system

Abstract

Provide a system. [Solution] a means for storing ideas received from users; A means for saving the review criteria set by the administrator; a means for evaluating ideas using generative AI based on the stored ideas; A means of selecting valuable ideas based on the evaluation results; a means for notifying the user of the results of the selected ideas; A system including:

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] Until now, there has been no system for efficiently evaluating ideas collected from users and selecting valuable ideas. The evaluation criteria and evaluation process are often set manually, which creates the problem of subjective evaluation. Furthermore, it is difficult to fairly evaluate many ideas in a short amount of time, and there is no guarantee that the selected ideas are practical. The present invention aims to solve these problems and provide a fair and efficient idea evaluation system. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for storing ideas received from users, a means for storing evaluation criteria set by an administrator, a means for evaluating ideas using generative AI based on the stored ideas, a means for selecting valuable ideas based on the evaluation results, and a means for notifying users of the results of the selected ideas. Furthermore, by evaluating ideas based on weights using the evaluation criteria set by the administrator, a fair and objective evaluation is achieved. Furthermore, by using generative AI to evaluate ideas using text analysis and natural language processing techniques, it is possible to efficiently evaluate a large number of ideas and quickly select valuable ideas.

[0006] A "user" is a user who submits ideas to the system and receives evaluation results.

[0007] An "Administrator" is a person or entity that sets the screening criteria and manages the entire system.

[0008] "Ideas" are proposals or ideas submitted by users through the system.

[0009] "Evaluation criteria" are the evaluation items and their weightings set by the administrator to evaluate ideas.

[0010] "Storage means" refers to a database or storage device for storing data such as ideas and evaluation criteria, and retrieving them as needed.

[0011] "Generative AI" is a system that uses artificial intelligence technology to automatically evaluate ideas.

[0012] The "means of evaluation" is the process of calculating and scoring the value of ideas using generative AI.

[0013] The "selection method" is the process of selecting valuable ideas based on the evaluation results.

[0014] "Means of notification" refers to communication means or interfaces for communicating the evaluation results and selected ideas to users and administrators.

[0015] "Text analysis" is a technique that uses natural language processing technology to analyze text and evaluate its content.

[0016] "Natural language processing technology" is an artificial intelligence technology for understanding and analyzing human language.

[0017] The "system" refers to the overall mechanism in which each means of the present invention works together to evaluate and select ideas. [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] ---

[0040] The present invention provides a system for efficiently evaluating ideas received from users and selecting valuable ideas. This system is implemented in the following manner.

[0041] System Overview

[0042] 1. Submit your idea

[0043] User: Enter the "Title of the idea," "Detailed description," and "Related images and files (optional)" using a web form or application.

[0044] User: Click the "Submit" button to submit your idea.

[0045] Terminal: Issues an API request to send user input data to the server.

[0046] Server: Receives API requests and stores the input idea data in a database.

[0047] Server: Returns a response to the user confirming that the idea was successfully submitted.

[0048] 2. Setting the screening criteria

[0049] User (Administrator): The administrator accesses the review criteria settings screen via the web interface or app.

[0050] User (Administrator): Enter evaluation criteria such as "originality," "feasibility," and "market value," and set the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[0051] Terminal: Sends the evaluation criteria and their weighting set by the administrator to the server.

[0052] Server: Stores the received criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[0053] 3. Evaluating ideas

[0054] Server: Retrieves unrated ideas from the database.

[0055] Server: Calls the generative AI to evaluate each idea based on the evaluation criteria set for each idea obtained.

[0056] Generative AI: It performs text analysis and natural language processing on each idea to calculate scores such as "originality," "feasibility," and "market value."

[0057] Generative AI: Based on the calculated score, the idea is given a final evaluation score, where an overall score is calculated using the set weights.

[0058] Server: Stores the evaluation scores returned by the generative AI in a database.

[0059] 4. Picking up valuable ideas

[0060] Server: Based on the evaluation scores stored in the database, ideas that exceed the standard score are selected. The standard score is determined based on the minimum criteria set by the administrator.

[0061] Server: compiles the ideas into a list and makes them accessible to users.

[0062] Terminal: Generates a screen displaying a list of picked ideas and shows it to the user.

[0063] 5. Notification of Results

[0064] Server: Sends emails and in-app notifications to submitters of selected ideas informing them of the evaluation results.

[0065] Users will receive a notification to find out if their idea was featured, including the rating score and reasons for its selection.

[0066] Specific examples

[0067] When a user submits an idea for a "smart trash can," the device sends the data to the server, where the idea is stored in a database. The administrator sets the evaluation criteria, such as "originality," "feasibility," and "market value," and these are stored on the server.

[0068] The server uses generative AI to evaluate the "smart trash cans" and calculate a score based on each criterion. If the overall score exceeds the criterion, the server will select the idea as a valuable idea, and the device will display a list. Finally, the user will be notified and can check the evaluation results.

[0069] In this way, the system of the present invention can efficiently and fairly carry out the entire process from soliciting ideas from users to ultimately selecting valuable ideas, significantly improving the accuracy and efficiency of the idea discovery process in companies and organizations.

[0070] The processing flow will be explained below.

[0071] Program processing flow

[0072] Step 1:

[0073] A user uses a web form or application to enter an idea title, a detailed description, and optional related images and files.

[0074] Step 2:

[0075] The user clicks the "Send" button, and the terminal sends the idea data to the server.

[0076] Step 3:

[0077] The server receives the API request and stores the input idea data in a database.

[0078] Step 4:

[0079] The server returns a response confirming to the user that the idea was successfully submitted.

[0080] Step 5:

[0081] The user (administrator) accesses the review criteria settings screen via the web interface or app.

[0082] Step 6:

[0083] The user (administrator) inputs evaluation criteria such as "originality," "feasibility," and "market value," and sets the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[0084] Step 7:

[0085] The terminal sends the evaluation criteria and their weighting set by the administrator to the server.

[0086] Step 8:

[0087] The server stores the received evaluation criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[0088] Step 9:

[0089] The server retrieves unrated ideas from the database.

[0090] Step 10:

[0091] The server calls a generative AI to evaluate each idea it receives based on the evaluation criteria set for each idea.

[0092] Step 11:

[0093] Generative AI performs text analysis and natural language processing on each idea, calculating scores for "originality," "feasibility," "market value," and other factors.

[0094] Step 12:

[0095] Based on the calculated scores, the generative AI assigns a final evaluation score to the idea, which calculates an overall score using the weights you set.

[0096] Step 13:

[0097] The server stores the evaluation scores returned by the generative AI in a database.

[0098] Step 14:

[0099] The server selects ideas that exceed a benchmark score based on the evaluation scores stored in the database, which is determined based on minimum criteria set by the administrator.

[0100] Step 15:

[0101] The server compiles a list of picked ideas and makes them accessible to users.

[0102] Step 16:

[0103] The device generates a screen displaying a list of the picked ideas and shows it to the user.

[0104] Step 17:

[0105] The server will send an email or in-app notification to the submitter of the picked idea informing them of the evaluation results.

[0106] Step 18:

[0107] Users will receive a notification to find out if their idea was featured, along with a rating score and reasons for its selection.

[0108] Example 1

[0109] 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."

[0110] It is important for companies and organizations to efficiently evaluate the many ideas submitted by users and appropriately select the most valuable ideas. However, manual evaluation requires time and effort, and there is a possibility that subjective judgments may be involved, making it inefficient and impartial.

[0111] 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.

[0112] In this invention, the server includes means for storing ideas received from users, means for storing evaluation criteria set by an administrator, means for evaluating the ideas using a generative AI model based on the stored ideas, means for selecting valuable ideas that exceed a standard score based on the evaluation scores, and means for notifying users of the evaluation results of the selected ideas. This makes it possible to efficiently and fairly evaluate received ideas and quickly select valuable ideas.

[0113] "User" means any person or entity that uses the System to submit Ideas.

[0114] "Administrator" means an individual or organization responsible for the operation and management of the system and with the authority to set screening criteria.

[0115] "Idea" refers to a new proposal, concept or idea submitted by a user.

[0116] The "evaluation criteria" are the evaluation criteria for ideas set by the administrator, and include multiple evaluation items such as originality, feasibility, and market value.

[0117] "Generative AI model" refers to an artificial intelligence algorithm that evaluates user-submitted ideas using text analysis and natural language processing techniques.

[0118] An "evaluation score" is a score or number that the generative AI model assigns to each idea based on the evaluation criteria.

[0119] The "baseline score" refers to the minimum evaluation score required to select a worthy idea, and is set by the administrator.

[0120] A "valuable idea" is an idea whose evaluation score exceeds the standard score and is judged to be beneficial to users and companies.

[0121] "Notification means" refers to the method by which the server communicates the evaluation results to the user, and includes email, in-app notifications, etc.

[0122] The present invention relates to a system for efficiently evaluating ideas received from users and selecting valuable ideas. The system is composed of users, terminals, and a server.

[0123] System Configuration

[0124] 1. User: Submits an idea using a web form or application by entering the "idea title," "detailed description," and "related images and files (optional)."

[0125] 2. Terminal: Receives user input data and sends it to the server by sending an HTTP POST request to the API endpoint and including the idea data.

[0126] 3. Server:

[0127] Save Idea: Receives an API request and saves the entered idea data to the database. Executes a SQL insert statement.

[0128] Saving the criteria: The criteria received from the administrator (originality, feasibility, market value) and their respective weights are saved in the database using SQL insert or update statements.

[0129] Evaluate ideas: Retrieve unrated ideas from the database and invoke the generative AI model by sending an API request, including the idea data and evaluation criteria.

[0130] Evaluation-based selection: The generative AI model evaluates ideas using text analysis and natural language processing techniques, calculates a score based on each evaluation criterion, and then calculates a final score using the calculated scores to select ideas that exceed the standard score.

[0131] Notification method: The submitters of selected ideas will be notified of the evaluation results via email and / or in-app notification.

[0132] Hardware and Software Configuration

[0133] Hardware: Server, client terminal (PC, smartphone, tablet, etc.)

[0134] software:

[0135] Front-end: web forms, applications

[0136] Backend: API endpoints, database (SQL)

[0137] Generative AI models: natural language processing libraries, text analysis tools

[0138] Specific examples

[0139] A user submits an idea for a "smart trash can." For example, "a trash can with a function that automatically calls a trash collection service when a certain amount of trash accumulates." The device sends the data to the server using an HTTP POST request, and the server stores the data in a database.

[0140] The administrator will set the following evaluation criteria and weightings.

[0141] Originality: 50%

[0142] Likelihood: 30%

[0143] Market value: 20%

[0144] AI assessment prompt example

[0145] A "smart trash can" is a trash can that automatically calls a trash collection service when a certain amount of trash has accumulated. Please rate this idea using the following criteria.

[0146] Originality: 50%

[0147] Likelihood: 30%

[0148] Market value: 20%

[0149] The server sends this prompt to the generative AI model, which then calculates a score based on each criterion. For example, if the AI ​​scores "originality: 90 points, feasibility: 70 points, market value: 80 points," it will calculate an overall score taking into account the weights. The overall score is calculated as follows:

[0150] Total score = (originality score × originality weight) + (feasibility score × feasibility weight) + (market value score × market value weight)

[0151] = (90 × 0.5) + (70 × 0.3) + (80 × 0.2)

[0152] = 45 + 21 + 16

[0153] = 82

[0154] If the total score exceeds a threshold (e.g., 75 points), the server selects the idea as valuable and notifies the user. This allows the system of the present invention to efficiently evaluate ideas and select them fairly.

[0155] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0156] Step 1:

[0157] Submit your idea

[0158] User: Using a web form or application, enter the "Title of the idea," "Detailed description," and "Related images and files (optional)," then click the "Submit" button.

[0159] Terminal: Takes user input data and sends it to the API endpoint in an HTTP POST request, including the idea title, detailed description, and associated files.

[0160] Server: Receives the API request and executes an INSERT statement to save the idea data in the database. Example: INSERT INTO ideas (title, description, files) VALUES (?, ?, ?)

[0161] Server: Returns an HTTP response (200 OK) to the user confirming that the idea was successfully submitted. The response includes a confirmation message.

[0162] Step 2:

[0163] Setting the review criteria

[0164] User (Administrator): Access the judging criteria setting screen via the web interface or app, and enter judging criteria such as "originality," "feasibility," and "market value" along with their respective weightings (e.g., originality 50%, feasibility 30%, market value 20%).

[0165] Terminal: Takes the administrator's input and sends it to the server via an HTTP POST request, which includes the criteria and their weights.

[0166] Server: Store the received criteria and weights in the database. Example: INSERT INTO criteria (originality_weight, feasibility_weight, market_value_weight) VALUES (?, ?, ?)

[0167] Server: Returns an HTTP response (200 OK) to the administrator confirming that the review criteria were successfully set. This response includes a confirmation message.

[0168] Step 3:

[0169] Idea Evaluation

[0170] Server: Get unrated ideas from the database. Example: SELECT FROM ideas WHERE evaluated = false

[0171] Server: Calls the generative AI model to evaluate each idea based on the evaluation criteria set for each idea. Generates prompts to send to the AI ​​model.

[0172] Generative AI model: Receives API requests and evaluates ideas using text analysis and natural language processing techniques, calculating scores (originality, feasibility, market value) based on each evaluation criteria.

[0173] Generative AI model: Returns the calculated score to the server, which includes the score for each assessment item and the final evaluation score.

[0174] Server: Using the received scores, calculate the total score by multiplying each score by the weight set in the evaluation criteria. Example: total_score = (originality_score originality_weight) + (feasibility_score feasibility_weight) + (market_value_score market_value_weight)

[0175] Server: Save the calculated total score to the database and update the idea's evaluated flag. Example: UPDATE ideas SET total_score = ?, evaluated = true WHERE id = ?

[0176] Step 4:

[0177] Picking up valuable ideas

[0178] Server: Select ideas from the database whose total score exceeds the threshold score. Example: SELECT FROM ideas WHERE total_score >= ?

[0179] Server: Compiles the selected ideas into a list and formats them in an accessible format (e.g. HTML or JSON).

[0180] Terminal: Renders the data received from the server and generates a screen displaying a list of valuable ideas for the user.

[0181] Step 5:

[0182] Notification of results

[0183] Server: Sends emails and in-app notifications to the winners of the ideas, including the score and reasons for the idea's selection.

[0184] Users: Receive notifications to find out if their ideas are selected as valuable ideas.

[0185] In this way, each processing step of the system is carried out efficiently through cooperation between users, terminals, and servers, from idea submission to evaluation, selection, and notification.

[0186] (Application example 1)

[0187] 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."

[0188] In recent years, there has been an increasing demand for efficient and fair evaluation in idea solicitation and selection. However, manual evaluation is time-consuming and laborious, and it is difficult to ensure fairness. While generative artificial intelligence (AI) is an alternative, it poses challenges, such as the difficulty of designing appropriate prompts to effectively evaluate ideas and the difficulty of calculating an overall evaluation by weighting the evaluation criteria. Furthermore, the process of quickly notifying evaluation results and providing feedback to users must be efficient.

[0189] 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.

[0190] In this invention, the server includes means for storing ideas received from users, means for storing evaluation criteria set by an administrator, means for evaluating ideas using a generative artificial intelligence, means for generating prompt sentences for ideas to be evaluated, means for requesting the generative artificial intelligence to evaluate the ideas using the prompt sentences, means for selecting valuable ideas based on the evaluation results, and means for notifying users of the results of the selected ideas. This makes it possible to evaluate ideas efficiently and fairly and provide prompt feedback to users.

[0191] "Users" are members of the public who submit ideas and suggestions.

[0192] An "Administrator" is a person or entity with the authority to set the criteria for evaluating ideas and oversee the evaluation process.

[0193] "Ideas" are new ideas or improvements suggested by users.

[0194] "Evaluation criteria" are measures such as originality, feasibility, and market value used to evaluate ideas.

[0195] "Generative AI" is AI that has the ability to evaluate ideas using natural language processing and text analysis.

[0196] A "prompt" is a specific instruction used when evaluating ideas using generative artificial intelligence.

[0197] The "evaluation result" is the score of the idea calculated by the generative artificial intelligence.

[0198] A "worthy idea" is an idea that receives a high rating based on the established evaluation criteria.

[0199] "Notification" is a message that notifies the user of the evaluation results or selection results.

[0200] A "server" is a computer system that stores ideas submitted by users and set evaluation criteria, and runs the generative artificial intelligence.

[0201] The present invention relates to a system for efficiently and fairly evaluating ideas received from users and selecting valuable ideas. This system includes the processes of registering ideas, setting review criteria by an administrator, evaluation by generative artificial intelligence, selection, and notification.

[0202] System Overview

[0203] 1. Submit your idea

[0204] Users can use the official application to register "new product ideas" and "improvement suggestions." Ideas can include titles, detailed descriptions, related images, files, and other attachments.

[0205] When the send button is clicked, data is sent from the terminal to the server.

[0206] 2. Setting the screening criteria

[0207] Administrators access the administrator screen within the app to set the evaluation criteria (e.g., originality, feasibility, market value) and their weighting.

[0208] The evaluation criteria set by the administrator are stored on the server.

[0209] 3. Evaluating ideas

[0210] The server retrieves unrated ideas from the database, then generates prompts for the ideas to be rated.

[0211] The generated prompt is used to request an evaluation of the idea from the generative AI, which then performs text analysis and natural language processing according to the prompt to calculate an evaluation score based on each criterion.

[0212] 4. Selecting Valuable Ideas

[0213] The server calculates an overall score based on the weighting of the evaluation scores obtained from the generative artificial intelligence.

[0214] Ideas whose overall score exceeds the set standard are selected as worthy ideas.

[0215] 5. Notification of Results

[0216] The server will then send a notification to the submitter of the selected idea, including the evaluation score and the reason for the selection.

[0217] Hardware and software used

[0218] Server: A computer system that stores ideas received from users and set evaluation criteria, and runs generative artificial intelligence. A Linux (registered trademark)-based server or cloud service (e.g., Amazon Web Services, Google (registered trademark) Cloud Platform) can be used.

[0219] Generative AI: An AI model capable of natural language processing. Specifically, it uses OpenAI's GPT-3 (registered trademark).

[0220] Database: A system for managing data on saved ideas and evaluation criteria. An SQL database (e.g., MySQL (registered trademark), PostgreSQL) can be used.

[0221] Specific examples

[0222] A user submits an idea for an "eco-bag sharing service." The administrator sets the judging criteria as 50% originality, 30% feasibility, and 20% market value. The server retrieves unrated ideas and evaluates them using the following prompts from a generative AI:

[0223] Prompt Sentence Examples

[0224] "Please rate this new product idea. The title of the idea is 'Eco Bag Sharing Service' and the detailed description is 'We will create a system for sharing used eco bags to reduce environmental impact.' Please rate each item (originality, feasibility, market value) on a scale of 1 to 10 and return each score."

[0225] The generative AI analyzes the text based on the prompt and returns a score for each evaluation criterion. The server calculates the overall score based on the results, and if the score exceeds the criterion, a notification message is sent to the user. The notification includes the evaluation score and the reason for the selection, allowing the user to check the content.

[0226] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0227] Step 1:

[0228] Users use the official application to register their ideas. The data they enter is the idea title, detailed description, and related images and files. When the user clicks the "Submit" button, the device sends this data to the server as an API request.

[0229] Step 2:

[0230] The server receives the API request sent from the device and saves the idea data in the database. At this time, it generates a response confirming that the data was saved successfully and sends it back to the device. The server then notifies the user that the data was saved successfully.

[0231] Step 3:

[0232] The administrator sets the evaluation criteria from the application's administration screen. The data to be entered are evaluation criteria such as "originality," "feasibility," and "market value," along with their weighting (e.g., originality 50%, feasibility 30%, market value 20%). When the administrator clicks the "Set" button, the device sends this data to the server as an API request.

