and presents it to the user. The specific pricing algorithm is based on the user's selection and the settings in the server.

[1053] Examples of concrete examples and prompts

[1054] For example, if a user wants to research brand information for "Brand A," they enter "Brand A" into the browser's input form and click the submit button. The server uses external data sources and APIs to collect information related to "Brand A," and calculates the recognition, awareness, and reputation scores using a generative AI model. These scores can be viewed in real time. If a user requests more detailed research, a price will be displayed according to the desired ranking.

[1055] Example prompt sentence:

[1056] To research brand information for "Brand A," enter the brand name in the browser's input form and click the submit button. The server uses external data sources and APIs to collect information related to "Brand A," and uses a generative AI model to calculate scores for name recognition, awareness, and reputation. You can view the results in real time. If you would like a more detailed investigation, a price will be displayed based on your desired rank.

[1057] As described above, this invention is a useful tool for companies to conduct rapid and accurate market analysis and formulate efficient marketing and sales strategies. Furthermore, by using a generative AI model, it can provide highly accurate results.

[1058] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1059] Step 1:

[1060] The server launches the program and loads the generative AI model. Specifically, the server uses Python's TensorFlow library to load the trained generative AI model into memory, and the server is then ready to analyze data related to the brand.

[1061] Input: Server start command

[1062] Output: Generative AI model loaded in memory

[1063] Step 2:

[1064] A user accesses a web application using a browser on their device. They enter a brand name in the browser's input form and click the submit button. For example, the user enters "BrandA."

[1065] Input: Brand name (e.g. "BrandA")

[1066] Output: Submit button click event

[1067] Step 3:

[1068] The device receives the click event of the submit button, converts the brand name entered by the user into JSON format, constructs the brand name as a JSON object using JavaScript, and then sends this JSON data to the server using an HTTP POST request.

[1069] Input: Submit button click event from browser

[1070] Output: Brand information in JSON format (e.g. "{'brand_name': 'BrandA'}")

[1071] Step 4:

[1072] The server parses the JSON data received from the device, extracts the brand name, and then calls an external data source API to retrieve information related to the specified brand. It uses the Python Requests library to collect data from external APIs, such as Google Trends, Twitter API, and Brandwatch.

[1073] Input: Brand information in JSON format (e.g. "{'brand_name': 'BrandA'}")

[1074] Output: Brand information retrieved from an external data source

[1075] Step 5:

[1076] The server inputs the acquired data into a generative AI model to calculate brand awareness, recognition, and reputation. The analyzed data is converted into a new JSON format and an evaluation score is calculated. For example, specific values ​​such as awareness of 0.85, recognition of 0.78, and reputation of 0.92 are output.

[1077] Input: Brand information retrieved from an external data source

[1078] Output: Prominence, awareness, and reputation scores (e.g., "{'brand_name': 'BrandA', 'Prominence': 0.85, 'Awareness': 0.78, 'Reputation': 0.92}")

[1079] Step 6:

[1080] The server converts the calculated score back into JSON format and sends it back to the user's device in real time over the network. The user's device receives this JSON data, parses it using JavaScript, and displays the analysis results in the browser.

[1081] Input: Prominence, awareness, and reputation scores (e.g., "{'brand_name': 'BrandA', 'Prominence': 0.85, 'Awareness': 0.78, 'Reputation': 0.92}")

[1082] Output: Analysis result JSON data returned to the user's device

[1083] Step 7:

[1084] If the user checks the analysis results on the device and wishes to conduct a more detailed investigation, they can select the depth and level of detail of the investigation and send the request again. The detailed investigation request is also sent to the server in JSON format.

[1085] Input: JSON format analysis results and user's detailed investigation request (e.g., "{'brand_name': 'BrandA', 'Request Detail': 'Rank 3'}")

[1086] Output: Detailed survey request JSON data sent to the server

[1087] Step 8:

[1088] The server receives detailed survey requests from users and dynamically sets prices according to the specified rank. For example, if a survey with rank 3 is requested, the server calculates the price corresponding to rank 3 (e.g., 3,000 yen) and presents it to the user. Prices are dynamically set using a Python calculation algorithm.

[1089] Input: User's detailed survey request JSON data

[1090] Output: Dynamically set price information (e.g., "{'brand_name': 'BrandA', 'Price for Rank 3': 3000}")

[1091] (Application example 1)

[1092] 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."