[0233] Step 4:

[0234] The server saves the evaluation criteria and their weights sent from the administrator's terminal in a database. At this time, it generates a response to confirm that the settings were completed successfully and returns it to the terminal. The server then notifies the administrator that the data was saved successfully.

[0235] Step 5:

[0236] The server retrieves unrated ideas from the database, then generates a prompt for each idea to rate it, including the idea's title and detailed description, and sends it to the generative AI model.

[0237] Step 6:

[0238] The server uses the generated prompt to request a generative AI (e.g., GPT-3) to evaluate the idea. The generative AI performs text analysis and natural language processing based on the prompt, and calculates a score for each criterion, such as originality, feasibility, and market value.

[0239] Step 7:

[0240] The server receives the scores returned by the generative AI and calculates an overall rating for each score based on the weights set by the administrator. For example, if originality is 7, feasibility is 8, and market value is 6, the overall rating score is calculated as (7 0.5 + 8 0.3 + 6 0.2).

[0241] Step 8:

[0242] The server selects valuable ideas based on the calculated overall evaluation score. Ideas whose overall evaluation score exceeds a set standard are selected and stored in a database.

[0243] Step 9:

[0244] The server will then send a notification to the submitter of the selected idea, including the evaluation score and the reason for the selection. The notification will be sent via in-app notification or email, and the user can check the content.

[0245] Step 10:

[0246] The user receives a notification from the server to know that their idea has been selected. The user can check the evaluation score and the reason for the selection in the notification and understand the details of how their idea was evaluated.

[0247] 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.

[0248] ---

[0249] The present invention provides a system that efficiently evaluates ideas received from users and selects valuable ideas, as well as a system that recognizes users' emotions and takes them into account in the evaluation results. This system can be implemented in the following manner.

[0250] System Overview

[0251] 1. Submit your idea

[0252] User: Using a web form or application, enter the "Title of the idea," "Detailed description," and "Related images and files (optional)."

[0253] User: Click the "Submit" button to submit your idea.

[0254] Terminal: Issues an API request to send user input data to the server.

[0255] Server: Receives API requests and stores the input idea data in a database.

[0256] Server: Returns a response to the user confirming that the idea was successfully submitted.

[0257] 2. Setting the screening criteria

[0258] User (Administrator): The administrator accesses the review criteria settings screen via the web interface or app.

[0259] User (Administrator): Enter evaluation criteria such as "originality," "feasibility," and "market value," and set the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[0260] Terminal: Sends the evaluation criteria and their weighting set by the administrator to the server.

[0261] Server: Stores the received criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[0262] 3. Evaluating ideas

[0263] Server: Retrieves unrated ideas from the database.

[0264] Server: Calls the generative AI to evaluate each idea based on the evaluation criteria set for each idea obtained.

[0265] Generative AI: It performs text analysis and natural language processing on each idea to calculate scores such as "originality," "feasibility," and "market value."

[0266] Generative AI: Based on the calculated score, the idea is given a final evaluation score, where an overall score is calculated using the set weights.

[0267] Server: Stores the evaluation scores returned by the generative AI in a database.

[0268] 4. Emotion evaluation using an emotion engine

[0269] Server: Utilizing the emotion engine, we obtain user emotion data when submitting an idea. This data is analyzed from the text and voice when the user enters the idea.

[0270] Emotion engine: Recognizes emotions from user input, facial expressions, and voice, and generates an emotion score such as positive or negative.

[0271] Server: Stores the sentiment scores in a database and adds them to the overall rating of the idea.

[0272] 5. Picking up valuable ideas

[0273] Server: Based on the evaluation and sentiment scores stored in the database, the server selects ideas that exceed a benchmark score, which is determined based on minimum criteria set by the administrator.

[0274] Server: compiles the ideas into a list and makes them accessible to users.

[0275] Terminal: Generates a screen displaying a list of picked ideas and shows it to the user.

[0276] 6. Notification of Results

[0277] Server: Sends emails and in-app notifications to submitters of selected ideas informing them of the evaluation results.

[0278] Users will receive a notification to find out if their idea was featured, along with a rating score, reasons for selection, and sentiment score for the idea.

[0279] Specific examples

[0280] When a user submits an idea for a "smart trash can," the device sends the data to the server, where the idea is stored in a database. The administrator sets the evaluation criteria, such as "originality," "feasibility," and "market value," and these are stored on the server.

[0281] The server uses generative AI to evaluate the "smart trash cans" and calculate a score based on each criterion. An emotion engine also analyzes the user's emotions at the time of submission and generates an emotion score. If the overall score exceeds the criteria, the server selects the idea as a valuable idea, and the device displays a list of the ideas. Finally, the user receives a notification, where they can view the emotion score along with the evaluation results.

[0282] In this way, the system of the present invention can efficiently and fairly carry out the entire process from soliciting ideas from users to ultimately selecting valuable ideas. This significantly improves the accuracy and efficiency of the idea discovery process in companies and organizations. Furthermore, by taking user emotions into account, a more human-like evaluation system can be realized.

[0283] The processing flow will be explained below.

[0284] Program processing flow

[0285] Step 1:

[0286] A user uses a web form or application to enter an idea title, a detailed description, and optional related images and files.

[0287] Step 2:

[0288] The user clicks the "Send" button, and the terminal sends the idea data to the server.

[0289] Step 3:

[0290] The server receives the API request and stores the input idea data in a database.

[0291] Step 4:

[0292] The server returns a response confirming to the user that the idea was successfully submitted.

[0293] Step 5:

[0294] The user (administrator) accesses the review criteria settings screen via the web interface or app.

[0295] Step 6:

[0296] The user (administrator) inputs evaluation criteria such as "originality," "feasibility," and "market value," and sets the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[0297] Step 7:

[0298] The terminal sends the evaluation criteria and their weighting set by the administrator to the server.

[0299] Step 8:

[0300] The server stores the received evaluation criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[0301] Step 9:

[0302] The server retrieves unrated ideas from the database.

[0303] Step 10:

[0304] The server calls a generative AI to evaluate each idea it receives based on the evaluation criteria set for each idea.

[0305] Step 11:

[0306] Generative AI performs text analysis and natural language processing on each idea, calculating scores for "originality," "feasibility," "market value," and other factors.

[0307] Step 12:

[0308] Based on the calculated scores, the generative AI assigns a final evaluation score to the idea, which calculates an overall score using the weights you set.

[0309] Step 13:

[0310] The server stores the evaluation scores returned by the generative AI in a database.

[0311] Step 14:

[0312] The server uses an emotion engine to acquire the user's emotion data when submitting an idea.

[0313] Step 15:

[0314] The emotion engine recognizes emotions from the user's input, facial expressions, and voice, and generates an emotion score such as positive or negative.

[0315] Step 16:

[0316] The server stores the emotion scores in a database and adds them to the overall evaluation of the idea.

[0317] Step 17:

[0318] The server selects ideas that exceed the standard score based on the evaluation scores and sentiment scores stored in the database.

[0319] Step 18:

[0320] The server compiles a list of picked ideas and makes them accessible to users.

[0321] Step 19:

[0322] The device generates a screen displaying a list of the picked ideas and shows it to the user.

[0323] Step 20:

[0324] The server will send an email or in-app notification to the submitter of the picked idea informing them of the evaluation results.

[0325] Step 21:

[0326] Users will receive a notification to find out if their idea was featured, along with a rating score, reasons for selection, and sentiment score for the idea.

[0327] Through the above steps, the system of the present invention can efficiently and fairly collect ideas from users, select the most valuable ideas, and evaluate them while taking their emotions into consideration.

[0328] Example 2

[0329] 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."

[0330] Conventional idea evaluation systems have difficulty in efficiently and fairly evaluating ideas submitted by users, and in particular, they lack consideration of user emotions in their evaluations. As a result, there is a problem in which valuable ideas are not properly selected.

[0331] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for storing ideas received from users, a means for storing evaluation criteria set by an administrator, a means for evaluating ideas using a generative AI model, a means for analyzing user emotion data using an emotion engine and generating an emotion score, a means for selecting valuable ideas based on the evaluation results and the emotion score, and a means for notifying the user of the results of the selected ideas. This allows ideas to be evaluated efficiently and fairly, and by taking user emotions into consideration, more appropriate and valuable ideas can be selected.

[0332] "User" refers to a user who submits an idea to the system.

[0333] "Administrator" refers to the person in charge of setting the system's review criteria and managing the system as a whole.

[0334] "Evaluation criteria" refers to the criteria for evaluating ideas, including items such as originality, feasibility, and market value.

[0335] A "generative AI model" is an artificial intelligence model used to evaluate ideas, using text analysis and natural language processing techniques.

[0336] An "emotion engine" refers to a technology that analyzes a user's emotional data and generates an emotional score, such as positive or negative.

[0337] "Evaluation results" refers to the aggregated scores and evaluations of ideas calculated by the generative AI model.

[0338] "Emotion score" refers to a numerical representation of a user's emotional state calculated by the emotion engine.

[0339] "Valuable Ideas" refer to useful ideas that have been comprehensively evaluated and selected based on set evaluation criteria and emotional scores.

[0340] "Notification" refers to a means of communication to inform users of the evaluation results and information about selected ideas.

[0341] System Overview

[0342] This invention is a system that efficiently evaluates ideas submitted by users and selects valuable ideas. It also recognizes the user's emotions and incorporates them into the evaluation results. This system utilizes the following hardware and software:

[0343] Server: Stores ideas and evaluation data in a database and interacts with generative AI models and emotion engines.

[0344] Terminal: Provides an interface for users and administrators to access and send and receive data.

[0345] Users: Submit ideas and receive notifications of results.

[0346] Specific processing of the system

[0347] Submit your idea

[0348] The user uses a web form or application to enter the "idea title," "detailed description," and "related images and files (optional)." When the user clicks the "Submit" button, the device sends the data to the server. The server receives the API request, saves the idea in a database, and notifies the user that the idea has been successfully submitted.

[0349] Setting the review criteria

[0350] The user (administrator) accesses the evaluation criteria setting screen and sets evaluation criteria such as "originality," "feasibility," and "market value" along with the weighting of each. The terminal sends the setting information to the server, which stores the data in a database. The server also notifies the administrator that the setting was successful.

[0351] Idea Evaluation

[0352] The server retrieves unrated ideas from the database. For each idea, the server invokes a generative AI model and performs text analysis and natural language processing to calculate scores for "originality," "feasibility," "market value," etc. The evaluation results are returned to the server, which calculates an overall score and stores it in the database.

[0353] Emotion evaluation by emotion engine

[0354] The server uses an emotion engine to obtain the user's emotion data when they submit an idea. It recognizes emotions from the user's input, facial expressions, and voice, and generates an emotion score. The emotion score is stored in a database and is reflected in the overall evaluation of the idea.

[0355] Picking up valuable ideas

[0356] The server selects ideas that exceed the benchmark score based on the evaluation score and sentiment score, and the selected ideas are displayed in a list on the terminal for user access.

[0357] Notification of results

[0358] Finally, the server generates an email or in-app notification to the submitter of the selected idea informing them of the evaluation result. Users can receive the notification and check whether their idea was selected. The notification also includes the idea's evaluation score, the reason for selection, and the sentiment score.

[0359] Specific examples

[0360] When a user submits an idea for a "smart trash can," the device sends the data to the server, and the idea is saved in a database. An administrator sets the evaluation criteria of "originality," "feasibility," and "market value," which are saved on the server. The server uses a generative AI model to evaluate the "smart trash can" and calculates a score based on each criterion. An emotion engine also analyzes the user's emotions at the time of submission and generates an emotion score. If the overall score exceeds the criteria, the server selects the idea as a valuable idea, and the device displays a list. Finally, the user is notified and can check the emotion score along with the evaluation results.

[0361] Prompt Sentence Examples

[0362] Please calculate a score for the idea "Smart Trash Can" based on the following criteria: Originality 50%, Feasibility 30%, Market Value 20%. Also, please consider the user's sentiment (positive or negative) at the time of submission and give an overall score.

[0363] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0364] Step 1: Submit your idea

[0365] A user opens a web form or application and enters the "idea title," "detailed description," and "related images and files (optional)." For example, a user enters the title "Smart Trash Can" and a specific description.

[0366] Input: Title, description, related images and files

[0367] The device incorporates the user's input data into an API request and sends it to the server in JSON format.

[0368] The server receives the API request and checks the data format and required fields, for example, whether the title is empty and whether a detailed description is provided.

[0369] Output: Save notification

[0370] If there are no problems, the server saves the idea in a database and generates a response informing the user that the idea was successfully submitted.

[0371] Step 2: Setting the review criteria

[0372] The user (administrator) accesses the evaluation criteria setting screen and sets evaluation criteria such as "originality," "feasibility," and "market value" and the weighting of each.

[0373] Input: Judging criteria and weighting

[0374] The device incorporates the set evaluation criteria and their weighting into an API request and sends it to the server.

[0375] The server stores the received evaluation criteria and weights, and performs database operations for storage.

[0376] Output: Configuration confirmation notice

[0377] The server generates and sends a response to the administrator indicating that the setting was successful.

[0378] Step 3: Evaluate your ideas

[0379] The server retrieves unrated ideas from the database, for example the most recently added "smart trash can" idea.

[0380] Input: Unrated idea data

[0381] The server calls a generative AI model for each idea it receives, using the set evaluation criteria as prompts.

[0382] The generative AI model performs text analysis and natural language processing on each idea to calculate scores for originality, feasibility, market value, etc. For example, for the prompt sentence "smart trash can," the overall score is calculated with weights of 50% for originality, 30% for feasibility, and 20% for market value.

[0383] Output: Evaluation score

[0384] The generative AI model calculates a final evaluation score based on the calculated scores and returns it to the server, which stores the score in a database.

[0385] Step 4: Emotion evaluation by the emotion engine

[0386] The server uses an emotion engine to obtain user emotion data when an idea is submitted, for example by analyzing text or voice data.

[0387] Input: User text and voice data

[0388] The emotion engine recognizes emotions from the user's input, facial expressions, and voice, and generates an emotion score such as positive or negative.

[0389] Output: Sentiment score

[0390] The server stores the generated emotion scores in a database and adds them to the overall evaluation of the idea.

[0391] Step 5: Identifying valuable ideas

[0392] The server selects ideas that exceed a threshold score based on their rating and sentiment scores, which are based on minimum criteria set by the administrator.

[0393] Input: Rating score, sentiment score, criteria score

[0394] The server compiles a list of the selected ideas and makes it accessible to users.

[0395] Output: List of selected ideas

[0396] The device generates a screen displaying a list of the ideas picked up and shows it to the user. By providing a user-friendly interface, the user can easily and quickly check the evaluation results.

[0397] Step 6: Notification of results

[0398] The server generates emails and in-app notifications to the submitters of the selected ideas informing them of the evaluation results.

[0399] Input: Picked idea data, user contact information

[0400] The server generates and sends a notification to the submitter, which includes the rating score, the reason for selection, and the sentiment score.

[0401] Output: Information message

[0402] Users will receive a notification to see if their idea has been picked up, and can use the information in the notification to decide what to do next.

[0403] (Application example 2)

[0404] 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."

[0405] Conventional idea evaluation systems do not take into account the user's emotions when evaluating ideas submitted by users, resulting in a lack of human-like evaluation and the possibility of overlooking high-quality ideas. Furthermore, the evaluation process is inefficient, making it difficult to process when a large number of ideas are submitted.

[0406] The identification process 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 storing ideas received from users, means for storing evaluation criteria set by an administrator, means for evaluating the ideas using a generative AI based on the stored ideas, means for acquiring user emotion data and performing emotion recognition, means for selecting valuable ideas based on the evaluation results and the emotion data, and means for notifying the user of the results of the selected ideas. This enables human-like evaluation that takes user emotions into consideration, making it possible to evaluate many ideas efficiently and fairly.

[0407] "User" means an individual or organization that submits an idea and receives the evaluation results.

[0408] "Administrator" refers to the person or organization that sets the system's review criteria and oversees the idea evaluation and selection process.

[0409] An "idea" is a specific proposal for a new product or service that a user has invented.

[0410] "Evaluation criteria" are indicators used to evaluate ideas, and include criteria such as "originality," "feasibility," and "market value."

[0411] "Generative AI" is an artificial intelligence system that uses text analysis and natural language processing to automatically evaluate ideas.

[0412] "Emotion data" is data that indicates the user's emotions at the time of submitting the idea, and is obtained from text, facial expressions, voice, etc.

[0413] "Emotion recognition" is the process of analyzing a user's emotional data and determining whether the emotion is positive or negative.

[0414] "Evaluation results" refer to the evaluation scores for each idea calculated using generative AI and emotion recognition technology.

[0415] A "valuable idea" is an idea that receives a high rating based on established evaluation criteria and evaluation using emotional data.

[0416] "Notification methods" are mechanisms for informing users of the evaluation results and information about selected ideas, and include email and in-app notifications.

[0417] The system of the present invention is capable of efficiently evaluating ideas submitted by users and performing a comprehensive evaluation that takes into account the user's emotions. The system operates by appropriately arranging hardware and software. A specific example of the system is shown below.

[0418] Hardware and Software Configuration

[0419] server:

[0420] Role: Central data processing and management.

[0421] Software: Flask (a Python web application framework), database (e.g., MySQL), generative AI model (natural language processing), emotion recognition engine.

[0422] Device:

[0423] Role: Provides an interface for users to submit ideas.

[0424] Software: Web forms and custom applications.

[0425] User:

[0426] Role: Submit ideas and review evaluation results.

[0427] System Operation

[0428] Submit your idea

[0429] Users enter their ideas and related data through a web form or a dedicated application and send it to the server, which receives it and stores it in a database, allowing users to register their ideas in the system.

[0430] Setting the review criteria

[0431] Administrators set the judging criteria through a web interface or application, which are then stored in a database by the server, establishing the criteria necessary for evaluating ideas.

[0432] Idea Evaluation

[0433] The server calls a generative AI model, analyzes the text of the registered idea, and evaluates it. This generative AI calculates scores for "originality," "feasibility," "market value," and other factors, and returns the results to the server. At the same time, an emotion recognition engine is used to analyze the emotions felt when the user inputs the idea. Emotional data is obtained from voice and text, and a score such as positive or negative is generated.

[0434] Effective evaluation and communication of results

[0435] The server combines the evaluation score and sentiment score to calculate an overall score. Ideas whose overall score meets certain criteria are selected and the result is notified to the user via email or in-app notification, allowing the user to check the evaluation results.

[0436] Specific examples

[0437] For example, if a user submits an idea for a "smart trash can," the system works as follows: The user inputs the text of the idea and sends it to the server along with its emotional data. The server uses a generative AI model to evaluate the idea and calculates scores for "originality," "feasibility," and "market value." At the same time, an emotional recognition engine analyzes the user's emotional data and generates a positive emotional score. An overall score is calculated, and if it meets the criteria, the user is notified.

[0438] Example prompt sentence:

[0439] A user submitted a new product idea: "Health management system using a smartwatch."

[0440] Please rate this idea's "originality," "feasibility," and "market value."

[0441] In your evaluation results, please include a score (1-10) for each item and the reason for your score.

[0442] In this way, the system of the present invention realizes human-like evaluation that takes into account the user's emotions, and by efficiently evaluating many ideas, it is possible to pick out valuable ideas.

[0443] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0444] Step 1:

[0445] Users input their ideas through a web form or application on their device. This includes the text data of the idea, related images and files, and the user's emotional data (voice, facial expressions, etc.). Once the input data is ready, they click the "Send" button. Clicking the Send button becomes an input event, and the device sends the input data to the server as an API request.

[0446] Step 2:

[0447] The server receives the API request and saves the received data in the database. It stores the idea text data, related files, and emotion data in the appropriate tables in the database, and returns a response to the device indicating that the save operation was successful, allowing the user to confirm that their idea was successfully submitted.

[0448] Step 3:

[0449] The administrator sets the evaluation criteria using a web interface or application. They input the evaluation criteria, such as "originality," "feasibility," and "market value," to be used to evaluate users' ideas, along with their respective weights (e.g., originality 50%, feasibility 30%, market value 20%), and click "Save." The device then sends this setting data to the server.