[1093] Traditional brand data collection and analysis systems struggled to accurately predict the effectiveness of advertising campaigns and provide detailed insights for formulating optimal strategies for target audiences. Furthermore, they lacked the ability for users to dynamically set prices based on demand, limiting the ability to develop flexible marketing strategies. This resulted in issues that reduced the effectiveness and cost-effectiveness of advertising campaigns.

[1094] 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.

[1095] In this invention, the server includes means for collecting and analyzing data related to brand names using a generative AI model, means for calculating brand awareness, recognition, and reputation based on the collected data, means for providing the calculated insights to users in real time, means for providing effectiveness predictions based on the target demographic and budget of the advertising campaign, and means for dynamic pricing according to demand. This enables rapid and accurate understanding of market conditions in advertising campaigns, enabling the formulation of effective marketing strategies and achieving high cost efficiency.

[1096] A "generative AI model" is an algorithm trained using machine learning techniques that has the ability to identify and analyze specific data patterns.

[1097] "Data related to a brand name" refers to information about a specific brand, including a wide range of data such as name recognition, awareness, and reputation.

[1098] "Brand awareness" refers to an indicator that shows how well a particular brand is recognized in the market and among consumers.

[1099] "Brand awareness" refers to an indicator that shows the degree of identifiable knowledge and image that consumers have of a particular brand.

[1100] "Brand reputation" refers to an indicator that shows the degree of evaluation and trustworthiness of a particular brand among consumers and the market.

[1101] A "target audience" is a group of consumers that is specifically targeted by advertising or marketing efforts.

[1102] "Advertising campaign effectiveness forecasting" refers to a prediction that evaluates in advance the impact and results of a specific advertising activity on the target audience.

[1103] "Dynamic pricing" refers to the practice of adjusting prices in real time based on demand and market conditions.

[1104] This invention relates to a system for collecting and analyzing data related to brand names using a generative AI model. This system uses a cloud server, user terminals, and external APIs to quickly and accurately predict the effectiveness of advertising campaigns. An embodiment of this system is described below in detail.

[1105] System Configuration

[1106] The server uses a pre-trained generative AI model to collect and analyze data related to the brand name entered by the user. Specifically, the server uses a cloud server (e.g., AWS EC2) to load the generative AI model (e.g., GPT-4) and perform analysis.

[1107] User Interface

[1108] The user inputs the brand name using a mobile application (using React Native for example) on their smartphone. When the user inputs the brand name and submits it, the data is sent to the server in JSON format.

[1109] Data collection

[1110] The server uses external data sources and APIs (e.g., Twitter API, Google Trends API) to obtain information related to the brand name, including brand awareness, recognition, reputation, etc. The server sends an API request and receives the results in JSON format.

[1111] Data analysis

[1112] The server uses the generative AI model to calculate brand awareness, recognition, and reputation based on the received data. For example, it generates scores such as 0.85 for brand awareness, 0.78 for recognition, and 0.92 for reputation. The calculation results are returned to the user in real time in JSON format.

[1113] Effect prediction

[1114] Additionally, the server provides forecasts based on the target audience and budget of the ad campaign, including the impact on the target audience and return on investment. Users can use these insights to plan effective ad campaigns.

[1115] Dynamic Pricing

[1116] If the user requests a detailed analysis, the server will dynamically set prices for each rank. For example, if the user selects rank 3, the server will calculate and present a specific price, such as 3,000 yen.

[1117] Specific examples

[1118] As a specific use case, consider a situation where a marketing professional at an advertising agency wants to predict the effectiveness of a new advertising campaign for "Brand A." The user opens the smartphone application and enters the following prompt:

[1119] "I would like to predict the effectiveness of Brand A's advertising campaign. I would like you to analyze the scores of name recognition, awareness, and reputation, and then predict and present the effectiveness for the target demographic."

[1120] As a result, the server calculates a brand awareness score of 0.85, an awareness score of 0.78, and a reputation score of 0.92 for "Brand A," and returns these to the user in real time. The server also provides detailed advertising effectiveness predictions and dynamic pricing, allowing users to create highly accurate marketing strategies.

[1121] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1122] Step 1:

[1123] The user opens the mobile application on their smartphone, enters the brand name and a prompt message related to the advertising campaign in the application's input fields, and clicks the submit button. At this time, the entered brand name and prompt message are sent from the device to the server in JSON format.

[1124] Step 2:

[1125] The server parses the received JSON data, extracts the brand name and prompt, and sends a request to external data sources and APIs (e.g., Twitter API, Google Trends API) that includes the brand name and collects related data.

[1126] Step 3:

[1127] The data received from the external API is stored in JSON format on the server. The server then uses a generative AI model based on this collected data to calculate brand awareness, recognition, and reputation. For example, a generative AI model (GPT-4) performs pattern recognition based on past data. Specifically, the following values ​​are calculated: awareness score 0.85, recognition score 0.78, and reputation score 0.92.

[1128] Step 4:

[1129] The server then organizes the calculation results in JSON format and sends them back to the user's smartphone in real time, where the user can view the results, including the insight information.

[1130] Step 5:

[1131] If a user wants more detailed analysis or a prediction of the effectiveness of their advertising campaign, they select a rank for detailed analysis. The server will dynamically set a price based on the selected rank. This price is calculated based on a pre-set fee structure, and a specific price such as 3,000 yen is set for rank 3.

[1132] Step 6:

[1133] This dynamic pricing information is presented to users, who can then review it and access detailed analytics and performance forecasts, providing specific insights into their ad campaigns based on their target demographic and budget.

[1134] Step 7:

[1135] All processing results are displayed on the user's smartphone, ultimately enabling the user to create highly accurate marketing strategies based on detailed data.

[1136] 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.

[1137] This invention relates to a system that uses a generative AI model and an emotion engine to collect and analyze brand data and provide insights to users in real time. An embodiment of this system is described below.

[1138] First, when the program starts, the server loads a pre-trained generative AI model and emotion engine. The model uses machine learning techniques to learn patterns in data related to the brand, and the emotion engine is used to recognize and analyze user emotions.

[1139] The user accesses the web application through the browser on their device, enters the brand name they wish to survey, for example, "BrandA," and clicks the submit button. The device then sends the entered brand name in JSON format to the server.

[1140] When the server receives the brand name sent from the device, it uses external data sources and APIs to obtain information related to the brand. At this time, it sends a request to the external API using the brand name as a query and collects information about the brand in JSON format.

[1141] Next, the server uses the generative AI model to calculate the brand's name recognition, recognition, and reputation based on the acquired data. Specifically, it analyzes information related to the brand name and calculates scores for each evaluation index. For example, it calculates the name recognition, recognition, and reputation scores for "Brand A."

[1142] Additionally, to take user emotional data into account, an emotion engine is used to recognize and analyze emotions from user input. Through text input and other interactions provided by the user, the emotion engine evaluates the user's emotional state. This can yield emotional data such as "the user has positive feelings toward the brand."

[1143] The analyzed findings and sentiment data are sent back to the user's device in real time from the server. Users can view these results on their device and obtain detailed brand insights and sentiment information about their target audience. For example, in addition to numerical data such as awareness of 0.85, recognition of 0.78, and reputation of 0.92, the user's sentiment score is also provided.

[1144] In addition, if the user selects the level of detail or depth of the search, the server performs dynamic pricing. It calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the price based on rank 3 (e.g., 3,000 yen) and presents it to the user.

[1145] As a concrete example, if a user wants to conduct a survey on "Brand A," the user enters "Brand A" in the browser and clicks the submit button. The device sends the brand name to the server, which then uses external data sources and APIs to obtain information related to "Brand A." The server then uses a generative AI model to calculate scores for name recognition, awareness, and reputation. It also uses an emotion engine to obtain the user's emotional data and adds it to the analysis results. These results are then provided to the user in JSON format. If the user then requests a survey at rank 3, the server sets the price for rank 3, calculating it to be 3,000 yen and presenting it to the user.

[1146] In this way, the invention will enable businesses to gain detailed insights into their brands quickly and with high accuracy, and will be a useful tool for developing more meaningful marketing and sales strategies that incorporate user sentiment data.

[1147] The processing flow will be explained below.

[1148] Step 1:

[1149] When the program starts, the server loads the pre-trained generative AI model and emotion engine, deploying them in memory and making them available for subsequent data collection and analysis.