[0450] Step 4:

[0451] The server saves the evaluation criteria data received from the administrator in the database and returns a response indicating that the save operation was successful to the administrator's terminal. This ensures that the evaluation criteria are applied to the system and will be used for the next idea evaluation.

[0452] Step 5:

[0453] The server retrieves unrated ideas from the database. Based on the retrieved idea data, it invokes a generative AI model to perform text analysis and natural language processing. This calculates scores for each idea in terms of "originality," "feasibility," and "market value," and returns these to the server. The output is idea evaluation data with each score assigned.

[0454] Step 6:

[0455] The server passes the emotional data acquired from the user when submitting the idea to the emotion recognition engine for emotion analysis. The emotion recognition engine analyzes the voice and facial expression data and generates an emotional score, such as positive or negative. This emotional score is returned to the server and added to the evaluation data.

[0456] Step 7:

[0457] The server combines the scores obtained from the generative AI model and the emotion recognition engine to calculate an overall evaluation score. It then calculates a weighted average of each score based on the weights of the set evaluation criteria to calculate a final overall score. Ideas whose overall score meets certain criteria are selected as valuable ideas.

[0458] Step 8:

[0459] The server stores the evaluation results of the selected worthy ideas in a database. It then generates emails or in-app notifications to inform users of the results of the selected ideas. The notifications include details of the evaluation results (individual scores, overall score, and sentiment score) to ensure users fully understand the evaluation process.

[0460] Step 9:

[0461] Users will receive a notification to check the results of their idea evaluation. By clicking the link in the notification, they can view the detailed evaluation results through a web interface or application. This allows users to understand how their idea was evaluated and get hints for improvement.

[0462] Through this series of processes, users submit ideas and receive evaluation results, which motivates them to submit higher quality ideas and improves the quality of the entire system.

[0463] 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.

[0464] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0465] 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.

[0466] [Second embodiment]

[0467] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0468] 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.

[0469] 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).

[0470] 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.

[0471] 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.

[0472] 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).

[0473] 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.

[0474] 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.

[0475] 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.

[0476] 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.

[0477] 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.

[0478] 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."

[0479] ---

[0480] The present invention provides a system for efficiently evaluating ideas received from users and selecting valuable ideas. This system is implemented in the following manner.

[0481] System Overview

[0482] 1. Submit your idea

[0483] User: Enter the "Title of the idea," "Detailed description," and "Related images and files (optional)" using a web form or application.

[0484] User: Click the "Submit" button to submit your idea.

[0485] Terminal: Issues an API request to send user input data to the server.

[0486] Server: Receives API requests and stores the input idea data in a database.

[0487] Server: Returns a response to the user confirming that the idea was successfully submitted.

[0488] 2. Setting the screening criteria

[0489] User (Administrator): The administrator accesses the review criteria settings screen via the web interface or app.

[0490] User (Administrator): Enter evaluation criteria such as "originality," "feasibility," and "market value," and set the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[0491] Terminal: Sends the evaluation criteria and their weighting set by the administrator to the server.

[0492] Server: Stores the received criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[0493] 3. Evaluating ideas

[0494] Server: Retrieves unrated ideas from the database.

[0495] Server: Calls the generative AI to evaluate each idea based on the evaluation criteria set for each idea obtained.

[0496] Generative AI: It performs text analysis and natural language processing on each idea to calculate scores such as "originality," "feasibility," and "market value."

[0497] Generative AI: Based on the calculated score, the idea is given a final evaluation score, where an overall score is calculated using the set weights.

[0498] Server: Stores the evaluation scores returned by the generative AI in a database.

[0499] 4. Picking up valuable ideas

[0500] Server: Based on the evaluation scores stored in the database, ideas that exceed the standard score are selected. The standard score is determined based on the minimum criteria set by the administrator.

[0501] Server: compiles the ideas into a list and makes them accessible to users.

[0502] Terminal: Generates a screen displaying a list of picked ideas and shows it to the user.

[0503] 5. Notification of Results

[0504] Server: Sends emails and in-app notifications to submitters of selected ideas informing them of the evaluation results.

[0505] Users will receive a notification to find out if their idea was featured, including the rating score and reasons for its selection.

[0506] Specific examples

[0507] When a user submits an idea for a "smart trash can," the device sends the data to the server, where the idea is stored in a database. The administrator sets the evaluation criteria, such as "originality," "feasibility," and "market value," and these are stored on the server.

[0508] The server uses generative AI to evaluate the "smart trash cans" and calculate a score based on each criterion. If the overall score exceeds the criterion, the server will select the idea as a valuable idea, and the device will display a list. Finally, the user will be notified and can check the evaluation results.

[0509] In this way, the system of the present invention can efficiently and fairly carry out the entire process from soliciting ideas from users to ultimately selecting valuable ideas, significantly improving the accuracy and efficiency of the idea discovery process in companies and organizations.

[0510] The processing flow will be explained below.

[0511] Program processing flow

[0512] Step 1:

[0513] A user uses a web form or application to enter an idea title, a detailed description, and optional related images and files.

[0514] Step 2:

[0515] The user clicks the "Send" button, and the terminal sends the idea data to the server.

[0516] Step 3:

[0517] The server receives the API request and stores the input idea data in a database.

[0518] Step 4:

[0519] The server returns a response confirming to the user that the idea was successfully submitted.

[0520] Step 5:

[0521] The user (administrator) accesses the review criteria settings screen via the web interface or app.

[0522] Step 6:

[0523] The user (administrator) inputs evaluation criteria such as "originality," "feasibility," and "market value," and sets the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[0524] Step 7:

[0525] The terminal sends the evaluation criteria and their weighting set by the administrator to the server.

[0526] Step 8:

[0527] The server stores the received evaluation criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[0528] Step 9:

[0529] The server retrieves unrated ideas from the database.

[0530] Step 10:

[0531] The server calls a generative AI to evaluate each idea it receives based on the evaluation criteria set for each idea.

[0532] Step 11:

[0533] Generative AI performs text analysis and natural language processing on each idea, calculating scores for "originality," "feasibility," "market value," and other factors.

[0534] Step 12:

[0535] Based on the calculated scores, the generative AI assigns a final evaluation score to the idea, which calculates an overall score using the weights you set.

[0536] Step 13:

[0537] The server stores the evaluation scores returned by the generative AI in a database.

[0538] Step 14:

[0539] The server selects ideas that exceed a benchmark score based on the evaluation scores stored in the database, which is determined based on minimum criteria set by the administrator.

[0540] Step 15:

[0541] The server compiles a list of picked ideas and makes them accessible to users.

[0542] Step 16:

[0543] The device generates a screen displaying a list of the picked ideas and shows it to the user.

[0544] Step 17:

[0545] The server will send an email or in-app notification to the submitter of the picked idea informing them of the evaluation results.

[0546] Step 18:

[0547] Users will receive a notification to find out if their idea was featured, along with a rating score and reasons for its selection.

[0548] Example 1

[0549] 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."

[0550] It is important for companies and organizations to efficiently evaluate the many ideas submitted by users and appropriately select the most valuable ideas. However, manual evaluation requires time and effort, and there is a possibility that subjective judgments may be involved, making it inefficient and impartial.

[0551] 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.

[0552] In this invention, the server includes means for storing ideas received from users, means for storing evaluation criteria set by an administrator, means for evaluating the ideas using a generative AI model based on the stored ideas, means for selecting valuable ideas that exceed a standard score based on the evaluation scores, and means for notifying users of the evaluation results of the selected ideas. This makes it possible to efficiently and fairly evaluate received ideas and quickly select valuable ideas.

[0553] "User" means any person or entity that uses the System to submit Ideas.

[0554] "Administrator" means an individual or organization responsible for the operation and management of the system and with the authority to set screening criteria.

[0555] "Idea" refers to a new proposal, concept or idea submitted by a user.

[0556] The "evaluation criteria" are the evaluation criteria for ideas set by the administrator, and include multiple evaluation items such as originality, feasibility, and market value.

[0557] "Generative AI model" refers to an artificial intelligence algorithm that evaluates user-submitted ideas using text analysis and natural language processing techniques.

[0558] An "evaluation score" is a score or number that the generative AI model assigns to each idea based on the evaluation criteria.

[0559] The "baseline score" refers to the minimum evaluation score required to select a worthy idea, and is set by the administrator.

[0560] A "valuable idea" is an idea whose evaluation score exceeds the standard score and is judged to be beneficial to users and companies.

[0561] "Notification means" refers to the method by which the server communicates the evaluation results to the user, and includes email, in-app notifications, etc.

[0562] The present invention relates to a system for efficiently evaluating ideas received from users and selecting valuable ideas. The system is composed of users, terminals, and a server.

[0563] System Configuration

[0564] 1. User: Submits an idea using a web form or application by entering the "idea title," "detailed description," and "related images and files (optional)."

[0565] 2. Terminal: Receives user input data and sends it to the server by sending an HTTP POST request to the API endpoint and including the idea data.

[0566] 3. Server:

[0567] Save Idea: Receives an API request and saves the entered idea data to the database. Executes a SQL insert statement.

[0568] Saving the criteria: The criteria received from the administrator (originality, feasibility, market value) and their respective weights are saved in the database using SQL insert or update statements.

[0569] Evaluate ideas: Retrieve unrated ideas from the database and invoke the generative AI model by sending an API request, including the idea data and evaluation criteria.

[0570] Evaluation-based selection: The generative AI model evaluates ideas using text analysis and natural language processing techniques, calculates a score based on each evaluation criterion, and then calculates a final score using the calculated scores to select ideas that exceed the standard score.

[0571] Notification method: The submitters of selected ideas will be notified of the evaluation results via email and / or in-app notification.

[0572] Hardware and Software Configuration

[0573] Hardware: Server, client terminal (PC, smartphone, tablet, etc.)

[0574] software:

[0575] Front-end: web forms, applications

[0576] Backend: API endpoints, database (SQL)

[0577] Generative AI models: natural language processing libraries, text analysis tools

[0578] Specific examples

[0579] A user submits an idea for a "smart trash can." For example, "a trash can with a function that automatically calls a trash collection service when a certain amount of trash accumulates." The device sends the data to the server using an HTTP POST request, and the server stores the data in a database.

[0580] The administrator will set the following evaluation criteria and weightings.

[0581] Originality: 50%

[0582] Likelihood: 30%

[0583] Market value: 20%

[0584] AI assessment prompt example

[0585] A "smart trash can" is a trash can that automatically calls a trash collection service when a certain amount of trash has accumulated. Please rate this idea using the following criteria.

[0586] Originality: 50%

[0587] Likelihood: 30%

[0588] Market value: 20%

[0589] The server sends this prompt to the generative AI model, which then calculates a score based on each criterion. For example, if the AI ​​scores "originality: 90 points, feasibility: 70 points, market value: 80 points," it will calculate an overall score taking into account the weights. The overall score is calculated as follows:

[0590] Total score = (originality score × originality weight) + (feasibility score × feasibility weight) + (market value score × market value weight)

[0591] = (90 × 0.5) + (70 × 0.3) + (80 × 0.2)

[0592] = 45 + 21 + 16

[0593] = 82

[0594] If the total score exceeds a threshold (e.g., 75 points), the server selects the idea as valuable and notifies the user. This allows the system of the present invention to efficiently evaluate ideas and select them fairly.

[0595] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0596] Step 1:

[0597] Submit your idea

[0598] User: Using a web form or application, enter the "Title of the idea," "Detailed description," and "Related images and files (optional)," then click the "Submit" button.

[0599] Terminal: Takes user input data and sends it to the API endpoint in an HTTP POST request, including the idea title, detailed description, and associated files.

[0600] Server: Receives the API request and executes an INSERT statement to save the idea data in the database. Example: INSERT INTO ideas (title, description, files) VALUES (?, ?, ?)

[0601] Server: Returns an HTTP response (200 OK) to the user confirming that the idea was successfully submitted. The response includes a confirmation message.

[0602] Step 2:

[0603] Setting the review criteria

[0604] User (Administrator): Access the judging criteria setting screen via the web interface or app, and enter judging criteria such as "originality," "feasibility," and "market value" along with their respective weightings (e.g., originality 50%, feasibility 30%, market value 20%).

[0605] Terminal: Takes the administrator's input and sends it to the server via an HTTP POST request, which includes the criteria and their weights.

[0606] Server: Store the received criteria and weights in the database. Example: INSERT INTO criteria (originality_weight, feasibility_weight, market_value_weight) VALUES (?, ?, ?)

[0607] Server: Returns an HTTP response (200 OK) to the administrator confirming that the review criteria were successfully set. This response includes a confirmation message.

[0608] Step 3:

[0609] Idea Evaluation

[0610] Server: Get unrated ideas from the database. Example: SELECT FROM ideas WHERE evaluated = false

[0611] Server: Calls the generative AI model to evaluate each idea based on the evaluation criteria set for each idea. Generates prompts to send to the AI ​​model.

[0612] Generative AI model: Receives API requests and evaluates ideas using text analysis and natural language processing techniques, calculating scores (originality, feasibility, market value) based on each evaluation criteria.

[0613] Generative AI model: Returns the calculated score to the server, which includes the score for each assessment item and the final evaluation score.

[0614] Server: Using the received scores, calculate the total score by multiplying each score by the weight set in the evaluation criteria. Example: total_score = (originality_score originality_weight) + (feasibility_score feasibility_weight) + (market_value_score market_value_weight)

[0615] Server: Save the calculated total score to the database and update the idea's evaluated flag. Example: UPDATE ideas SET total_score = ?, evaluated = true WHERE id = ?

[0616] Step 4:

[0617] Picking up valuable ideas

[0618] Server: Select ideas from the database whose total score exceeds the threshold score. Example: SELECT FROM ideas WHERE total_score >= ?

[0619] Server: Compiles the selected ideas into a list and formats them in an accessible format (e.g. HTML or JSON).

[0620] Terminal: Renders the data received from the server and generates a screen displaying a list of valuable ideas for the user.

[0621] Step 5:

[0622] Notification of results

[0623] Server: Sends emails and in-app notifications to the winners of the ideas, including the score and reasons for the idea's selection.

[0624] Users: Receive notifications to find out if their ideas are selected as valuable ideas.

[0625] In this way, each processing step of the system is carried out efficiently through cooperation between users, terminals, and servers, from idea submission to evaluation, selection, and notification.

[0626] (Application example 1)

[0627] 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."

[0628] In recent years, there has been an increasing demand for efficient and fair evaluation in idea solicitation and selection. However, manual evaluation is time-consuming and laborious, and it is difficult to ensure fairness. While generative artificial intelligence (AI) is an alternative, it poses challenges, such as the difficulty of designing appropriate prompts to effectively evaluate ideas and the difficulty of calculating an overall evaluation by weighting the evaluation criteria. Furthermore, the process of quickly notifying evaluation results and providing feedback to users must be efficient.

[0629] 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.

[0630] In this invention, the server includes means for storing ideas received from users, means for storing evaluation criteria set by an administrator, means for evaluating ideas using a generative artificial intelligence, means for generating prompt sentences for ideas to be evaluated, means for requesting the generative artificial intelligence to evaluate the ideas using the prompt sentences, means for selecting valuable ideas based on the evaluation results, and means for notifying users of the results of the selected ideas. This makes it possible to evaluate ideas efficiently and fairly and provide prompt feedback to users.

[0631] "Users" are members of the public who submit ideas and suggestions.

[0632] An "Administrator" is a person or entity with the authority to set the criteria for evaluating ideas and oversee the evaluation process.

[0633] "Ideas" are new ideas or improvements suggested by users.

[0634] "Evaluation criteria" are measures such as originality, feasibility, and market value used to evaluate ideas.

[0635] "Generative AI" is AI that has the ability to evaluate ideas using natural language processing and text analysis.

[0636] A "prompt" is a specific instruction used when evaluating ideas using generative artificial intelligence.

[0637] The "evaluation result" is the score of the idea calculated by the generative artificial intelligence.

[0638] A "worthy idea" is an idea that receives a high rating based on the established evaluation criteria.

[0639] "Notification" is a message that notifies the user of the evaluation results or selection results.

[0640] A "server" is a computer system that stores ideas submitted by users and set evaluation criteria, and runs the generative artificial intelligence.

[0641] The present invention relates to a system for efficiently and fairly evaluating ideas received from users and selecting valuable ideas. This system includes the processes of registering ideas, setting review criteria by an administrator, evaluation by generative artificial intelligence, selection, and notification.

[0642] System Overview

[0643] 1. Submit your idea

[0644] Users can use the official application to register "new product ideas" and "improvement suggestions." Ideas can include titles, detailed descriptions, related images, files, and other attachments.

[0645] When the send button is clicked, data is sent from the terminal to the server.

[0646] 2. Setting the screening criteria

[0647] Administrators access the administrator screen within the app to set the evaluation criteria (e.g., originality, feasibility, market value) and their weighting.

[0648] The evaluation criteria set by the administrator are stored on the server.

[0649] 3. Evaluating ideas

[0650] The server retrieves unrated ideas from the database, then generates prompts for the ideas to be rated.

[0651] The generated prompt is used to request an evaluation of the idea from the generative AI, which then performs text analysis and natural language processing according to the prompt to calculate an evaluation score based on each criterion.

[0652] 4. Selecting Valuable Ideas

[0653] The server calculates an overall score based on the weighting of the evaluation scores obtained from the generative artificial intelligence.

[0654] Ideas whose overall score exceeds the set standard are selected as worthy ideas.

[0655] 5. Notification of Results

[0656] The server will then send a notification to the submitter of the selected idea, including the evaluation score and the reason for the selection.

[0657] Hardware and software used

[0658] Server: A computer system that stores ideas received from users and set evaluation criteria, and runs generative AI. A Linux-based server or cloud service (e.g., Amazon Web Services, Google Cloud Platform) can be used.

[0659] Generative AI: An AI model capable of natural language processing. Specifically, OpenAI's GPT-3 is used.

[0660] Database: A system for managing data on stored ideas and evaluation criteria. An SQL database (e.g., MySQL, PostgreSQL) can be used.

[0661] Specific examples

[0662] A user submits an idea for an "eco-bag sharing service." The administrator sets the judging criteria as 50% originality, 30% feasibility, and 20% market value. The server retrieves unrated ideas and evaluates them using the following prompts from a generative AI:

[0663] Prompt Sentence Examples

[0664] "Please rate this new product idea. The title of the idea is 'Eco Bag Sharing Service' and the detailed description is 'We will create a system for sharing used eco bags to reduce environmental impact.' Please rate each item (originality, feasibility, market value) on a scale of 1 to 10 and return each score."

[0665] The generative AI analyzes the text based on the prompt and returns a score for each evaluation criterion. The server calculates the overall score based on the results, and if the score exceeds the criterion, a notification message is sent to the user. The notification includes the evaluation score and the reason for the selection, allowing the user to check the content.

[0666] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0667] Step 1:

[0668] Users use the official application to register their ideas. The data they enter is the idea title, detailed description, and related images and files. When the user clicks the "Submit" button, the device sends this data to the server as an API request.

[0669] Step 2:

[0670] The server receives the API request sent from the device and saves the idea data in the database. At this time, it generates a response confirming that the data was saved successfully and sends it back to the device. The server then notifies the user that the data was saved successfully.

[0671] Step 3:

[0672] The administrator sets the evaluation criteria from the application's administration screen. The data to be entered are evaluation criteria such as "originality," "feasibility," and "market value," along with their weighting (e.g., originality 50%, feasibility 30%, market value 20%). When the administrator clicks the "Set" button, the device sends this data to the server as an API request.

[0673] Step 4:

[0674] The server saves the evaluation criteria and their weights sent from the administrator's terminal in a database. At this time, it generates a response to confirm that the settings were completed successfully and returns it to the terminal. The server then notifies the administrator that the data was saved successfully.

[0675] Step 5:

[0676] The server retrieves unrated ideas from the database, then generates a prompt for each idea to rate it, including the idea's title and detailed description, and sends it to the generative AI model.