[1150] Step 2:

[1151] A user accesses the web application using a browser on a device, enters the name of the brand for which the user wishes to conduct a survey, for example, "BrandA," and clicks the submit button.

[1152] Step 3:

[1153] The terminal sends the entered brand name in JSON format to the server, which then receives the brand name specified by the user.

[1154] Step 4:

[1155] The server reads the brand name received from the device and retrieves related data using an external API, by sending a request to the external API with the brand name as a query to collect information about the brand.

[1156] Step 5:

[1157] The server analyzes the data received from the external API and extracts the necessary information (e.g., popularity, recognition, reputation). Based on this data, a generative AI model is used to calculate the scores for each evaluation index.

[1158] Step 6:

[1159] The server uses an emotion engine to obtain emotion data based on user input and interactions, including emotion recognition from user text input and other interactions.

[1160] Step 7:

[1161] The server combines the calculated popularity, recognition, and reputation scores with user sentiment data to generate a comprehensive analysis that provides detailed insights, including sentiment scores.

[1162] Step 8:

[1163] The server creates the analysis results in JSON format and sends them back to the user's device in real time, allowing the user to check the results immediately.

[1164] Step 9:

[1165] Users can further specify the level of detail and depth of the investigation by selecting a rank. For example, to select rank 3, select the appropriate option on the screen.

[1166] Step 10:

[1167] The terminal transmits the designated rank information to the server, which then receives a request for detailed investigation based on the rank.

[1168] Step 11:

[1169] The server calculates the price based on the specified rank and returns it to the user's terminal. For example, it calculates the price corresponding to rank 3 (e.g., 3,000 yen) and presents it to the user.

[1170] Step 12:

[1171] Develop appropriate marketing and sales strategies based on the analytics and pricing information you receive, and use this information to effectively promote your products to your target audience.

[1172] This series of processes allows companies to quickly gain highly accurate insights about their brand, and by incorporating emotional data, they can improve the accuracy of their marketing strategies.

[1173] Example 2

[1174] 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."

[1175] In modern marketing and brand management, it is extremely important to quickly and accurately obtain detailed brand-related insights and user sentiment data. However, conventional systems have struggled to objectively measure brand awareness, recognition, and reputation, or analyze user sentiment data in real time. This has left companies struggling to obtain sufficient information when formulating effective marketing strategies for their target audiences.

[1176] 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.

[1177] In this invention, the server includes means for collecting and analyzing data related to brand names using a generative AI model, means for recognizing and analyzing user emotions using an emotion engine, means for calculating brand awareness, recognition, and reputation based on the collected data, means for providing analyzed insights and emotion data to users in real time, and means for dynamic pricing according to demand, thereby enabling companies to quickly and accurately obtain detailed insights about their brands and emotion data of their target audiences.

[1178] A "generative AI model" is a machine learning model that learns, collects, and analyzes patterns in data related to brand names.

[1179] The "emotion engine" is a software component that recognizes and analyzes a user's emotions based on the user's text input and interactions.

[1180] "Brand awareness" is an evaluation indicator that indicates how widely a brand is recognized.

[1181] "Brand awareness" is an evaluation index that indicates the degree to which consumers or users recognize a particular brand and understand its characteristics.

[1182] "Brand reputation" is a score that indicates the evaluation and trust that consumers and users have of a brand.

[1183] "Means of providing in real time" refers to a method of instantly returning and providing analyzed data and knowledge to users.

[1184] "Dynamic pricing" is a method of varying prices depending on the level of detail and depth of research selected by the user.

[1185] "External Data Sources" refers to various sources on the Internet that provide information related to the brand.

[1186] "API" stands for Application Program Interface and refers to a mechanism that enables data communication between different software programs.

[1187] This invention relates to a system that uses a generative AI model and an emotion engine to collect and analyze brand data and provide insights to users in real time. An embodiment of this system is described below.

[1188] Hardware and Software Use:

[1189] Server: Collects and analyzes data, runs generative AI models and emotion engines.

[1190] User terminal: Uses a browser to receive input from the user.

[1191] Browser: Use any web browser (e.g., Google Chrome, Mozilla Firefox).

[1192] Generative AI models: Use machine learning models such as OpenAI GPT-4.

[1193] Sentiment Engine: Uses the Sentiment Analysis API (e.g., Google Cloud Natural Language API).