[0677] Step 6:

[0678] The server uses the generated prompt to request a generative AI (e.g., GPT-3) to evaluate the idea. The generative AI performs text analysis and natural language processing based on the prompt, and calculates a score for each criterion, such as originality, feasibility, and market value.

[0679] Step 7:

[0680] The server receives the scores returned by the generative AI and calculates an overall rating for each score based on the weights set by the administrator. For example, if originality is 7, feasibility is 8, and market value is 6, the overall rating score is calculated as (7 0.5 + 8 0.3 + 6 0.2).

[0681] Step 8:

[0682] The server selects valuable ideas based on the calculated overall evaluation score. Ideas whose overall evaluation score exceeds a set standard are selected and stored in a database.

[0683] Step 9:

[0684] The server will then send a notification to the submitter of the selected idea, including the evaluation score and the reason for the selection. The notification will be sent via in-app notification or email, and the user can check the content.

[0685] Step 10:

[0686] The user receives a notification from the server to know that their idea has been selected. The user can check the evaluation score and the reason for the selection in the notification and understand the details of how their idea was evaluated.

[0687] 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.

[0688] ---

[0689] The present invention provides a system that efficiently evaluates ideas received from users and selects valuable ideas, as well as a system that recognizes users' emotions and takes them into account in the evaluation results. This system can be implemented in the following manner.

[0690] System Overview

[0691] 1. Submit your idea

[0692] User: Using a web form or application, enter the "Title of the idea," "Detailed description," and "Related images and files (optional)."

[0693] User: Click the "Submit" button to submit your idea.

[0694] Terminal: Issues an API request to send user input data to the server.

[0695] Server: Receives API requests and stores the input idea data in a database.

[0696] Server: Returns a response to the user confirming that the idea was successfully submitted.

[0697] 2. Setting the screening criteria

[0698] User (Administrator): The administrator accesses the review criteria settings screen via the web interface or app.

[0699] User (Administrator): Enter evaluation criteria such as "originality," "feasibility," and "market value," and set the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[0700] Terminal: Sends the evaluation criteria and their weighting set by the administrator to the server.

[0701] Server: Stores the received criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[0702] 3. Evaluating ideas

[0703] Server: Retrieves unrated ideas from the database.

[0704] Server: Calls the generative AI to evaluate each idea based on the evaluation criteria set for each idea obtained.

[0705] Generative AI: It performs text analysis and natural language processing on each idea to calculate scores such as "originality," "feasibility," and "market value."

[0706] Generative AI: Based on the calculated score, the idea is given a final evaluation score, where an overall score is calculated using the set weights.

[0707] Server: Stores the evaluation scores returned by the generative AI in a database.

[0708] 4. Emotion evaluation using an emotion engine

[0709] Server: Utilizing the emotion engine, we obtain user emotion data when submitting an idea. This data is analyzed from the text and voice when the user enters the idea.

[0710] Emotion engine: Recognizes emotions from user input, facial expressions, and voice, and generates an emotion score such as positive or negative.

[0711] Server: Stores the sentiment scores in a database and adds them to the overall rating of the idea.

[0712] 5. Picking up valuable ideas

[0713] Server: Based on the evaluation and sentiment scores stored in the database, the server selects ideas that exceed a benchmark score, which is determined based on minimum criteria set by the administrator.

[0714] Server: compiles the ideas into a list and makes them accessible to users.

[0715] Terminal: Generates a screen displaying a list of picked ideas and shows it to the user.

[0716] 6. Notification of Results

[0717] Server: Sends emails and in-app notifications to submitters of selected ideas informing them of the evaluation results.

[0718] Users will receive a notification to find out if their idea was featured, along with a rating score, reasons for selection, and sentiment score for the idea.

[0719] Specific examples

[0720] When a user submits an idea for a "smart trash can," the device sends the data to the server, where the idea is stored in a database. The administrator sets the evaluation criteria, such as "originality," "feasibility," and "market value," and these are stored on the server.

[0721] The server uses generative AI to evaluate the "smart trash cans" and calculate a score based on each criterion. An emotion engine also analyzes the user's emotions at the time of submission and generates an emotion score. If the overall score exceeds the criteria, the server selects the idea as a valuable idea, and the device displays a list of the ideas. Finally, the user receives a notification, where they can view the emotion score along with the evaluation results.

[0722] In this way, the system of the present invention can efficiently and fairly carry out the entire process from soliciting ideas from users to ultimately selecting valuable ideas. This significantly improves the accuracy and efficiency of the idea discovery process in companies and organizations. Furthermore, by taking user emotions into account, a more human-like evaluation system can be realized.

[0723] The processing flow will be explained below.

[0724] Program processing flow

[0725] Step 1:

[0726] A user uses a web form or application to enter an idea title, a detailed description, and optional related images and files.

[0727] Step 2:

[0728] The user clicks the "Send" button, and the terminal sends the idea data to the server.

[0729] Step 3:

[0730] The server receives the API request and stores the input idea data in a database.

[0731] Step 4:

[0732] The server returns a response confirming to the user that the idea was successfully submitted.

[0733] Step 5:

[0734] The user (administrator) accesses the review criteria settings screen via the web interface or app.

[0735] Step 6:

[0736] The user (administrator) inputs evaluation criteria such as "originality," "feasibility," and "market value," and sets the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[0737] Step 7:

[0738] The terminal sends the evaluation criteria and their weighting set by the administrator to the server.

[0739] Step 8:

[0740] The server stores the received evaluation criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[0741] Step 9:

[0742] The server retrieves unrated ideas from the database.

[0743] Step 10:

[0744] The server calls a generative AI to evaluate each idea it receives based on the evaluation criteria set for each idea.

[0745] Step 11:

[0746] Generative AI performs text analysis and natural language processing on each idea, calculating scores for "originality," "feasibility," "market value," and other factors.

[0747] Step 12:

[0748] Based on the calculated scores, the generative AI assigns a final evaluation score to the idea, which calculates an overall score using the weights you set.

[0749] Step 13:

[0750] The server stores the evaluation scores returned by the generative AI in a database.

[0751] Step 14:

[0752] The server uses an emotion engine to acquire the user's emotion data when submitting an idea.

[0753] Step 15:

[0754] The emotion engine recognizes emotions from the user's input, facial expressions, and voice, and generates an emotion score such as positive or negative.

[0755] Step 16:

[0756] The server stores the emotion scores in a database and adds them to the overall evaluation of the idea.

[0757] Step 17:

[0758] The server selects ideas that exceed the standard score based on the evaluation scores and sentiment scores stored in the database.

[0759] Step 18:

[0760] The server compiles a list of picked ideas and makes them accessible to users.

[0761] Step 19:

[0762] The device generates a screen displaying a list of the picked ideas and shows it to the user.

[0763] Step 20:

[0764] The server will send an email or in-app notification to the submitter of the picked idea informing them of the evaluation results.

[0765] Step 21:

[0766] Users will receive a notification to find out if their idea was featured, along with a rating score, reasons for selection, and sentiment score for the idea.

[0767] Through the above steps, the system of the present invention can efficiently and fairly collect ideas from users, select the most valuable ideas, and evaluate them while taking their emotions into consideration.

[0768] Example 2

[0769] 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."

[0770] Conventional idea evaluation systems have difficulty in efficiently and fairly evaluating ideas submitted by users, and in particular, they lack consideration of user emotions in their evaluations. As a result, there is a problem in which valuable ideas are not properly selected.

[0771] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for storing ideas received from users, a means for storing evaluation criteria set by an administrator, a means for evaluating ideas using a generative AI model, a means for analyzing user emotion data using an emotion engine and generating an emotion score, a means for selecting valuable ideas based on the evaluation results and the emotion score, and a means for notifying the user of the results of the selected ideas. This allows ideas to be evaluated efficiently and fairly, and by taking user emotions into consideration, more appropriate and valuable ideas can be selected.

[0772] "User" refers to a user who submits an idea to the system.

[0773] "Administrator" refers to the person in charge of setting the system's review criteria and managing the system as a whole.

[0774] "Evaluation criteria" refers to the criteria for evaluating ideas, including items such as originality, feasibility, and market value.

[0775] A "generative AI model" is an artificial intelligence model used to evaluate ideas, using text analysis and natural language processing techniques.

[0776] An "emotion engine" refers to a technology that analyzes a user's emotional data and generates an emotional score, such as positive or negative.

[0777] "Evaluation results" refers to the aggregated scores and evaluations of ideas calculated by the generative AI model.

[0778] "Emotion score" refers to a numerical representation of a user's emotional state calculated by the emotion engine.

[0779] "Valuable Ideas" refer to useful ideas that have been comprehensively evaluated and selected based on set evaluation criteria and emotional scores.

[0780] "Notification" refers to a means of communication to inform users of the evaluation results and information about selected ideas.

[0781] System Overview

[0782] This invention is a system that efficiently evaluates ideas submitted by users and selects valuable ideas. It also recognizes the user's emotions and incorporates them into the evaluation results. This system utilizes the following hardware and software:

[0783] Server: Stores ideas and evaluation data in a database and interacts with generative AI models and emotion engines.

[0784] Terminal: Provides an interface for users and administrators to access and send and receive data.

[0785] Users: Submit ideas and receive notifications of results.

[0786] Specific processing of the system

[0787] Submit your idea

[0788] The user uses a web form or application to enter the "idea title," "detailed description," and "related images and files (optional)." When the user clicks the "Submit" button, the device sends the data to the server. The server receives the API request, saves the idea in a database, and notifies the user that the idea has been successfully submitted.

[0789] Setting the review criteria

[0790] The user (administrator) accesses the evaluation criteria setting screen and sets evaluation criteria such as "originality," "feasibility," and "market value" along with the weighting of each. The terminal sends the setting information to the server, which stores the data in a database. The server also notifies the administrator that the setting was successful.

[0791] Idea Evaluation

[0792] The server retrieves unrated ideas from the database. For each idea, the server invokes a generative AI model and performs text analysis and natural language processing to calculate scores for "originality," "feasibility," "market value," etc. The evaluation results are returned to the server, which calculates an overall score and stores it in the database.

[0793] Emotion evaluation by emotion engine

[0794] The server uses an emotion engine to obtain the user's emotion data when they submit an idea. It recognizes emotions from the user's input, facial expressions, and voice, and generates an emotion score. The emotion score is stored in a database and is reflected in the overall evaluation of the idea.

[0795] Picking up valuable ideas

[0796] The server selects ideas that exceed the benchmark score based on the evaluation score and sentiment score, and the selected ideas are displayed in a list on the terminal for user access.

[0797] Notification of results

[0798] Finally, the server generates an email or in-app notification to the submitter of the selected idea informing them of the evaluation result. Users can receive the notification and check whether their idea was selected. The notification also includes the idea's evaluation score, the reason for selection, and the sentiment score.

[0799] Specific examples

[0800] When a user submits an idea for a "smart trash can," the device sends the data to the server, and the idea is saved in a database. An administrator sets the evaluation criteria of "originality," "feasibility," and "market value," which are saved on the server. The server uses a generative AI model to evaluate the "smart trash can" and calculates a score based on each criterion. An emotion engine also analyzes the user's emotions at the time of submission and generates an emotion score. If the overall score exceeds the criteria, the server selects the idea as a valuable idea, and the device displays a list. Finally, the user is notified and can check the emotion score along with the evaluation results.

[0801] Prompt Sentence Examples

[0802] Please calculate a score for the idea "Smart Trash Can" based on the following criteria: Originality 50%, Feasibility 30%, Market Value 20%. Also, please consider the user's sentiment (positive or negative) at the time of submission and give an overall score.

[0803] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0804] Step 1: Submit your idea

[0805] A user opens a web form or application and enters the "idea title," "detailed description," and "related images and files (optional)." For example, a user enters the title "Smart Trash Can" and a specific description.

[0806] Input: Title, description, related images and files

[0807] The device incorporates the user's input data into an API request and sends it to the server in JSON format.

[0808] The server receives the API request and checks the data format and required fields, for example, whether the title is empty and whether a detailed description is provided.

[0809] Output: Save notification

[0810] If there are no problems, the server saves the idea in a database and generates a response informing the user that the idea was successfully submitted.

[0811] Step 2: Setting the review criteria

[0812] The user (administrator) accesses the evaluation criteria setting screen and sets evaluation criteria such as "originality," "feasibility," and "market value" and the weighting of each.

[0813] Input: Judging criteria and weighting

[0814] The device incorporates the set evaluation criteria and their weighting into an API request and sends it to the server.

[0815] The server stores the received evaluation criteria and weights, and performs database operations for storage.

[0816] Output: Configuration confirmation notice

[0817] The server generates and sends a response to the administrator indicating that the setting was successful.

[0818] Step 3: Evaluate your ideas

[0819] The server retrieves unrated ideas from the database, for example the most recently added "smart trash can" idea.

[0820] Input: Unrated idea data

[0821] The server calls a generative AI model for each idea it receives, using the set evaluation criteria as prompts.

[0822] The generative AI model performs text analysis and natural language processing on each idea to calculate scores for originality, feasibility, market value, etc. For example, for the prompt sentence "smart trash can," the overall score is calculated with weights of 50% for originality, 30% for feasibility, and 20% for market value.

[0823] Output: Evaluation score

[0824] The generative AI model calculates a final evaluation score based on the calculated scores and returns it to the server, which stores the score in a database.

[0825] Step 4: Emotion evaluation by the emotion engine

[0826] The server uses an emotion engine to obtain user emotion data when an idea is submitted, for example by analyzing text or voice data.

[0827] Input: User text and voice data

[0828] The emotion engine recognizes emotions from the user's input, facial expressions, and voice, and generates an emotion score such as positive or negative.

[0829] Output: Sentiment score

[0830] The server stores the generated emotion scores in a database and adds them to the overall evaluation of the idea.

[0831] Step 5: Identifying valuable ideas

[0832] The server selects ideas that exceed a threshold score based on their rating and sentiment scores, which are based on minimum criteria set by the administrator.

[0833] Input: Rating score, sentiment score, criteria score

[0834] The server compiles a list of the selected ideas and makes it accessible to users.

[0835] Output: List of selected ideas

[0836] The device generates a screen displaying a list of the ideas picked up and shows it to the user. By providing a user-friendly interface, the user can easily and quickly check the evaluation results.

[0837] Step 6: Notification of results

[0838] The server generates emails and in-app notifications to the submitters of the selected ideas informing them of the evaluation results.

[0839] Input: Picked idea data, user contact information

[0840] The server generates and sends a notification to the submitter, which includes the rating score, the reason for selection, and the sentiment score.

[0841] Output: Information message

[0842] Users will receive a notification to see if their idea has been picked up, and can use the information in the notification to decide what to do next.

[0843] (Application example 2)

[0844] 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."

[0845] Conventional idea evaluation systems do not take into account the user's emotions when evaluating ideas submitted by users, resulting in a lack of human-like evaluation and the possibility of overlooking high-quality ideas. Furthermore, the evaluation process is inefficient, making it difficult to process when a large number of ideas are submitted.

[0846] The identification process 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 storing ideas received from users, means for storing evaluation criteria set by an administrator, means for evaluating the ideas using a generative AI based on the stored ideas, means for acquiring user emotion data and performing emotion recognition, means for selecting valuable ideas based on the evaluation results and the emotion data, and means for notifying the user of the results of the selected ideas. This enables human-like evaluation that takes user emotions into consideration, making it possible to evaluate many ideas efficiently and fairly.

[0847] "User" means an individual or organization that submits an idea and receives the evaluation results.

[0848] "Administrator" refers to the person or organization that sets the system's review criteria and oversees the idea evaluation and selection process.

[0849] An "idea" is a specific proposal for a new product or service that a user has invented.

[0850] "Evaluation criteria" are indicators used to evaluate ideas, and include criteria such as "originality," "feasibility," and "market value."

[0851] "Generative AI" is an artificial intelligence system that uses text analysis and natural language processing to automatically evaluate ideas.

[0852] "Emotion data" is data that indicates the user's emotions at the time of submitting the idea, and is obtained from text, facial expressions, voice, etc.

[0853] "Emotion recognition" is the process of analyzing a user's emotional data and determining whether the emotion is positive or negative.

[0854] "Evaluation results" refer to the evaluation scores for each idea calculated using generative AI and emotion recognition technology.

[0855] A "valuable idea" is an idea that receives a high rating based on established evaluation criteria and evaluation using emotional data.

[0856] "Notification methods" are mechanisms for informing users of the evaluation results and information about selected ideas, and include email and in-app notifications.

[0857] The system of the present invention is capable of efficiently evaluating ideas submitted by users and performing a comprehensive evaluation that takes into account the user's emotions. The system operates by appropriately arranging hardware and software. A specific example of the system is shown below.

[0858] Hardware and Software Configuration

[0859] server:

[0860] Role: Central data processing and management.

[0861] Software: Flask (a Python web application framework), database (e.g., MySQL), generative AI model (natural language processing), emotion recognition engine.

[0862] Device:

[0863] Role: Provides an interface for users to submit ideas.

[0864] Software: Web forms and custom applications.

[0865] User:

[0866] Role: Submit ideas and review evaluation results.

[0867] System Operation

[0868] Submit your idea

[0869] Users enter their ideas and related data through a web form or a dedicated application and send it to the server, which receives it and stores it in a database, allowing users to register their ideas in the system.

[0870] Setting the review criteria

[0871] Administrators set the judging criteria through a web interface or application, which are then stored in a database by the server, establishing the criteria necessary for evaluating ideas.

[0872] Idea Evaluation

[0873] The server calls a generative AI model, analyzes the text of the registered idea, and evaluates it. This generative AI calculates scores for "originality," "feasibility," "market value," and other factors, and returns the results to the server. At the same time, an emotion recognition engine is used to analyze the emotions felt when the user inputs the idea. Emotional data is obtained from voice and text, and a score such as positive or negative is generated.

[0874] Effective evaluation and communication of results

[0875] The server combines the evaluation score and sentiment score to calculate an overall score. Ideas whose overall score meets certain criteria are selected and the result is notified to the user via email or in-app notification, allowing the user to check the evaluation results.

[0876] Specific examples

[0877] For example, if a user submits an idea for a "smart trash can," the system works as follows: The user inputs the text of the idea and sends it to the server along with its emotional data. The server uses a generative AI model to evaluate the idea and calculates scores for "originality," "feasibility," and "market value." At the same time, an emotional recognition engine analyzes the user's emotional data and generates a positive emotional score. An overall score is calculated, and if it meets the criteria, the user is notified.

[0878] Example prompt sentence:

[0879] A user submitted a new product idea: "Health management system using a smartwatch."

[0880] Please rate this idea's "originality," "feasibility," and "market value."

[0881] In your evaluation results, please include a score (1-10) for each item and the reason for your score.

[0882] In this way, the system of the present invention realizes human-like evaluation that takes into account the user's emotions, and by efficiently evaluating many ideas, it is possible to pick out valuable ideas.

[0883] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0884] Step 1:

[0885] Users input their ideas through a web form or application on their device. This includes the text data of the idea, related images and files, and the user's emotional data (voice, facial expressions, etc.). Once the input data is ready, they click the "Send" button. Clicking the Send button becomes an input event, and the device sends the input data to the server as an API request.

[0886] Step 2:

[0887] The server receives the API request and saves the received data in the database. It stores the idea text data, related files, and emotion data in the appropriate tables in the database, and returns a response to the device indicating that the save operation was successful, allowing the user to confirm that their idea was successfully submitted.

[0888] Step 3:

[0889] The administrator sets the evaluation criteria using a web interface or application. They input the evaluation criteria, such as "originality," "feasibility," and "market value," to be used to evaluate users' ideas, along with their respective weights (e.g., originality 50%, feasibility 30%, market value 20%), and click "Save." The device then sends this setting data to the server.

[0890] Step 4:

[0891] The server saves the evaluation criteria data received from the administrator in the database and returns a response indicating that the save operation was successful to the administrator's terminal. This ensures that the evaluation criteria are applied to the system and will be used for the next idea evaluation.

[0892] Step 5:

[0893] The server retrieves unrated ideas from the database. Based on the retrieved idea data, it invokes a generative AI model to perform text analysis and natural language processing. This calculates scores for each idea in terms of "originality," "feasibility," and "market value," and returns these to the server. The output is idea evaluation data with each score assigned.

[0894] Step 6:

[0895] The server passes the emotional data acquired from the user when submitting the idea to the emotion recognition engine for emotion analysis. The emotion recognition engine analyzes the voice and facial expression data and generates an emotional score, such as positive or negative. This emotional score is returned to the server and added to the evaluation data.

[0896] Step 7:

[0897] The server combines the scores obtained from the generative AI model and the emotion recognition engine to calculate an overall evaluation score. It then calculates a weighted average of each score based on the weights of the set evaluation criteria to calculate a final overall score. Ideas whose overall score meets certain criteria are selected as valuable ideas.

[0898] Step 8:

[0899] The server stores the evaluation results of the selected worthy ideas in a database. It then generates emails or in-app notifications to inform users of the results of the selected ideas. The notifications include details of the evaluation results (individual scores, overall score, and sentiment score) to ensure users fully understand the evaluation process.

[0900] Step 9:

[0901] Users will receive a notification to check the results of their idea evaluation. By clicking the link in the notification, they can view the detailed evaluation results through a web interface or application. This allows users to understand how their idea was evaluated and get hints for improvement.

[0902] Through this series of processes, users submit ideas and receive evaluation results, which motivates them to submit higher quality ideas and improves the quality of the entire system.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] [Third embodiment]

[0907] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0908] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0909] 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).

[0910] 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.

[0911] 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.

[0912] 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).

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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."

[0919] ---

[0920] The present invention provides a system for efficiently evaluating ideas received from users and selecting valuable ideas. This system is implemented in the following manner.

[0921] System Overview

[0922] 1. Submit your idea

[0923] User: Enter the "Title of the idea," "Detailed description," and "Related images and files (optional)" using a web form or application.

[0924] User: Click the "Submit" button to submit your idea.

[0925] Terminal: Issues an API request to send user input data to the server.

[0926] Server: Receives API requests and stores the input idea data in a database.

[0927] Server: Returns a response to the user confirming that the idea was successfully submitted.

[0928] 2. Setting the screening criteria

[0929] User (Administrator): The administrator accesses the review criteria settings screen via the web interface or app.

[0930] User (Administrator): Enter evaluation criteria such as "originality," "feasibility," and "market value," and set the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[0931] Terminal: Sends the evaluation criteria and their weighting set by the administrator to the server.

[0932] Server: Stores the received criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[0933] 3. Evaluating ideas

[0934] Server: Retrieves unrated ideas from the database.

[0935] Server: Calls the generative AI to evaluate each idea based on the evaluation criteria set for each idea obtained.

[0936] Generative AI: It performs text analysis and natural language processing on each idea to calculate scores such as "originality," "feasibility," and "market value."

[0937] Generative AI: Based on the calculated score, the idea is given a final evaluation score, where an overall score is calculated using the set weights.

[0938] Server: Stores the evaluation scores returned by the generative AI in a database.

[0939] 4. Picking up valuable ideas

[0940] Server: Based on the evaluation scores stored in the database, ideas that exceed the standard score are selected. The standard score is determined based on the minimum criteria set by the administrator.

[0941] Server: compiles the ideas into a list and makes them accessible to users.

[0942] Terminal: Generates a screen displaying a list of picked ideas and shows it to the user.

[0943] 5. Notification of Results

[0944] Server: Sends emails and in-app notifications to submitters of selected ideas informing them of the evaluation results.

[0945] Users will receive a notification to find out if their idea was featured, including the rating score and reasons for its selection.

[0946] Specific examples

[0947] When a user submits an idea for a "smart trash can," the device sends the data to the server, where the idea is stored in a database. The administrator sets the evaluation criteria, such as "originality," "feasibility," and "market value," and these are stored on the server.

[0948] The server uses generative AI to evaluate the "smart trash cans" and calculate a score based on each criterion. If the overall score exceeds the criterion, the server will select the idea as a valuable idea, and the device will display a list. Finally, the user will be notified and can check the evaluation results.

[0949] In this way, the system of the present invention can efficiently and fairly carry out the entire process from soliciting ideas from users to ultimately selecting valuable ideas, significantly improving the accuracy and efficiency of the idea discovery process in companies and organizations.

[0950] The processing flow will be explained below.

[0951] Program processing flow

[0952] Step 1:

[0953] A user uses a web form or application to enter an idea title, a detailed description, and optional related images and files.

[0954] Step 2:

[0955] The user clicks the "Send" button, and the terminal sends the idea data to the server.

[0956] Step 3:

[0957] The server receives the API request and stores the input idea data in a database.

[0958] Step 4:

[0959] The server returns a response confirming to the user that the idea was successfully submitted.

[0960] Step 5:

[0961] The user (administrator) accesses the review criteria settings screen via the web interface or app.

[0962] Step 6:

[0963] The user (administrator) inputs evaluation criteria such as "originality," "feasibility," and "market value," and sets the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[0964] Step 7:

[0965] The terminal sends the evaluation criteria and their weighting set by the administrator to the server.

[0966] Step 8:

[0967] The server stores the received evaluation criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[0968] Step 9:

[0969] The server retrieves unrated ideas from the database.

[0970] Step 10:

[0971] The server calls a generative AI to evaluate each idea it receives based on the evaluation criteria set for each idea.

[0972] Step 11:

[0973] Generative AI performs text analysis and natural language processing on each idea, calculating scores for "originality," "feasibility," "market value," and other factors.

[0974] Step 12:

[0975] Based on the calculated scores, the generative AI assigns a final evaluation score to the idea, which calculates an overall score using the weights you set.

[0976] Step 13:

[0977] The server stores the evaluation scores returned by the generative AI in a database.

[0978] Step 14:

[0979] The server selects ideas that exceed a benchmark score based on the evaluation scores stored in the database, which is determined based on minimum criteria set by the administrator.

[0980] Step 15:

[0981] The server compiles a list of picked ideas and makes them accessible to users.

[0982] Step 16:

[0983] The device generates a screen displaying a list of the picked ideas and shows it to the user.

[0984] Step 17:

[0985] The server will send an email or in-app notification to the submitter of the picked idea informing them of the evaluation results.

[0986] Step 18:

[0987] Users will receive a notification to find out if their idea was featured, along with a rating score and reasons for its selection.

[0988] Example 1

[0989] 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."

[0990] It is important for companies and organizations to efficiently evaluate the many ideas submitted by users and appropriately select the most valuable ideas. However, manual evaluation requires time and effort, and there is a possibility that subjective judgments may be involved, making it inefficient and impartial.

[0991] 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.

[0992] In this invention, the server includes means for storing ideas received from users, means for storing evaluation criteria set by an administrator, means for evaluating the ideas using a generative AI model based on the stored ideas, means for selecting valuable ideas that exceed a standard score based on the evaluation scores, and means for notifying users of the evaluation results of the selected ideas. This makes it possible to efficiently and fairly evaluate received ideas and quickly select valuable ideas.

[0993] "User" means any person or entity that uses the System to submit Ideas.

[0994] "Administrator" means an individual or organization responsible for the operation and management of the system and with the authority to set screening criteria.

[0995] "Idea" refers to a new proposal, concept or idea submitted by a user.

[0996] The "evaluation criteria" are the evaluation criteria for ideas set by the administrator, and include multiple evaluation items such as originality, feasibility, and market value.

[0997] "Generative AI model" refers to an artificial intelligence algorithm that evaluates user-submitted ideas using text analysis and natural language processing techniques.

[0998] An "evaluation score" is a score or number that the generative AI model assigns to each idea based on the evaluation criteria.

[0999] The "baseline score" refers to the minimum evaluation score required to select a worthy idea, and is set by the administrator.

[1000] A "valuable idea" is an idea whose evaluation score exceeds the standard score and is judged to be beneficial to users and companies.

[1001] "Notification means" refers to the method by which the server communicates the evaluation results to the user, and includes email, in-app notifications, etc.

[1002] The present invention relates to a system for efficiently evaluating ideas received from users and selecting valuable ideas. The system is composed of users, terminals, and a server.

[1003] System Configuration

[1004] 1. User: Submits an idea using a web form or application by entering the "idea title," "detailed description," and "related images and files (optional)."

[1005] 2. Terminal: Receives user input data and sends it to the server by sending an HTTP POST request to the API endpoint and including the idea data.

[1006] 3. Server:

[1007] Save Idea: Receives an API request and saves the entered idea data to the database. Executes a SQL insert statement.

[1008] Saving the criteria: The criteria received from the administrator (originality, feasibility, market value) and their respective weights are saved in the database using SQL insert or update statements.

[1009] Evaluate ideas: Retrieve unrated ideas from the database and invoke the generative AI model by sending an API request, including the idea data and evaluation criteria.

[1010] Evaluation-based selection: The generative AI model evaluates ideas using text analysis and natural language processing techniques, calculates a score based on each evaluation criterion, and then calculates a final score using the calculated scores to select ideas that exceed the standard score.

[1011] Notification method: The submitters of selected ideas will be notified of the evaluation results via email and / or in-app notification.

[1012] Hardware and Software Configuration

[1013] Hardware: Server, client terminal (PC, smartphone, tablet, etc.)

[1014] software:

[1015] Front-end: web forms, applications

[1016] Backend: API endpoints, database (SQL)

[1017] Generative AI models: natural language processing libraries, text analysis tools

[1018] Specific examples

[1019] A user submits an idea for a "smart trash can." For example, "a trash can with a function that automatically calls a trash collection service when a certain amount of trash accumulates." The device sends the data to the server using an HTTP POST request, and the server stores the data in a database.

[1020] The administrator will set the following evaluation criteria and weightings.

[1021] Originality: 50%

[1022] Likelihood: 30%

[1023] Market value: 20%

[1024] AI assessment prompt example

[1025] A "smart trash can" is a trash can that automatically calls a trash collection service when a certain amount of trash has accumulated. Please rate this idea using the following criteria.

[1026] Originality: 50%

[1027] Likelihood: 30%

[1028] Market value: 20%

[1029] The server sends this prompt to the generative AI model, which then calculates a score based on each criterion. For example, if the AI ​​scores "originality: 90 points, feasibility: 70 points, market value: 80 points," it will calculate an overall score taking into account the weights. The overall score is calculated as follows:

[1030] Total score = (originality score × originality weight) + (feasibility score × feasibility weight) + (market value score × market value weight)

[1031] = (90 × 0.5) + (70 × 0.3) + (80 × 0.2)

[1032] = 45 + 21 + 16

[1033] = 82

[1034] If the total score exceeds a threshold (e.g., 75 points), the server selects the idea as valuable and notifies the user. This allows the system of the present invention to efficiently evaluate ideas and select them fairly.

[1035] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1036] Step 1:

[1037] Submit your idea

[1038] User: Using a web form or application, enter the "Title of the idea," "Detailed description," and "Related images and files (optional)," then click the "Submit" button.

[1039] Terminal: Takes user input data and sends it to the API endpoint in an HTTP POST request, including the idea title, detailed description, and associated files.

[1040] Server: Receives the API request and executes an INSERT statement to save the idea data in the database. Example: INSERT INTO ideas (title, description, files) VALUES (?, ?, ?)

[1041] Server: Returns an HTTP response (200 OK) to the user confirming that the idea was successfully submitted. The response includes a confirmation message.

[1042] Step 2:

[1043] Setting the review criteria

[1044] User (Administrator): Access the judging criteria setting screen via the web interface or app, and enter judging criteria such as "originality," "feasibility," and "market value" along with their respective weightings (e.g., originality 50%, feasibility 30%, market value 20%).

[1045] Terminal: Takes the administrator's input and sends it to the server via an HTTP POST request, which includes the criteria and their weights.

[1046] Server: Store the received criteria and weights in the database. Example: INSERT INTO criteria (originality_weight, feasibility_weight, market_value_weight) VALUES (?, ?, ?)

[1047] Server: Returns an HTTP response (200 OK) to the administrator confirming that the review criteria were successfully set. This response includes a confirmation message.

[1048] Step 3:

[1049] Idea Evaluation

[1050] Server: Get unrated ideas from the database. Example: SELECT FROM ideas WHERE evaluated = false

[1051] Server: Calls the generative AI model to evaluate each idea based on the evaluation criteria set for each idea. Generates prompts to send to the AI ​​model.

[1052] Generative AI model: Receives API requests and evaluates ideas using text analysis and natural language processing techniques, calculating scores (originality, feasibility, market value) based on each evaluation criteria.

[1053] Generative AI model: Returns the calculated score to the server, which includes the score for each assessment item and the final evaluation score.

[1054] Server: Using the received scores, calculate the total score by multiplying each score by the weight set in the evaluation criteria. Example: total_score = (originality_score originality_weight) + (feasibility_score feasibility_weight) + (market_value_score market_value_weight)

[1055] Server: Save the calculated total score to the database and update the idea's evaluated flag. Example: UPDATE ideas SET total_score = ?, evaluated = true WHERE id = ?

[1056] Step 4:

[1057] Picking up valuable ideas

[1058] Server: Select ideas from the database whose total score exceeds the threshold score. Example: SELECT FROM ideas WHERE total_score >= ?

[1059] Server: Compiles the selected ideas into a list and formats them in an accessible format (e.g. HTML or JSON).

[1060] Terminal: Renders the data received from the server and generates a screen displaying a list of valuable ideas for the user.

[1061] Step 5:

[1062] Notification of results

[1063] Server: Sends emails and in-app notifications to the winners of the ideas, including the score and reasons for the idea's selection.

[1064] Users: Receive notifications to find out if their ideas are selected as valuable ideas.

[1065] In this way, each processing step of the system is carried out efficiently through cooperation between users, terminals, and servers, from idea submission to evaluation, selection, and notification.

[1066] (Application example 1)

[1067] 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."

[1068] In recent years, there has been an increasing demand for efficient and fair evaluation in idea solicitation and selection. However, manual evaluation is time-consuming and laborious, and it is difficult to ensure fairness. While generative artificial intelligence (AI) is an alternative, it poses challenges, such as the difficulty of designing appropriate prompts to effectively evaluate ideas and the difficulty of calculating an overall evaluation by weighting the evaluation criteria. Furthermore, the process of quickly notifying evaluation results and providing feedback to users must be efficient.

[1069] 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.

[1070] In this invention, the server includes means for storing ideas received from users, means for storing evaluation criteria set by an administrator, means for evaluating ideas using a generative artificial intelligence, means for generating prompt sentences for ideas to be evaluated, means for requesting the generative artificial intelligence to evaluate the ideas using the prompt sentences, means for selecting valuable ideas based on the evaluation results, and means for notifying users of the results of the selected ideas. This makes it possible to evaluate ideas efficiently and fairly and provide prompt feedback to users.

[1071] "Users" are members of the public who submit ideas and suggestions.

[1072] An "Administrator" is a person or entity with the authority to set the criteria for evaluating ideas and oversee the evaluation process.

[1073] "Ideas" are new ideas or improvements suggested by users.

[1074] "Evaluation criteria" are measures such as originality, feasibility, and market value used to evaluate ideas.

[1075] "Generative AI" is AI that has the ability to evaluate ideas using natural language processing and text analysis.

[1076] A "prompt" is a specific instruction used when evaluating ideas using generative artificial intelligence.

[1077] The "evaluation result" is the score of the idea calculated by the generative artificial intelligence.

[1078] A "worthy idea" is an idea that receives a high rating based on the established evaluation criteria.

[1079] "Notification" is a message that notifies the user of the evaluation results or selection results.

[1080] A "server" is a computer system that stores ideas submitted by users and set evaluation criteria, and runs the generative artificial intelligence.

[1081] The present invention relates to a system for efficiently and fairly evaluating ideas received from users and selecting valuable ideas. This system includes the processes of registering ideas, setting review criteria by an administrator, evaluation by generative artificial intelligence, selection, and notification.

[1082] System Overview

[1083] 1. Submit your idea

[1084] Users can use the official application to register "new product ideas" and "improvement suggestions." Ideas can include titles, detailed descriptions, related images, files, and other attachments.

[1085] When the send button is clicked, data is sent from the terminal to the server.

[1086] 2. Setting the screening criteria

[1087] Administrators access the administrator screen within the app to set the evaluation criteria (e.g., originality, feasibility, market value) and their weighting.

[1088] The evaluation criteria set by the administrator are stored on the server.

[1089] 3. Evaluating ideas

[1090] The server retrieves unrated ideas from the database, then generates prompts for the ideas to be rated.

[1091] The generated prompt is used to request an evaluation of the idea from the generative AI, which then performs text analysis and natural language processing according to the prompt to calculate an evaluation score based on each criterion.

[1092] 4. Selecting Valuable Ideas

[1093] The server calculates an overall score based on the weighting of the evaluation scores obtained from the generative artificial intelligence.

[1094] Ideas whose overall score exceeds the set standard are selected as worthy ideas.

[1095] 5. Notification of Results

[1096] The server will then send a notification to the submitter of the selected idea, including the evaluation score and the reason for the selection.

[1097] Hardware and software used

[1098] Server: A computer system that stores ideas received from users and set evaluation criteria, and runs generative AI. A Linux-based server or cloud service (e.g., Amazon Web Services, Google Cloud Platform) can be used.

[1099] Generative AI: An AI model capable of natural language processing. Specifically, OpenAI's GPT-3 is used.

[1100] Database: A system for managing data on stored ideas and evaluation criteria. An SQL database (e.g., MySQL, PostgreSQL) can be used.

[1101] Specific examples

[1102] A user submits an idea for an "eco-bag sharing service." The administrator sets the judging criteria as 50% originality, 30% feasibility, and 20% market value. The server retrieves unrated ideas and evaluates them using the following prompts from a generative AI:

[1103] Prompt Sentence Examples

[1104] "Please rate this new product idea. The title of the idea is 'Eco Bag Sharing Service' and the detailed description is 'We will create a system for sharing used eco bags to reduce environmental impact.' Please rate each item (originality, feasibility, market value) on a scale of 1 to 10 and return each score."

[1105] The generative AI analyzes the text based on the prompt and returns a score for each evaluation criterion. The server calculates the overall score based on the results, and if the score exceeds the criterion, a notification message is sent to the user. The notification includes the evaluation score and the reason for the selection, allowing the user to check the content.

[1106] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1107] Step 1:

[1108] Users use the official application to register their ideas. The data they enter is the idea title, detailed description, and related images and files. When the user clicks the "Submit" button, the device sends this data to the server as an API request.

[1109] Step 2:

[1110] The server receives the API request sent from the device and saves the idea data in the database. At this time, it generates a response confirming that the data was saved successfully and sends it back to the device. The server then notifies the user that the data was saved successfully.

[1111] Step 3:

[1112] The administrator sets the evaluation criteria from the application's administration screen. The data to be entered are evaluation criteria such as "originality," "feasibility," and "market value," along with their weighting (e.g., originality 50%, feasibility 30%, market value 20%). When the administrator clicks the "Set" button, the device sends this data to the server as an API request.

[1113] Step 4:

[1114] The server saves the evaluation criteria and their weights sent from the administrator's terminal in a database. At this time, it generates a response to confirm that the settings were completed successfully and returns it to the terminal. The server then notifies the administrator that the data was saved successfully.

[1115] Step 5:

[1116] The server retrieves unrated ideas from the database, then generates a prompt for each idea to rate it, including the idea's title and detailed description, and sends it to the generative AI model.

[1117] Step 6:

[1118] The server uses the generated prompt to request a generative AI (e.g., GPT-3) to evaluate the idea. The generative AI performs text analysis and natural language processing based on the prompt, and calculates a score for each criterion, such as originality, feasibility, and market value.