[1194] External data sources and APIs: Providing information relevant to your brand (e.g., Twitter API, Google News API).

[1195] Specific operation steps:

[1196] 1. Start the program:

[1197] When the program starts, the server loads a pre-trained generative AI model and an emotion engine. The generative AI model learns patterns in data related to the brand, and the emotion engine recognizes and analyzes user emotions.

[1198] 2. Enter your brand name:

[1199] The user opens a browser on their device and accesses the web application. The user enters the name of the brand they wish to survey. For example, they enter "BrandA" and clicks the submit button.

[1200] 3. Submit your brand name:

[1201] The device sends the brand name entered by the user in JSON format to the server, securely transmitting the data using the HTTPS protocol.

[1202] 4. Brand Data Collection:

[1203] The server retrieves information related to the brand using external data sources and APIs based on the brand name received from the device. Specifically, it sends a request to an external API (e.g., Twitter API, Google News API) using the brand name as a query, and collects information about the brand in JSON format.

[1204] 5. Brand Data Analysis:

[1205] The server uses a generative AI model to calculate brand awareness, recognition, and reputation based on the collected brand data. For example, the server calculates scores for "Brand A" such as awareness of 0.85, recognition of 0.78, and reputation of 0.92.

[1206] 6. Emotional Data Analysis:

[1207] The server uses an emotion engine to recognize and analyze emotions from user input. It evaluates whether the user has positive emotions about the brand. For example, it extracts "positive" emotion from the user input.

[1208] 7. Returning analysis results and emotion data:

[1209] The server sends the analyzed findings and sentiment data back to the user's device in real time in JSON format, where the user can view the results and get detailed brand insights and sentiment information about the target audience.

[1210] 8. Dynamic Pricing:

[1211] The server performs dynamic pricing when the user selects the level of detail and depth of the investigation. It calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the price for rank 3 as 3,000 yen and presents it to the user.

[1212] Examples:

[1213] If a user wants to research "BrandA", the system works as follows:

[1214] 1. The user enters "BrandA" in the browser and clicks the submit button.

[1215] 2. After receiving the brand name, the server uses the generative AI model to collect and analyze data about "BrandA."

[1216] 3. The server uses the emotion engine to recognize and analyze emotion data from the user's input.

[1217] 4. The server returns numerical data such as popularity 0.85, recognition 0.78, and reputation 0.92 to the user, as well as emotional data of "positive."

[1218] 5. If the user requests an additional detailed investigation of rank 3, the server calculates a price of 3,000 yen and presents it to the user.

[1219] Examples of prompts for generative AI models:

[1220] Calculate the familiarity, recognition, and reputation scores for brand "BrandA," and also rate the positivity of users based on their sentiment data.

[1221] In this way, the specific actions of the server, terminal and user make this system a useful tool for companies to gain detailed insights about their brand.

[1222] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1223] Step 1:

[1224] When the program starts, the server loads a pre-trained generative AI model and emotion engine, which prepares the system for analyzing brand data. The input is the configuration data for the generative AI model and emotion engine, and the output is a system ready for analysis.

[1225] Step 2:

[1226] The user opens a browser on their device and accesses the web application. They enter the name of the brand they want to survey and click the submit button. For example, they enter "BrandA." The input is a string of the brand name, and the output is JSON-formatted data sent from the device to the server.

[1227] Step 3:

[1228] The terminal sends the brand name entered by the user to the server in JSON format. The data is sent securely using the HTTPS protocol. The input is the brand name entered by the user, and the output is the request data sent to the server.

[1229] Step 4:

[1230] The server retrieves brand-related information using external data sources and APIs based on the brand name received from the device. Specifically, it sends a request to an external API (e.g., Twitter API, Google News API) using the brand name as a query, and collects brand-related information in JSON format. The input is the brand name query, and the output is the collected brand-related information.

[1231] Step 5:

[1232] The server uses a generative AI model based on the collected brand data to calculate brand awareness, recognition, and reputation. For example, it calculates scores such as 0.85 for awareness, 0.78 for recognition, and 0.92 for reputation for "Brand A." The input is the collected brand data, and the output is the score for each brand evaluation indicator.

[1233] Step 6:

[1234] The server uses an emotion engine to recognize and analyze emotions from user input. It evaluates whether the user has positive emotions about the brand. For example, it extracts the "positive" emotion from the user's input. The input is the user's text input, and the output is the user's emotion data.

[1235] Step 7:

[1236] The server sends the analyzed findings and sentiment data in JSON format back to the user's device in real time. The user can view these results on their device and obtain detailed brand insights and sentiment information about the target audience. The input is the analysis results and sentiment data, and the output is real-time information provided to the user.

[1237] Step 8:

[1238] The server performs dynamic pricing when the user selects the level of detail and depth of the search. It calculates the price according to the rank specified by the user and returns it to the user. For example, if the user selects rank 3, the server calculates the price for rank 3 as 3,000 yen and presents it to the user. The input is the rank selected by the user, and the output is the calculated price information.

[1239] Examples:

[1240] If a user wants to research "BrandA":

[1241] 1. The user enters "BrandA" in the browser and clicks the submit button.

[1242] 2. After receiving the brand name, the server uses the generative AI model to collect and analyze data about "BrandA."

[1243] 3. The server uses the emotion engine to recognize and analyze emotion data from the user's input.

[1244] 4. The server returns numerical data such as popularity 0.85, recognition 0.78, and reputation 0.92 to the user, as well as emotional data of "positive."

[1245] 5. If the user requests an additional detailed investigation of rank 3, the server calculates a price of 3,000 yen and presents it to the user.

[1246] (Application example 2)

[1247] 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."

[1248] Conventional advertising systems simply collect and analyze brand-related information, making it difficult to provide personalized advertising that takes into account user emotional data and real-time interactions. The present invention aims to solve this problem and provide more accurate advertising.

[1249] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing data related to brand names using a generative AI model, means for calculating brand awareness, recognition, and reputation based on the collected data, means for providing the calculated insights to users in real time, means for recognizing and analyzing the emotional state of users using an emotion engine, means for displaying personalized advertisements based on the user's emotional data and brand analysis results, and means for dynamic pricing according to demand. This enables personalized display of advertisements based on the user's emotional state and brand evaluation.

[1250] A "generative AI model" is a model that uses machine learning techniques to learn patterns in data relevant to a brand and is useful for data collection and analysis.

[1251] An "emotion engine" is a technology for recognizing and analyzing emotional states through user input and interaction.

[1252] "Name recognition" is an indicator that indicates how widely known a particular brand is.

[1253] "Awareness" is an evaluation indicator that indicates the depth of knowledge and understanding of a particular brand.

[1254] "Reputation" is an evaluation index that indicates the degree of evaluation and trust for a particular brand.

[1255] "Personalized advertising" is advertising that is customized based on a user's individual interests and emotional state.

[1256] "Dynamic pricing" is a method of flexibly changing prices based on demand and other conditions.

[1257] A "target audience" is a specific group of consumers targeted by advertising and marketing activities.

[1258] An "external data source" is a data provider used to obtain information from outside the system.

[1259] "API" stands for Application Program Interface, a set of rules and tools that allow different software systems to communicate with each other.

[1260] This invention relates to a system that uses generative AI models and emotion engines to collect and analyze brand-related data, provide real-time insights to users, and even display personalized advertisements based on user emotion data.

[1261] First, when the program starts up, the server loads a pre-trained generative AI model and emotion engine. The generative AI model uses machine learning techniques to learn patterns in data related to the brand, and the emotion engine is used to recognize and analyze the user's emotional state.

[1262] The user accesses the application on their device and enters the name of the brand they wish to research. For example, if they enter "Brand A" and click the submit button, the device will send the entered brand name to the server in JSON format. After receiving the brand name sent from the device, the server uses external data sources and APIs to obtain information related to the brand. In this case, a request is sent to the external API using the brand name as a query, and information about the brand is collected in JSON format.

[1263] Next, the server uses the generative AI model based on the acquired data to calculate the brand's name recognition, recognition, and reputation. Specifically, it analyzes information related to the brand name and calculates scores for each evaluation index. For example, it calculates the name recognition, recognition, and reputation scores for "Brand A."

[1264] In addition, the server also takes into account the user's emotional data, using an emotion engine to recognize and analyze emotions from the user's input. Through the text input and other interactions provided by the user, the emotion engine evaluates the user's emotional state. Based on this evaluation, emotion data can be obtained, such as "the user has positive emotions toward the brand."