[1119] Step 7:

[1120] The server receives the scores returned by the generative AI and calculates an overall rating for each score based on the weights set by the administrator. For example, if originality is 7, feasibility is 8, and market value is 6, the overall rating score is calculated as (7 0.5 + 8 0.3 + 6 0.2).

[1121] Step 8:

[1122] The server selects valuable ideas based on the calculated overall evaluation score. Ideas whose overall evaluation score exceeds a set standard are selected and stored in a database.

[1123] Step 9:

[1124] The server will then send a notification to the submitter of the selected idea, including the evaluation score and the reason for the selection. The notification will be sent via in-app notification or email, and the user can check the content.

[1125] Step 10:

[1126] The user receives a notification from the server to know that their idea has been selected. The user can check the evaluation score and the reason for the selection in the notification and understand the details of how their idea was evaluated.

[1127] 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.

[1128] ---

[1129] The present invention provides a system that efficiently evaluates ideas received from users and selects valuable ideas, as well as a system that recognizes users' emotions and takes them into account in the evaluation results. This system can be implemented in the following manner.

[1130] System Overview

[1131] 1. Submit your idea

[1132] User: Using a web form or application, enter the "Title of the idea," "Detailed description," and "Related images and files (optional)."

[1133] User: Click the "Submit" button to submit your idea.

[1134] Terminal: Issues an API request to send user input data to the server.

[1135] Server: Receives API requests and stores the input idea data in a database.

[1136] Server: Returns a response to the user confirming that the idea was successfully submitted.

[1137] 2. Setting the screening criteria

[1138] User (Administrator): The administrator accesses the review criteria settings screen via the web interface or app.

[1139] User (Administrator): Enter evaluation criteria such as "originality," "feasibility," and "market value," and set the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[1140] Terminal: Sends the evaluation criteria and their weighting set by the administrator to the server.

[1141] Server: Stores the received criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[1142] 3. Evaluating ideas

[1143] Server: Retrieves unrated ideas from the database.

[1144] Server: Calls the generative AI to evaluate each idea based on the evaluation criteria set for each idea obtained.

[1145] Generative AI: It performs text analysis and natural language processing on each idea to calculate scores such as "originality," "feasibility," and "market value."

[1146] Generative AI: Based on the calculated score, the idea is given a final evaluation score, where an overall score is calculated using the set weights.

[1147] Server: Stores the evaluation scores returned by the generative AI in a database.

[1148] 4. Emotion evaluation using an emotion engine

[1149] Server: Utilizing the emotion engine, we obtain user emotion data when submitting an idea. This data is analyzed from the text and voice when the user enters the idea.

[1150] Emotion engine: Recognizes emotions from user input, facial expressions, and voice, and generates an emotion score such as positive or negative.

[1151] Server: Stores the sentiment scores in a database and adds them to the overall rating of the idea.

[1152] 5. Picking up valuable ideas

[1153] Server: Based on the evaluation and sentiment scores stored in the database, the server selects ideas that exceed a benchmark score, which is determined based on minimum criteria set by the administrator.

[1154] Server: compiles the ideas into a list and makes them accessible to users.

[1155] Terminal: Generates a screen displaying a list of picked ideas and shows it to the user.

[1156] 6. Notification of Results

[1157] Server: Sends emails and in-app notifications to submitters of selected ideas informing them of the evaluation results.

[1158] Users will receive a notification to find out if their idea was featured, along with a rating score, reasons for selection, and sentiment score for the idea.

[1159] Specific examples

[1160] When a user submits an idea for a "smart trash can," the device sends the data to the server, where the idea is stored in a database. The administrator sets the evaluation criteria, such as "originality," "feasibility," and "market value," and these are stored on the server.

[1161] The server uses generative AI to evaluate the "smart trash cans" and calculate a score based on each criterion. An emotion engine also analyzes the user's emotions at the time of submission and generates an emotion score. If the overall score exceeds the criteria, the server selects the idea as a valuable idea, and the device displays a list of the ideas. Finally, the user receives a notification, where they can view the emotion score along with the evaluation results.

[1162] In this way, the system of the present invention can efficiently and fairly carry out the entire process from soliciting ideas from users to ultimately selecting valuable ideas. This significantly improves the accuracy and efficiency of the idea discovery process in companies and organizations. Furthermore, by taking user emotions into account, a more human-like evaluation system can be realized.

[1163] The processing flow will be explained below.

[1164] Program processing flow

[1165] Step 1:

[1166] A user uses a web form or application to enter an idea title, a detailed description, and optional related images and files.

[1167] Step 2:

[1168] The user clicks the "Send" button, and the terminal sends the idea data to the server.

[1169] Step 3:

[1170] The server receives the API request and stores the input idea data in a database.

[1171] Step 4:

[1172] The server returns a response confirming to the user that the idea was successfully submitted.

[1173] Step 5:

[1174] The user (administrator) accesses the review criteria settings screen via the web interface or app.

[1175] Step 6:

[1176] The user (administrator) inputs evaluation criteria such as "originality," "feasibility," and "market value," and sets the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[1177] Step 7:

[1178] The terminal sends the evaluation criteria and their weighting set by the administrator to the server.

[1179] Step 8:

[1180] The server stores the received evaluation criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[1181] Step 9:

[1182] The server retrieves unrated ideas from the database.

[1183] Step 10:

[1184] The server calls a generative AI to evaluate each idea it receives based on the evaluation criteria set for each idea.

[1185] Step 11:

[1186] Generative AI performs text analysis and natural language processing on each idea, calculating scores for "originality," "feasibility," "market value," and other factors.

[1187] Step 12:

[1188] Based on the calculated scores, the generative AI assigns a final evaluation score to the idea, which calculates an overall score using the weights you set.

[1189] Step 13:

[1190] The server stores the evaluation scores returned by the generative AI in a database.

[1191] Step 14:

[1192] The server uses an emotion engine to acquire the user's emotion data when submitting an idea.

[1193] Step 15:

[1194] The emotion engine recognizes emotions from the user's input, facial expressions, and voice, and generates an emotion score such as positive or negative.

[1195] Step 16:

[1196] The server stores the emotion scores in a database and adds them to the overall evaluation of the idea.

[1197] Step 17:

[1198] The server selects ideas that exceed the standard score based on the evaluation scores and sentiment scores stored in the database.

[1199] Step 18:

[1200] The server compiles a list of picked ideas and makes them accessible to users.

[1201] Step 19:

[1202] The device generates a screen displaying a list of the picked ideas and shows it to the user.

[1203] Step 20:

[1204] The server will send an email or in-app notification to the submitter of the picked idea informing them of the evaluation results.

[1205] Step 21:

[1206] Users will receive a notification to find out if their idea was featured, along with a rating score, reasons for selection, and sentiment score for the idea.

[1207] Through the above steps, the system of the present invention can efficiently and fairly collect ideas from users, select the most valuable ideas, and evaluate them while taking their emotions into consideration.

[1208] Example 2

[1209] 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."

[1210] Conventional idea evaluation systems have difficulty in efficiently and fairly evaluating ideas submitted by users, and in particular, they lack consideration of user emotions in their evaluations. As a result, there is a problem in which valuable ideas are not properly selected.

[1211] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for storing ideas received from users, a means for storing evaluation criteria set by an administrator, a means for evaluating ideas using a generative AI model, a means for analyzing user emotion data using an emotion engine and generating an emotion score, a means for selecting valuable ideas based on the evaluation results and the emotion score, and a means for notifying the user of the results of the selected ideas. This allows ideas to be evaluated efficiently and fairly, and by taking user emotions into consideration, more appropriate and valuable ideas can be selected.

[1212] "User" refers to a user who submits an idea to the system.

[1213] "Administrator" refers to the person in charge of setting the system's review criteria and managing the system as a whole.

[1214] "Evaluation criteria" refers to the criteria for evaluating ideas, including items such as originality, feasibility, and market value.

[1215] A "generative AI model" is an artificial intelligence model used to evaluate ideas, using text analysis and natural language processing techniques.

[1216] An "emotion engine" refers to a technology that analyzes a user's emotional data and generates an emotional score, such as positive or negative.

[1217] "Evaluation results" refers to the aggregated scores and evaluations of ideas calculated by the generative AI model.

[1218] "Emotion score" refers to a numerical representation of a user's emotional state calculated by the emotion engine.

[1219] "Valuable Ideas" refer to useful ideas that have been comprehensively evaluated and selected based on set evaluation criteria and emotional scores.

[1220] "Notification" refers to a means of communication to inform users of the evaluation results and information about selected ideas.

[1221] System Overview

[1222] This invention is a system that efficiently evaluates ideas submitted by users and selects valuable ideas. It also recognizes the user's emotions and incorporates them into the evaluation results. This system utilizes the following hardware and software:

[1223] Server: Stores ideas and evaluation data in a database and interacts with generative AI models and emotion engines.

[1224] Terminal: Provides an interface for users and administrators to access and send and receive data.

[1225] Users: Submit ideas and receive notifications of results.

[1226] Specific processing of the system

[1227] Submit your idea

[1228] The user uses a web form or application to enter the "idea title," "detailed description," and "related images and files (optional)." When the user clicks the "Submit" button, the device sends the data to the server. The server receives the API request, saves the idea in a database, and notifies the user that the idea has been successfully submitted.

[1229] Setting the review criteria

[1230] The user (administrator) accesses the evaluation criteria setting screen and sets evaluation criteria such as "originality," "feasibility," and "market value" along with the weighting of each. The terminal sends the setting information to the server, which stores the data in a database. The server also notifies the administrator that the setting was successful.

[1231] Idea Evaluation

[1232] The server retrieves unrated ideas from the database. For each idea, the server invokes a generative AI model and performs text analysis and natural language processing to calculate scores for "originality," "feasibility," "market value," etc. The evaluation results are returned to the server, which calculates an overall score and stores it in the database.

[1233] Emotion evaluation by emotion engine

[1234] The server uses an emotion engine to obtain the user's emotion data when they submit an idea. It recognizes emotions from the user's input, facial expressions, and voice, and generates an emotion score. The emotion score is stored in a database and is reflected in the overall evaluation of the idea.

[1235] Picking up valuable ideas

[1236] The server selects ideas that exceed the benchmark score based on the evaluation score and sentiment score, and the selected ideas are displayed in a list on the terminal for user access.

[1237] Notification of results

[1238] Finally, the server generates an email or in-app notification to the submitter of the selected idea informing them of the evaluation result. Users can receive the notification and check whether their idea was selected. The notification also includes the idea's evaluation score, the reason for selection, and the sentiment score.

[1239] Specific examples

[1240] When a user submits an idea for a "smart trash can," the device sends the data to the server, and the idea is saved in a database. An administrator sets the evaluation criteria of "originality," "feasibility," and "market value," which are saved on the server. The server uses a generative AI model to evaluate the "smart trash can" and calculates a score based on each criterion. An emotion engine also analyzes the user's emotions at the time of submission and generates an emotion score. If the overall score exceeds the criteria, the server selects the idea as a valuable idea, and the device displays a list. Finally, the user is notified and can check the emotion score along with the evaluation results.

[1241] Prompt Sentence Examples

[1242] Please calculate a score for the idea "Smart Trash Can" based on the following criteria: Originality 50%, Feasibility 30%, Market Value 20%. Also, please consider the user's sentiment (positive or negative) at the time of submission and give an overall score.

[1243] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1244] Step 1: Submit your idea

[1245] A user opens a web form or application and enters the "idea title," "detailed description," and "related images and files (optional)." For example, a user enters the title "Smart Trash Can" and a specific description.

[1246] Input: Title, description, related images and files

[1247] The device incorporates the user's input data into an API request and sends it to the server in JSON format.

[1248] The server receives the API request and checks the data format and required fields, for example, whether the title is empty and whether a detailed description is provided.

[1249] Output: Save notification

[1250] If there are no problems, the server saves the idea in a database and generates a response informing the user that the idea was successfully submitted.

[1251] Step 2: Setting the review criteria

[1252] The user (administrator) accesses the evaluation criteria setting screen and sets evaluation criteria such as "originality," "feasibility," and "market value" and the weighting of each.

[1253] Input: Judging criteria and weighting

[1254] The device incorporates the set evaluation criteria and their weighting into an API request and sends it to the server.

[1255] The server stores the received evaluation criteria and weights, and performs database operations for storage.

[1256] Output: Configuration confirmation notice

[1257] The server generates and sends a response to the administrator indicating that the setting was successful.

[1258] Step 3: Evaluate your ideas

[1259] The server retrieves unrated ideas from the database, for example the most recently added "smart trash can" idea.

[1260] Input: Unrated idea data

[1261] The server calls a generative AI model for each idea it receives, using the set evaluation criteria as prompts.

[1262] The generative AI model performs text analysis and natural language processing on each idea to calculate scores for originality, feasibility, market value, etc. For example, for the prompt sentence "smart trash can," the overall score is calculated with weights of 50% for originality, 30% for feasibility, and 20% for market value.

[1263] Output: Evaluation score

[1264] The generative AI model calculates a final evaluation score based on the calculated scores and returns it to the server, which stores the score in a database.

[1265] Step 4: Emotion evaluation by the emotion engine

[1266] The server uses an emotion engine to obtain user emotion data when an idea is submitted, for example by analyzing text or voice data.

[1267] Input: User text and voice data

[1268] The emotion engine recognizes emotions from the user's input, facial expressions, and voice, and generates an emotion score such as positive or negative.

[1269] Output: Sentiment score

[1270] The server stores the generated emotion scores in a database and adds them to the overall evaluation of the idea.

[1271] Step 5: Identifying valuable ideas

[1272] The server selects ideas that exceed a threshold score based on their rating and sentiment scores, which are based on minimum criteria set by the administrator.

[1273] Input: Rating score, sentiment score, criteria score

[1274] The server compiles a list of the selected ideas and makes it accessible to users.

[1275] Output: List of selected ideas

[1276] The device generates a screen displaying a list of the ideas picked up and shows it to the user. By providing a user-friendly interface, the user can easily and quickly check the evaluation results.

[1277] Step 6: Notification of results

[1278] The server generates emails and in-app notifications to the submitters of the selected ideas informing them of the evaluation results.

[1279] Input: Picked idea data, user contact information

[1280] The server generates and sends a notification to the submitter, which includes the rating score, the reason for selection, and the sentiment score.

[1281] Output: Information message

[1282] Users will receive a notification to see if their idea has been picked up, and can use the information in the notification to decide what to do next.

[1283] (Application example 2)

[1284] 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."

[1285] Conventional idea evaluation systems do not take into account the user's emotions when evaluating ideas submitted by users, resulting in a lack of human-like evaluation and the possibility of overlooking high-quality ideas. Furthermore, the evaluation process is inefficient, making it difficult to process when a large number of ideas are submitted.

[1286] The identification process 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 storing ideas received from users, means for storing evaluation criteria set by an administrator, means for evaluating the ideas using a generative AI based on the stored ideas, means for acquiring user emotion data and performing emotion recognition, means for selecting valuable ideas based on the evaluation results and the emotion data, and means for notifying the user of the results of the selected ideas. This enables human-like evaluation that takes user emotions into consideration, making it possible to evaluate many ideas efficiently and fairly.

[1287] "User" means an individual or organization that submits an idea and receives the evaluation results.

[1288] "Administrator" refers to the person or organization that sets the system's review criteria and oversees the idea evaluation and selection process.

[1289] An "idea" is a specific proposal for a new product or service that a user has invented.

[1290] "Evaluation criteria" are indicators used to evaluate ideas, and include criteria such as "originality," "feasibility," and "market value."

[1291] "Generative AI" is an artificial intelligence system that uses text analysis and natural language processing to automatically evaluate ideas.

[1292] "Emotion data" is data that indicates the user's emotions at the time of submitting the idea, and is obtained from text, facial expressions, voice, etc.

[1293] "Emotion recognition" is the process of analyzing a user's emotional data and determining whether the emotion is positive or negative.

[1294] "Evaluation results" refer to the evaluation scores for each idea calculated using generative AI and emotion recognition technology.

[1295] A "valuable idea" is an idea that receives a high rating based on established evaluation criteria and evaluation using emotional data.

[1296] "Notification methods" are mechanisms for informing users of the evaluation results and information about selected ideas, and include email and in-app notifications.

[1297] The system of the present invention is capable of efficiently evaluating ideas submitted by users and performing a comprehensive evaluation that takes into account the user's emotions. The system operates by appropriately arranging hardware and software. A specific example of the system is shown below.

[1298] Hardware and Software Configuration

[1299] server:

[1300] Role: Central data processing and management.

[1301] Software: Flask (a Python web application framework), database (e.g., MySQL), generative AI model (natural language processing), emotion recognition engine.

[1302] Device:

[1303] Role: Provides an interface for users to submit ideas.

[1304] Software: Web forms and custom applications.

[1305] User:

[1306] Role: Submit ideas and review evaluation results.

[1307] System Operation

[1308] Submit your idea

[1309] Users enter their ideas and related data through a web form or a dedicated application and send it to the server, which receives it and stores it in a database, allowing users to register their ideas in the system.

[1310] Setting the review criteria

[1311] Administrators set the judging criteria through a web interface or application, which are then stored in a database by the server, establishing the criteria necessary for evaluating ideas.

[1312] Idea Evaluation

[1313] The server calls a generative AI model, analyzes the text of the registered idea, and evaluates it. This generative AI calculates scores for "originality," "feasibility," "market value," and other factors, and returns the results to the server. At the same time, an emotion recognition engine is used to analyze the emotions felt when the user inputs the idea. Emotional data is obtained from voice and text, and a score such as positive or negative is generated.

[1314] Effective evaluation and communication of results

[1315] The server combines the evaluation score and sentiment score to calculate an overall score. Ideas whose overall score meets certain criteria are selected and the result is notified to the user via email or in-app notification, allowing the user to check the evaluation results.

[1316] Specific examples

[1317] For example, if a user submits an idea for a "smart trash can," the system works as follows: The user inputs the text of the idea and sends it to the server along with its emotional data. The server uses a generative AI model to evaluate the idea and calculates scores for "originality," "feasibility," and "market value." At the same time, an emotional recognition engine analyzes the user's emotional data and generates a positive emotional score. An overall score is calculated, and if it meets the criteria, the user is notified.

[1318] Example prompt sentence:

[1319] A user submitted a new product idea: "Health management system using a smartwatch."

[1320] Please rate this idea's "originality," "feasibility," and "market value."

[1321] In your evaluation results, please include a score (1-10) for each item and the reason for your score.

[1322] In this way, the system of the present invention realizes human-like evaluation that takes into account the user's emotions, and by efficiently evaluating many ideas, it is possible to pick out valuable ideas.

[1323] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1324] Step 1:

[1325] Users input their ideas through a web form or application on their device. This includes the text data of the idea, related images and files, and the user's emotional data (voice, facial expressions, etc.). Once the input data is ready, they click the "Send" button. Clicking the Send button becomes an input event, and the device sends the input data to the server as an API request.

[1326] Step 2:

[1327] The server receives the API request and saves the received data in the database. It stores the idea text data, related files, and emotion data in the appropriate tables in the database, and returns a response to the device indicating that the save operation was successful, allowing the user to confirm that their idea was successfully submitted.

[1328] Step 3:

[1329] The administrator sets the evaluation criteria using a web interface or application. They input the evaluation criteria, such as "originality," "feasibility," and "market value," to be used to evaluate users' ideas, along with their respective weights (e.g., originality 50%, feasibility 30%, market value 20%), and click "Save." The device then sends this setting data to the server.

[1330] Step 4:

[1331] The server saves the evaluation criteria data received from the administrator in the database and returns a response indicating that the save operation was successful to the administrator's terminal. This ensures that the evaluation criteria are applied to the system and will be used for the next idea evaluation.

[1332] Step 5:

[1333] The server retrieves unrated ideas from the database. Based on the retrieved idea data, it invokes a generative AI model to perform text analysis and natural language processing. This calculates scores for each idea in terms of "originality," "feasibility," and "market value," and returns these to the server. The output is idea evaluation data with each score assigned.

[1334] Step 6:

[1335] The server passes the emotional data acquired from the user when submitting the idea to the emotion recognition engine for emotion analysis. The emotion recognition engine analyzes the voice and facial expression data and generates an emotional score, such as positive or negative. This emotional score is returned to the server and added to the evaluation data.

[1336] Step 7:

[1337] The server combines the scores obtained from the generative AI model and the emotion recognition engine to calculate an overall evaluation score. It then calculates a weighted average of each score based on the weights of the set evaluation criteria to calculate a final overall score. Ideas whose overall score meets certain criteria are selected as valuable ideas.

[1338] Step 8:

[1339] The server stores the evaluation results of the selected worthy ideas in a database. It then generates emails or in-app notifications to inform users of the results of the selected ideas. The notifications include details of the evaluation results (individual scores, overall score, and sentiment score) to ensure users fully understand the evaluation process.

[1340] Step 9:

[1341] Users will receive a notification to check the results of their idea evaluation. By clicking the link in the notification, they can view the detailed evaluation results through a web interface or application. This allows users to understand how their idea was evaluated and get hints for improvement.

[1342] Through this series of processes, users submit ideas and receive evaluation results, which motivates them to submit higher quality ideas and improves the quality of the entire system.

[1343] 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.

[1344] 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.

[1345] 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.

[1346] [Fourth embodiment]

[1347] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1348] 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.

[1349] 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).

[1350] 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.

[1351] 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.

[1352] 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).

[1353] 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.

[1354] 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.

[1355] 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.

[1356] 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.

[1357] 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.

[1358] 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.

[1359] 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."

[1360] ---

[1361] The present invention provides a system for efficiently evaluating ideas received from users and selecting valuable ideas. This system is implemented in the following manner.

[1362] System Overview

[1363] 1. Submit your idea

[1364] User: Enter the "Title of the idea," "Detailed description," and "Related images and files (optional)" using a web form or application.

[1365] User: Click the "Submit" button to submit your idea.

[1366] Terminal: Issues an API request to send user input data to the server.

[1367] Server: Receives API requests and stores the input idea data in a database.

[1368] Server: Returns a response to the user confirming that the idea was successfully submitted.

[1369] 2. Setting the screening criteria

[1370] User (Administrator): The administrator accesses the review criteria settings screen via the web interface or app.

[1371] User (Administrator): Enter evaluation criteria such as "originality," "feasibility," and "market value," and set the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[1372] Terminal: Sends the evaluation criteria and their weighting set by the administrator to the server.

[1373] Server: Stores the received criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[1374] 3. Evaluating ideas

[1375] Server: Retrieves unrated ideas from the database.

[1376] Server: Calls the generative AI to evaluate each idea based on the evaluation criteria set for each idea obtained.

[1377] Generative AI: It performs text analysis and natural language processing on each idea to calculate scores such as "originality," "feasibility," and "market value."

[1378] Generative AI: Based on the calculated score, the idea is given a final evaluation score, where an overall score is calculated using the set weights.

[1379] Server: Stores the evaluation scores returned by the generative AI in a database.

[1380] 4. Picking up valuable ideas

[1381] Server: Based on the evaluation scores stored in the database, ideas that exceed the standard score are selected. The standard score is determined based on the minimum criteria set by the administrator.

[1382] Server: compiles the ideas into a list and makes them accessible to users.

[1383] Terminal: Generates a screen displaying a list of picked ideas and shows it to the user.

[1384] 5. Notification of Results

[1385] Server: Sends emails and in-app notifications to submitters of selected ideas informing them of the evaluation results.

[1386] Users will receive a notification to find out if their idea was featured, including the rating score and reasons for its selection.

[1387] Specific examples

[1388] When a user submits an idea for a "smart trash can," the device sends the data to the server, where the idea is stored in a database. The administrator sets the evaluation criteria, such as "originality," "feasibility," and "market value," and these are stored on the server.

[1389] The server uses generative AI to evaluate the "smart trash cans" and calculate a score based on each criterion. If the overall score exceeds the criterion, the server will select the idea as a valuable idea, and the device will display a list. Finally, the user will be notified and can check the evaluation results.

[1390] In this way, the system of the present invention can efficiently and fairly carry out the entire process from soliciting ideas from users to ultimately selecting valuable ideas, significantly improving the accuracy and efficiency of the idea discovery process in companies and organizations.

[1391] The processing flow will be explained below.

[1392] Program processing flow

[1393] Step 1:

[1394] A user uses a web form or application to enter an idea title, a detailed description, and optional related images and files.

[1395] Step 2:

[1396] The user clicks the "Send" button, and the terminal sends the idea data to the server.

[1397] Step 3:

[1398] The server receives the API request and stores the input idea data in a database.

[1399] Step 4:

[1400] The server returns a response confirming to the user that the idea was successfully submitted.

[1401] Step 5:

[1402] The user (administrator) accesses the review criteria settings screen via the web interface or app.

[1403] Step 6:

[1404] The user (administrator) inputs evaluation criteria such as "originality," "feasibility," and "market value," and sets the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[1405] Step 7:

[1406] The terminal sends the evaluation criteria and their weighting set by the administrator to the server.

[1407] Step 8:

[1408] The server stores the received evaluation criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[1409] Step 9:

[1410] The server retrieves unrated ideas from the database.

[1411] Step 10:

[1412] The server calls a generative AI to evaluate each idea it receives based on the evaluation criteria set for each idea.

[1413] Step 11:

[1414] Generative AI performs text analysis and natural language processing on each idea, calculating scores for "originality," "feasibility," "market value," and other factors.

[1415] Step 12:

[1416] Based on the calculated scores, the generative AI assigns a final evaluation score to the idea, which calculates an overall score using the weights you set.

[1417] Step 13:

[1418] The server stores the evaluation scores returned by the generative AI in a database.

[1419] Step 14:

[1420] The server selects ideas that exceed a benchmark score based on the evaluation scores stored in the database, which is determined based on minimum criteria set by the administrator.

[1421] Step 15:

[1422] The server compiles a list of picked ideas and makes them accessible to users.

[1423] Step 16:

[1424] The device generates a screen displaying a list of the picked ideas and shows it to the user.

[1425] Step 17:

[1426] The server will send an email or in-app notification to the submitter of the picked idea informing them of the evaluation results.

[1427] Step 18:

[1428] Users will receive a notification to find out if their idea was featured, along with a rating score and reasons for its selection.

[1429] Example 1

[1430] 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."

[1431] It is important for companies and organizations to efficiently evaluate the many ideas submitted by users and appropriately select the most valuable ideas. However, manual evaluation requires time and effort, and there is a possibility that subjective judgments may be involved, making it inefficient and impartial.

[1432] 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.

[1433] In this invention, the server includes means for storing ideas received from users, means for storing evaluation criteria set by an administrator, means for evaluating the ideas using a generative AI model based on the stored ideas, means for selecting valuable ideas that exceed a standard score based on the evaluation scores, and means for notifying users of the evaluation results of the selected ideas. This makes it possible to efficiently and fairly evaluate received ideas and quickly select valuable ideas.

[1434] "User" means any person or entity that uses the System to submit Ideas.

[1435] "Administrator" means an individual or organization responsible for the operation and management of the system and with the authority to set screening criteria.

[1436] "Idea" refers to a new proposal, concept or idea submitted by a user.

[1437] The "evaluation criteria" are the evaluation criteria for ideas set by the administrator, and include multiple evaluation items such as originality, feasibility, and market value.

[1438] "Generative AI model" refers to an artificial intelligence algorithm that evaluates user-submitted ideas using text analysis and natural language processing techniques.

[1439] An "evaluation score" is a score or number that the generative AI model assigns to each idea based on the evaluation criteria.

[1440] The "baseline score" refers to the minimum evaluation score required to select a worthy idea, and is set by the administrator.

[1441] A "valuable idea" is an idea whose evaluation score exceeds the standard score and is judged to be beneficial to users and companies.

[1442] "Notification means" refers to the method by which the server communicates the evaluation results to the user, and includes email, in-app notifications, etc.

[1443] The present invention relates to a system for efficiently evaluating ideas received from users and selecting valuable ideas. The system is composed of users, terminals, and a server.

[1444] System Configuration

[1445] 1. User: Submits an idea using a web form or application by entering the "idea title," "detailed description," and "related images and files (optional)."

[1446] 2. Terminal: Receives user input data and sends it to the server by sending an HTTP POST request to the API endpoint and including the idea data.

[1447] 3. Server:

[1448] Save Idea: Receives an API request and saves the entered idea data to the database. Executes a SQL insert statement.

[1449] Saving the criteria: The criteria received from the administrator (originality, feasibility, market value) and their respective weights are saved in the database using SQL insert or update statements.

[1450] Evaluate ideas: Retrieve unrated ideas from the database and invoke the generative AI model by sending an API request, including the idea data and evaluation criteria.

[1451] Evaluation-based selection: The generative AI model evaluates ideas using text analysis and natural language processing techniques, calculates a score based on each evaluation criterion, and then calculates a final score using the calculated scores to select ideas that exceed the standard score.

[1452] Notification method: The submitters of selected ideas will be notified of the evaluation results via email and / or in-app notification.

[1453] Hardware and Software Configuration

[1454] Hardware: Server, client terminal (PC, smartphone, tablet, etc.)

[1455] software:

[1456] Front-end: web forms, applications

[1457] Backend: API endpoints, database (SQL)

[1458] Generative AI models: natural language processing libraries, text analysis tools

[1459] Specific examples

[1460] A user submits an idea for a "smart trash can." For example, "a trash can with a function that automatically calls a trash collection service when a certain amount of trash accumulates." The device sends the data to the server using an HTTP POST request, and the server stores the data in a database.

[1461] The administrator will set the following evaluation criteria and weightings.

[1462] Originality: 50%

[1463] Likelihood: 30%

[1464] Market value: 20%

[1465] AI assessment prompt example

[1466] A "smart trash can" is a trash can that automatically calls a trash collection service when a certain amount of trash has accumulated. Please rate this idea using the following criteria.

[1467] Originality: 50%

[1468] Likelihood: 30%

[1469] Market value: 20%

[1470] The server sends this prompt to the generative AI model, which then calculates a score based on each criterion. For example, if the AI ​​scores "originality: 90 points, feasibility: 70 points, market value: 80 points," it will calculate an overall score taking into account the weights. The overall score is calculated as follows:

[1471] Total score = (originality score × originality weight) + (feasibility score × feasibility weight) + (market value score × market value weight)

[1472] = (90 × 0.5) + (70 × 0.3) + (80 × 0.2)

[1473] = 45 + 21 + 16

[1474] = 82

[1475] If the total score exceeds a threshold (e.g., 75 points), the server selects the idea as valuable and notifies the user. This allows the system of the present invention to efficiently evaluate ideas and select them fairly.

[1476] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1477] Step 1:

[1478] Submit your idea

[1479] User: Using a web form or application, enter the "Title of the idea," "Detailed description," and "Related images and files (optional)," then click the "Submit" button.

[1480] Terminal: Takes user input data and sends it to the API endpoint in an HTTP POST request, including the idea title, detailed description, and associated files.

[1481] Server: Receives the API request and executes an INSERT statement to save the idea data in the database. Example: INSERT INTO ideas (title, description, files) VALUES (?, ?, ?)

[1482] Server: Returns an HTTP response (200 OK) to the user confirming that the idea was successfully submitted. The response includes a confirmation message.

[1483] Step 2:

[1484] Setting the review criteria

[1485] User (Administrator): Access the judging criteria setting screen via the web interface or app, and enter judging criteria such as "originality," "feasibility," and "market value" along with their respective weightings (e.g., originality 50%, feasibility 30%, market value 20%).

[1486] Terminal: Takes the administrator's input and sends it to the server via an HTTP POST request, which includes the criteria and their weights.

[1487] Server: Store the received criteria and weights in the database. Example: INSERT INTO criteria (originality_weight, feasibility_weight, market_value_weight) VALUES (?, ?, ?)

[1488] Server: Returns an HTTP response (200 OK) to the administrator confirming that the review criteria were successfully set. This response includes a confirmation message.

[1489] Step 3:

[1490] Idea Evaluation

[1491] Server: Get unrated ideas from the database. Example: SELECT FROM ideas WHERE evaluated = false

[1492] Server: Calls the generative AI model to evaluate each idea based on the evaluation criteria set for each idea. Generates prompts to send to the AI ​​model.

[1493] Generative AI model: Receives API requests and evaluates ideas using text analysis and natural language processing techniques, calculating scores (originality, feasibility, market value) based on each evaluation criteria.

[1494] Generative AI model: Returns the calculated score to the server, which includes the score for each assessment item and the final evaluation score.

[1495] Server: Using the received scores, calculate the total score by multiplying each score by the weight set in the evaluation criteria. Example: total_score = (originality_score originality_weight) + (feasibility_score feasibility_weight) + (market_value_score market_value_weight)

[1496] Server: Save the calculated total score to the database and update the idea's evaluated flag. Example: UPDATE ideas SET total_score = ?, evaluated = true WHERE id = ?

[1497] Step 4:

[1498] Picking up valuable ideas

[1499] Server: Select ideas from the database whose total score exceeds the threshold score. Example: SELECT FROM ideas WHERE total_score >= ?

[1500] Server: Compiles the selected ideas into a list and formats them in an accessible format (e.g. HTML or JSON).

[1501] Terminal: Renders the data received from the server and generates a screen displaying a list of valuable ideas for the user.

[1502] Step 5:

[1503] Notification of results

[1504] Server: Sends emails and in-app notifications to the winners of the ideas, including the score and reasons for the idea's selection.

[1505] Users: Receive notifications to find out if their ideas are selected as valuable ideas.

[1506] In this way, each processing step of the system is carried out efficiently through cooperation between users, terminals, and servers, from idea submission to evaluation, selection, and notification.

[1507] (Application example 1)

[1508] 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."

[1509] In recent years, there has been an increasing demand for efficient and fair evaluation in idea solicitation and selection. However, manual evaluation is time-consuming and laborious, and it is difficult to ensure fairness. While generative artificial intelligence (AI) is an alternative, it poses challenges, such as the difficulty of designing appropriate prompts to effectively evaluate ideas and the difficulty of calculating an overall evaluation by weighting the evaluation criteria. Furthermore, the process of quickly notifying evaluation results and providing feedback to users must be efficient.

[1510] 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.

[1511] In this invention, the server includes means for storing ideas received from users, means for storing evaluation criteria set by an administrator, means for evaluating ideas using a generative artificial intelligence, means for generating prompt sentences for ideas to be evaluated, means for requesting the generative artificial intelligence to evaluate the ideas using the prompt sentences, means for selecting valuable ideas based on the evaluation results, and means for notifying users of the results of the selected ideas. This makes it possible to evaluate ideas efficiently and fairly and provide prompt feedback to users.

[1512] "Users" are members of the public who submit ideas and suggestions.

[1513] An "Administrator" is a person or entity with the authority to set the criteria for evaluating ideas and oversee the evaluation process.

[1514] "Ideas" are new ideas or improvements suggested by users.

[1515] "Evaluation criteria" are measures such as originality, feasibility, and market value used to evaluate ideas.

[1516] "Generative AI" is AI that has the ability to evaluate ideas using natural language processing and text analysis.

[1517] A "prompt" is a specific instruction used when evaluating ideas using generative artificial intelligence.

[1518] The "evaluation result" is the score of the idea calculated by the generative artificial intelligence.

[1519] A "worthy idea" is an idea that receives a high rating based on the established evaluation criteria.

[1520] "Notification" is a message that notifies the user of the evaluation results or selection results.

[1521] A "server" is a computer system that stores ideas submitted by users and set evaluation criteria, and runs the generative artificial intelligence.

[1522] The present invention relates to a system for efficiently and fairly evaluating ideas received from users and selecting valuable ideas. This system includes the processes of registering ideas, setting review criteria by an administrator, evaluation by generative artificial intelligence, selection, and notification.

[1523] System Overview

[1524] 1. Submit your idea

[1525] Users can use the official application to register "new product ideas" and "improvement suggestions." Ideas can include titles, detailed descriptions, related images, files, and other attachments.

[1526] When the send button is clicked, data is sent from the terminal to the server.

[1527] 2. Setting the screening criteria

[1528] Administrators access the administrator screen within the app to set the evaluation criteria (e.g., originality, feasibility, market value) and their weighting.

[1529] The evaluation criteria set by the administrator are stored on the server.

[1530] 3. Evaluating ideas

[1531] The server retrieves unrated ideas from the database, then generates prompts for the ideas to be rated.

[1532] The generated prompt is used to request an evaluation of the idea from the generative AI, which then performs text analysis and natural language processing according to the prompt to calculate an evaluation score based on each criterion.

[1533] 4. Selecting Valuable Ideas

[1534] The server calculates an overall score based on the weighting of the evaluation scores obtained from the generative artificial intelligence.

[1535] Ideas whose overall score exceeds the set standard are selected as worthy ideas.

[1536] 5. Notification of Results

[1537] The server will then send a notification to the submitter of the selected idea, including the evaluation score and the reason for the selection.

[1538] Hardware and software used

[1539] Server: A computer system that stores ideas received from users and set evaluation criteria, and runs generative AI. A Linux-based server or cloud service (e.g., Amazon Web Services, Google Cloud Platform) can be used.

[1540] Generative AI: An AI model capable of natural language processing. Specifically, OpenAI's GPT-3 is used.

[1541] Database: A system for managing data on stored ideas and evaluation criteria. An SQL database (e.g., MySQL, PostgreSQL) can be used.

[1542] Specific examples

[1543] A user submits an idea for an "eco-bag sharing service." The administrator sets the judging criteria as 50% originality, 30% feasibility, and 20% market value. The server retrieves unrated ideas and evaluates them using the following prompts from a generative AI:

[1544] Prompt Sentence Examples

[1545] "Please rate this new product idea. The title of the idea is 'Eco Bag Sharing Service' and the detailed description is 'We will create a system for sharing used eco bags to reduce environmental impact.' Please rate each item (originality, feasibility, market value) on a scale of 1 to 10 and return each score."

[1546] The generative AI analyzes the text based on the prompt and returns a score for each evaluation criterion. The server calculates the overall score based on the results, and if the score exceeds the criterion, a notification message is sent to the user. The notification includes the evaluation score and the reason for the selection, allowing the user to check the content.

[1547] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1548] Step 1:

[1549] Users use the official application to register their ideas. The data they enter is the idea title, detailed description, and related images and files. When the user clicks the "Submit" button, the device sends this data to the server as an API request.

[1550] Step 2:

[1551] The server receives the API request sent from the device and saves the idea data in the database. At this time, it generates a response confirming that the data was saved successfully and sends it back to the device. The server then notifies the user that the data was saved successfully.

[1552] Step 3:

[1553] The administrator sets the evaluation criteria from the application's administration screen. The data to be entered are evaluation criteria such as "originality," "feasibility," and "market value," along with their weighting (e.g., originality 50%, feasibility 30%, market value 20%). When the administrator clicks the "Set" button, the device sends this data to the server as an API request.

[1554] Step 4:

[1555] The server saves the evaluation criteria and their weights sent from the administrator's terminal in a database. At this time, it generates a response to confirm that the settings were completed successfully and returns it to the terminal. The server then notifies the administrator that the data was saved successfully.

[1556] Step 5:

[1557] The server retrieves unrated ideas from the database, then generates a prompt for each idea to rate it, including the idea's title and detailed description, and sends it to the generative AI model.

[1558] Step 6:

[1559] The server uses the generated prompt to request a generative AI (e.g., GPT-3) to evaluate the idea. The generative AI performs text analysis and natural language processing based on the prompt, and calculates a score for each criterion, such as originality, feasibility, and market value.

[1560] Step 7:

[1561] The server receives the scores returned by the generative AI and calculates an overall rating for each score based on the weights set by the administrator. For example, if originality is 7, feasibility is 8, and market value is 6, the overall rating score is calculated as (7 0.5 + 8 0.3 + 6 0.2).