[1265] The analyzed findings and sentiment data are sent back to the user's device in real time from the server. Users can view these results on their device and obtain detailed brand insights and sentiment information about their target audience. For example, in addition to numerical data such as awareness of 0.85, recognition of 0.78, and reputation of 0.92, the user's sentiment score is also provided.

[1266] Furthermore, the analysis results can be used to display personalized advertisements to users. These advertisements are selected based on the user's emotional state and brand evaluation data, so they can more effectively capture the user's attention. For example, an advertisement message such as "Check out the special sale on a highly rated brand!" can be displayed.

[1267] The hardware used includes servers and user devices (smartphones and PCs), and the software used includes generative AI models, emotion engines, and external APIs, allowing users to gain detailed insights about any brand and see personalized ads based on those insights.

[1268] As a concrete example, a user enters "Brand A" in a browser and clicks the submit button. The device sends the brand name to the server, which then uses external data sources and APIs to obtain information related to "Brand A." The server then uses a generative AI model to calculate scores for familiarity, recognition, and reputation. It also uses an emotion engine to obtain the user's emotional data and adds it to the analysis results. These results are then provided to the user in JSON format. If the user subsequently requests a survey at rank 3, the server sets the price for rank 3, calculating it to be 3,000 yen and presenting it to the user.

[1269] Example prompts for generative AI models:

[1270] "Please tell me about the name recognition, recognition, and reputation of Brand A."

[1271] Example prompts in the Emotion Engine:

[1272] I think this brand is high quality.

[1273] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1274] Step 1:

[1275] The server loads pre-trained generative AI models and emotion engines when the program starts. This loads the necessary models and engines into memory and makes them available for use. The input is the trained model and emotion engine data, and the output is the loaded model and engine.

[1276] Step 2:

[1277] The user accesses the application on their device and enters the brand name they wish to investigate. For example, they enter "Brand A" and click the submit button. This entered brand name is sent from the device to the server in JSON format. The input is the brand name entered by the user, and the output is brand name data in JSON format.

[1278] Step 3:

[1279] When the server receives the brand name sent from the device, it uses external data sources and APIs to obtain information related to the brand. At this time, it sends a request to the external API using the brand name as a query and collects information about the brand in JSON format. The input is brand name data in JSON format, and the output is brand information data in JSON format.

[1280] Step 4:

[1281] The server uses a generative AI model based on the acquired brand information data to calculate brand awareness, recognition, and reputation. Specifically, it analyzes various data related to the brand name and calculates scores for each evaluation indicator. The input is brand information data in JSON format, and the output is scores for awareness, recognition, and reputation.

[1282] Step 5:

[1283] The server also takes into account the user's emotional data, and therefore uses an emotion engine to recognize and analyze emotions from the user's input. Through text input and other interactions provided by the user, the emotion engine evaluates the user's emotional state. The input is the user's text input data, and the output is the analyzed emotional data.

[1284] Step 6:

[1285] The server transmits the analyzed findings and sentiment data to the user's device in real time, allowing the user to view the results on their device and obtain detailed brand insights and sentiment information. The inputs are recognition, awareness, and reputation scores and sentiment data, and the output is insights and sentiment information displayed on the user's device.

[1286] Step 7:

[1287] The server generates a personalized advertisement based on the analysis results and displays it to the user. The advertisement is selected based on the user's emotional state and brand evaluation data. The input is the emotional data and brand evaluation data, and the output is a personalized advertising message displayed on the user's device.

[1288] 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.

[1289] 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.

[1290] 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.

[1291] 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.

[1292] 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.

[1293] 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.

[1294] 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).

[1295] 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.

[1296] 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."

[1297] 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.

[1298] 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).

[1299] 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.

[1300] 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.

[1301] 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.

[1302] 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.

[1303] 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.

[1304] 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.

[1305] 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.

[1306] 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.

[1307] 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.

[1308] 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.

[1309] The following is further disclosed regarding the above embodiment.

[1310] (Claim 1)

[1311] a means of collecting and analyzing data related to brand names using a generative AI model;

[1312] A means of calculating brand awareness, recognition, and reputation based on the collected data;

[1313] a means of providing the calculated insights to the user in real time;

[1314] A means of dynamic pricing according to demand;

[1315] A system including:

[1316] (Claim 2)

[1317] 2. The system according to claim 1, which analyzes attribute information of the target audience and provides detailed data such as age, gender, hobbies, preferences, and purchasing behavior.

[1318] (Claim 3)

[1319] 10. The system of claim 1, wherein the system obtains information related to the brand using external data sources and APIs.

[1320] "Example 1"

[1321] (Claim 1)

[1322] When the program starts, it has a means to load a pre-trained generative AI model;

[1323] A means for a user to access a web application through a browser on a terminal, input a brand name, and submit the same;

[1324] A means for the terminal to send the input brand name in JSON format to the server;

[1325] a means for the server to obtain data related to the brand using external data sources and APIs;

[1326] A means to calculate brand awareness, recognition, and reputation using generative AI models based on the acquired data;

[1327] A means for returning the calculated score to the user's terminal in real time;

[1328] a means by which the server provides dynamic pricing based on the depth and detail of the search selected by the user;

[1329] A system including:

[1330] (Claim 2)

[1331] 2. The system according to claim 1, which analyzes attribute information of the target audience and provides detailed data such as age, gender, hobbies, preferences, and purchasing behavior.

[1332] (Claim 3)

[1333] 10. The system of claim 1, wherein the system obtains information related to the brand using external data sources and APIs.

[1334] "Application Example 1"

[1335] (Claim 1)

[1336] a means of collecting and analyzing data related to brand names using a generative AI model;

[1337] A means of calculating brand awareness, recognition, and reputation based on the collected data;

[1338] a means of providing the calculated insights to the user in real time;

[1339] A means of providing forecasts of advertising campaign effectiveness based on target audience and budget;

[1340] A means of dynamic pricing according to demand;

[1341] A system including:

[1342] (Claim 2)

[1343] 2. The system according to claim 1, which analyzes attribute information of the target audience and provides detailed data such as age, gender, hobbies, preferences, and purchasing behavior.

[1344] (Claim 3)

[1345] 10. The system of claim 1, wherein the system obtains information related to the brand using external data sources and APIs.

[1346] "Example 2: Combining Emotion Engines"

[1347] (Claim 1)

[1348] a means of collecting and analyzing data related to brand names using a generative AI model;

[1349] a means for recognizing and analyzing user emotions using an emotion engine;

[1350] A means of calculating brand awareness, recognition, and reputation based on the collected data;

[1351] a means for providing analyzed insights and sentiment data to a user in real time;

[1352] A means of dynamic pricing according to demand;

[1353] A system including:

[1354] (Claim 2)

[1355] 2. The system according to claim 1, which analyzes attribute information of the target audience and provides detailed data such as age, gender, hobbies, preferences, and purchasing behavior.

[1356] (Claim 3)

[1357] 10. The system of claim 1, wherein the system obtains information related to the brand using external data sources and APIs.

[1358] "Application example 2 when combining emotion engines"

[1359] (Claim 1)

[1360] a means of collecting and analyzing data related to brand names using a generative AI model;

[1361] A means of calculating brand awareness, recognition, and reputation based on the collected data;

[1362] A means of providing calculated insights to users in real time; and

[1363] means for recognizing and analyzing the emotional state of a user using an emotion engine;

[1364] A means for displaying personalized advertisements based on user emotion data and brand analysis results;

[1365] A means of dynamic pricing according to demand;

[1366] A system including:

[1367] (Claim 2)

[1368] 2. The system according to claim 1, which analyzes attribute information of the target audience and provides detailed data such as age, gender, hobbies, preferences, and purchasing behavior.

[1369] (Claim 3)

[1370] 10. The system of claim 1, wherein the system obtains information related to the brand using external data sources and APIs. [Explanation of symbols]

[1371] 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 of collecting and analyzing data related to brand names using a generative AI model; A means of calculating brand awareness, recognition, and reputation based on the collected data; a means of providing the calculated insights to the user in real time; A means of dynamic pricing according to demand; A system including:

2. 2. The system according to claim 1, wherein the system analyzes attribute information of the target audience and provides detailed data such as age, gender, hobbies, preferences, and purchasing behavior.

3. The system of claim 1 , wherein the system obtains information related to the brand using external data sources and APIs.

Images