[1562] Step 8:

[1563] The server selects valuable ideas based on the calculated overall evaluation score. Ideas whose overall evaluation score exceeds a set standard are selected and stored in a database.

[1564] Step 9:

[1565] The server will then send a notification to the submitter of the selected idea, including the evaluation score and the reason for the selection. The notification will be sent via in-app notification or email, and the user can check the content.

[1566] Step 10:

[1567] The user receives a notification from the server to know that their idea has been selected. The user can check the evaluation score and the reason for the selection in the notification and understand the details of how their idea was evaluated.

[1568] 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.

[1569] ---

[1570] The present invention provides a system that efficiently evaluates ideas received from users and selects valuable ideas, as well as a system that recognizes users' emotions and takes them into account in the evaluation results. This system can be implemented in the following manner.

[1571] System Overview

[1572] 1. Submit your idea

[1573] User: Using a web form or application, enter the "Title of the idea," "Detailed description," and "Related images and files (optional)."

[1574] User: Click the "Submit" button to submit your idea.

[1575] Terminal: Issues an API request to send user input data to the server.

[1576] Server: Receives API requests and stores the input idea data in a database.

[1577] Server: Returns a response to the user confirming that the idea was successfully submitted.

[1578] 2. Setting the screening criteria

[1579] User (Administrator): The administrator accesses the review criteria settings screen via the web interface or app.

[1580] User (Administrator): Enter evaluation criteria such as "originality," "feasibility," and "market value," and set the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[1581] Terminal: Sends the evaluation criteria and their weighting set by the administrator to the server.

[1582] Server: Stores the received criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[1583] 3. Evaluating ideas

[1584] Server: Retrieves unrated ideas from the database.

[1585] Server: Calls the generative AI to evaluate each idea based on the evaluation criteria set for each idea obtained.

[1586] Generative AI: It performs text analysis and natural language processing on each idea to calculate scores such as "originality," "feasibility," and "market value."

[1587] Generative AI: Based on the calculated score, the idea is given a final evaluation score, where an overall score is calculated using the set weights.

[1588] Server: Stores the evaluation scores returned by the generative AI in a database.

[1589] 4. Emotion evaluation using an emotion engine

[1590] Server: Utilizing the emotion engine, we obtain user emotion data when submitting an idea. This data is analyzed from the text and voice when the user enters the idea.

[1591] Emotion engine: Recognizes emotions from user input, facial expressions, and voice, and generates an emotion score such as positive or negative.

[1592] Server: Stores the sentiment scores in a database and adds them to the overall rating of the idea.

[1593] 5. Picking up valuable ideas

[1594] Server: Based on the evaluation and sentiment scores stored in the database, the server selects ideas that exceed a benchmark score, which is determined based on minimum criteria set by the administrator.

[1595] Server: compiles the ideas into a list and makes them accessible to users.

[1596] Terminal: Generates a screen displaying a list of picked ideas and shows it to the user.

[1597] 6. Notification of Results

[1598] Server: Sends emails and in-app notifications to submitters of selected ideas informing them of the evaluation results.

[1599] Users will receive a notification to find out if their idea was featured, along with a rating score, reasons for selection, and sentiment score for the idea.

[1600] Specific examples

[1601] When a user submits an idea for a "smart trash can," the device sends the data to the server, where the idea is stored in a database. The administrator sets the evaluation criteria, such as "originality," "feasibility," and "market value," and these are stored on the server.

[1602] The server uses generative AI to evaluate the "smart trash cans" and calculate a score based on each criterion. An emotion engine also analyzes the user's emotions at the time of submission and generates an emotion score. If the overall score exceeds the criteria, the server selects the idea as a valuable idea, and the device displays a list of the ideas. Finally, the user receives a notification, where they can view the emotion score along with the evaluation results.

[1603] In this way, the system of the present invention can efficiently and fairly carry out the entire process from soliciting ideas from users to ultimately selecting valuable ideas. This significantly improves the accuracy and efficiency of the idea discovery process in companies and organizations. Furthermore, by taking user emotions into account, a more human-like evaluation system can be realized.

[1604] The processing flow will be explained below.

[1605] Program processing flow

[1606] Step 1:

[1607] A user uses a web form or application to enter an idea title, a detailed description, and optional related images and files.

[1608] Step 2:

[1609] The user clicks the "Send" button, and the terminal sends the idea data to the server.

[1610] Step 3:

[1611] The server receives the API request and stores the input idea data in a database.

[1612] Step 4:

[1613] The server returns a response confirming to the user that the idea was successfully submitted.

[1614] Step 5:

[1615] The user (administrator) accesses the review criteria settings screen via the web interface or app.

[1616] Step 6:

[1617] The user (administrator) inputs evaluation criteria such as "originality," "feasibility," and "market value," and sets the weighting for each (e.g., originality 50%, feasibility 30%, market value 20%).

[1618] Step 7:

[1619] The terminal sends the evaluation criteria and their weighting set by the administrator to the server.

[1620] Step 8:

[1621] The server stores the received evaluation criteria and weights in a database and sends a response to the administrator confirming that the settings were successful.

[1622] Step 9:

[1623] The server retrieves unrated ideas from the database.

[1624] Step 10:

[1625] The server calls a generative AI to evaluate each idea it receives based on the evaluation criteria set for each idea.

[1626] Step 11:

[1627] Generative AI performs text analysis and natural language processing on each idea, calculating scores for "originality," "feasibility," "market value," and other factors.

[1628] Step 12:

[1629] Based on the calculated scores, the generative AI assigns a final evaluation score to the idea, which calculates an overall score using the weights you set.

[1630] Step 13:

[1631] The server stores the evaluation scores returned by the generative AI in a database.

[1632] Step 14:

[1633] The server uses an emotion engine to acquire the user's emotion data when submitting an idea.

[1634] Step 15:

[1635] The emotion engine recognizes emotions from the user's input, facial expressions, and voice, and generates an emotion score such as positive or negative.

[1636] Step 16:

[1637] The server stores the emotion scores in a database and adds them to the overall evaluation of the idea.

[1638] Step 17:

[1639] The server selects ideas that exceed the standard score based on the evaluation scores and sentiment scores stored in the database.

[1640] Step 18:

[1641] The server compiles a list of picked ideas and makes them accessible to users.

[1642] Step 19:

[1643] The device generates a screen displaying a list of the picked ideas and shows it to the user.

[1644] Step 20:

[1645] The server will send an email or in-app notification to the submitter of the picked idea informing them of the evaluation results.

[1646] Step 21:

[1647] Users will receive a notification to find out if their idea was featured, along with a rating score, reasons for selection, and sentiment score for the idea.

[1648] Through the above steps, the system of the present invention can efficiently and fairly collect ideas from users, select the most valuable ideas, and evaluate them while taking their emotions into consideration.

[1649] Example 2

[1650] 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."

[1651] Conventional idea evaluation systems have difficulty in efficiently and fairly evaluating ideas submitted by users, and in particular, they lack consideration of user emotions in their evaluations. As a result, there is a problem in which valuable ideas are not properly selected.

[1652] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for storing ideas received from users, a means for storing evaluation criteria set by an administrator, a means for evaluating ideas using a generative AI model, a means for analyzing user emotion data using an emotion engine and generating an emotion score, a means for selecting valuable ideas based on the evaluation results and the emotion score, and a means for notifying the user of the results of the selected ideas. This allows ideas to be evaluated efficiently and fairly, and by taking user emotions into consideration, more appropriate and valuable ideas can be selected.

[1653] "User" refers to a user who submits an idea to the system.

[1654] "Administrator" refers to the person in charge of setting the system's review criteria and managing the system as a whole.

[1655] "Evaluation criteria" refers to the criteria for evaluating ideas, including items such as originality, feasibility, and market value.

[1656] A "generative AI model" is an artificial intelligence model used to evaluate ideas, using text analysis and natural language processing techniques.

[1657] An "emotion engine" refers to a technology that analyzes a user's emotional data and generates an emotional score, such as positive or negative.

[1658] "Evaluation results" refers to the aggregated scores and evaluations of ideas calculated by the generative AI model.

[1659] "Emotion score" refers to a numerical representation of a user's emotional state calculated by the emotion engine.

[1660] "Valuable Ideas" refer to useful ideas that have been comprehensively evaluated and selected based on set evaluation criteria and emotional scores.

[1661] "Notification" refers to a means of communication to inform users of the evaluation results and information about selected ideas.

[1662] System Overview

[1663] This invention is a system that efficiently evaluates ideas submitted by users and selects valuable ideas. It also recognizes the user's emotions and incorporates them into the evaluation results. This system utilizes the following hardware and software:

[1664] Server: Stores ideas and evaluation data in a database and interacts with generative AI models and emotion engines.

[1665] Terminal: Provides an interface for users and administrators to access and send and receive data.

[1666] Users: Submit ideas and receive notifications of results.

[1667] Specific processing of the system

[1668] Submit your idea

[1669] The user uses a web form or application to enter the "idea title," "detailed description," and "related images and files (optional)." When the user clicks the "Submit" button, the device sends the data to the server. The server receives the API request, saves the idea in a database, and notifies the user that the idea has been successfully submitted.

[1670] Setting the review criteria

[1671] The user (administrator) accesses the evaluation criteria setting screen and sets evaluation criteria such as "originality," "feasibility," and "market value" along with the weighting of each. The terminal sends the setting information to the server, which stores the data in a database. The server also notifies the administrator that the setting was successful.

[1672] Idea Evaluation

[1673] The server retrieves unrated ideas from the database. For each idea, the server invokes a generative AI model and performs text analysis and natural language processing to calculate scores for "originality," "feasibility," "market value," etc. The evaluation results are returned to the server, which calculates an overall score and stores it in the database.

[1674] Emotion evaluation by emotion engine

[1675] The server uses an emotion engine to obtain the user's emotion data when they submit an idea. It recognizes emotions from the user's input, facial expressions, and voice, and generates an emotion score. The emotion score is stored in a database and is reflected in the overall evaluation of the idea.

[1676] Picking up valuable ideas

[1677] The server selects ideas that exceed the benchmark score based on the evaluation score and sentiment score, and the selected ideas are displayed in a list on the terminal for user access.

[1678] Notification of results

[1679] Finally, the server generates an email or in-app notification to the submitter of the selected idea informing them of the evaluation result. Users can receive the notification and check whether their idea was selected. The notification also includes the idea's evaluation score, the reason for selection, and the sentiment score.

[1680] Specific examples

[1681] When a user submits an idea for a "smart trash can," the device sends the data to the server, and the idea is saved in a database. An administrator sets the evaluation criteria of "originality," "feasibility," and "market value," which are saved on the server. The server uses a generative AI model to evaluate the "smart trash can" and calculates a score based on each criterion. An emotion engine also analyzes the user's emotions at the time of submission and generates an emotion score. If the overall score exceeds the criteria, the server selects the idea as a valuable idea, and the device displays a list. Finally, the user is notified and can check the emotion score along with the evaluation results.

[1682] Prompt Sentence Examples

[1683] Please calculate a score for the idea "Smart Trash Can" based on the following criteria: Originality 50%, Feasibility 30%, Market Value 20%. Also, please consider the user's sentiment (positive or negative) at the time of submission and give an overall score.

[1684] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1685] Step 1: Submit your idea

[1686] A user opens a web form or application and enters the "idea title," "detailed description," and "related images and files (optional)." For example, a user enters the title "Smart Trash Can" and a specific description.

[1687] Input: Title, description, related images and files

[1688] The device incorporates the user's input data into an API request and sends it to the server in JSON format.

[1689] The server receives the API request and checks the data format and required fields, for example, whether the title is empty and whether a detailed description is provided.

[1690] Output: Save notification

[1691] If there are no problems, the server saves the idea in a database and generates a response informing the user that the idea was successfully submitted.

[1692] Step 2: Setting the review criteria

[1693] The user (administrator) accesses the evaluation criteria setting screen and sets evaluation criteria such as "originality," "feasibility," and "market value" and the weighting of each.

[1694] Input: Judging criteria and weighting

[1695] The device incorporates the set evaluation criteria and their weighting into an API request and sends it to the server.

[1696] The server stores the received evaluation criteria and weights, and performs database operations for storage.

[1697] Output: Configuration confirmation notice

[1698] The server generates and sends a response to the administrator indicating that the setting was successful.

[1699] Step 3: Evaluate your ideas

[1700] The server retrieves unrated ideas from the database, for example the most recently added "smart trash can" idea.

[1701] Input: Unrated idea data

[1702] The server calls a generative AI model for each idea it receives, using the set evaluation criteria as prompts.

[1703] The generative AI model performs text analysis and natural language processing on each idea to calculate scores for originality, feasibility, market value, etc. For example, for the prompt sentence "smart trash can," the overall score is calculated with weights of 50% for originality, 30% for feasibility, and 20% for market value.

[1704] Output: Evaluation score

[1705] The generative AI model calculates a final evaluation score based on the calculated scores and returns it to the server, which stores the score in a database.

[1706] Step 4: Emotion evaluation by the emotion engine

[1707] The server uses an emotion engine to obtain user emotion data when an idea is submitted, for example by analyzing text or voice data.

[1708] Input: User text and voice data

[1709] The emotion engine recognizes emotions from the user's input, facial expressions, and voice, and generates an emotion score such as positive or negative.

[1710] Output: Sentiment score

[1711] The server stores the generated emotion scores in a database and adds them to the overall evaluation of the idea.

[1712] Step 5: Identifying valuable ideas

[1713] The server selects ideas that exceed a threshold score based on their rating and sentiment scores, which are based on minimum criteria set by the administrator.

[1714] Input: Rating score, sentiment score, criteria score

[1715] The server compiles a list of the selected ideas and makes it accessible to users.

[1716] Output: List of selected ideas

[1717] The device generates a screen displaying a list of the ideas picked up and shows it to the user. By providing a user-friendly interface, the user can easily and quickly check the evaluation results.

[1718] Step 6: Notification of results

[1719] The server generates emails and in-app notifications to the submitters of the selected ideas informing them of the evaluation results.

[1720] Input: Picked idea data, user contact information

[1721] The server generates and sends a notification to the submitter, which includes the rating score, the reason for selection, and the sentiment score.

[1722] Output: Information message

[1723] Users will receive a notification to see if their idea has been picked up, and can use the information in the notification to decide what to do next.

[1724] (Application example 2)

[1725] 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."

[1726] Conventional idea evaluation systems do not take into account the user's emotions when evaluating ideas submitted by users, resulting in a lack of human-like evaluation and the possibility of overlooking high-quality ideas. Furthermore, the evaluation process is inefficient, making it difficult to process when a large number of ideas are submitted.

[1727] The identification process 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 storing ideas received from users, means for storing evaluation criteria set by an administrator, means for evaluating the ideas using a generative AI based on the stored ideas, means for acquiring user emotion data and performing emotion recognition, means for selecting valuable ideas based on the evaluation results and the emotion data, and means for notifying the user of the results of the selected ideas. This enables human-like evaluation that takes user emotions into consideration, making it possible to evaluate many ideas efficiently and fairly.

[1728] "User" means an individual or organization that submits an idea and receives the evaluation results.

[1729] "Administrator" refers to the person or organization that sets the system's review criteria and oversees the idea evaluation and selection process.

[1730] An "idea" is a specific proposal for a new product or service that a user has invented.

[1731] "Evaluation criteria" are indicators used to evaluate ideas, and include criteria such as "originality," "feasibility," and "market value."

[1732] "Generative AI" is an artificial intelligence system that uses text analysis and natural language processing to automatically evaluate ideas.

[1733] "Emotion data" is data that indicates the user's emotions at the time of submitting the idea, and is obtained from text, facial expressions, voice, etc.

[1734] "Emotion recognition" is the process of analyzing a user's emotional data and determining whether the emotion is positive or negative.

[1735] "Evaluation results" refer to the evaluation scores for each idea calculated using generative AI and emotion recognition technology.

[1736] A "valuable idea" is an idea that receives a high rating based on established evaluation criteria and evaluation using emotional data.

[1737] "Notification methods" are mechanisms for informing users of the evaluation results and information about selected ideas, and include email and in-app notifications.

[1738] The system of the present invention is capable of efficiently evaluating ideas submitted by users and performing a comprehensive evaluation that takes into account the user's emotions. The system operates by appropriately arranging hardware and software. A specific example of the system is shown below.

[1739] Hardware and Software Configuration

[1740] server:

[1741] Role: Central data processing and management.

[1742] Software: Flask (a Python web application framework), database (e.g., MySQL), generative AI model (natural language processing), emotion recognition engine.

[1743] Device:

[1744] Role: Provides an interface for users to submit ideas.

[1745] Software: Web forms and custom applications.

[1746] User:

[1747] Role: Submit ideas and review evaluation results.

[1748] System Operation

[1749] Submit your idea

[1750] Users enter their ideas and related data through a web form or a dedicated application and send it to the server, which receives it and stores it in a database, allowing users to register their ideas in the system.

[1751] Setting the review criteria

[1752] Administrators set the judging criteria through a web interface or application, which are then stored in a database by the server, establishing the criteria necessary for evaluating ideas.

[1753] Idea Evaluation

[1754] The server calls a generative AI model, analyzes the text of the registered idea, and evaluates it. This generative AI calculates scores for "originality," "feasibility," "market value," and other factors, and returns the results to the server. At the same time, an emotion recognition engine is used to analyze the emotions felt when the user inputs the idea. Emotional data is obtained from voice and text, and a score such as positive or negative is generated.

[1755] Effective evaluation and communication of results

[1756] The server combines the evaluation score and sentiment score to calculate an overall score. Ideas whose overall score meets certain criteria are selected and the result is notified to the user via email or in-app notification, allowing the user to check the evaluation results.

[1757] Specific examples

[1758] For example, if a user submits an idea for a "smart trash can," the system works as follows: The user inputs the text of the idea and sends it to the server along with its emotional data. The server uses a generative AI model to evaluate the idea and calculates scores for "originality," "feasibility," and "market value." At the same time, an emotional recognition engine analyzes the user's emotional data and generates a positive emotional score. An overall score is calculated, and if it meets the criteria, the user is notified.

[1759] Example prompt sentence:

[1760] A user submitted a new product idea: "Health management system using a smartwatch."

[1761] Please rate this idea's "originality," "feasibility," and "market value."

[1762] In your evaluation results, please include a score (1-10) for each item and the reason for your score.

[1763] In this way, the system of the present invention realizes human-like evaluation that takes into account the user's emotions, and by efficiently evaluating many ideas, it is possible to pick out valuable ideas.

[1764] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1765] Step 1:

[1766] Users input their ideas through a web form or application on their device. This includes the text data of the idea, related images and files, and the user's emotional data (voice, facial expressions, etc.). Once the input data is ready, they click the "Send" button. Clicking the Send button becomes an input event, and the device sends the input data to the server as an API request.

[1767] Step 2:

[1768] The server receives the API request and saves the received data in the database. It stores the idea text data, related files, and emotion data in the appropriate tables in the database, and returns a response to the device indicating that the save operation was successful, allowing the user to confirm that their idea was successfully submitted.

[1769] Step 3:

[1770] The administrator sets the evaluation criteria using a web interface or application. They input the evaluation criteria, such as "originality," "feasibility," and "market value," to be used to evaluate users' ideas, along with their respective weights (e.g., originality 50%, feasibility 30%, market value 20%), and click "Save." The device then sends this setting data to the server.

[1771] Step 4:

[1772] The server saves the evaluation criteria data received from the administrator in the database and returns a response indicating that the save operation was successful to the administrator's terminal. This ensures that the evaluation criteria are applied to the system and will be used for the next idea evaluation.

[1773] Step 5:

[1774] The server retrieves unrated ideas from the database. Based on the retrieved idea data, it invokes a generative AI model to perform text analysis and natural language processing. This calculates scores for each idea in terms of "originality," "feasibility," and "market value," and returns these to the server. The output is idea evaluation data with each score assigned.

[1775] Step 6:

[1776] The server passes the emotional data acquired from the user when submitting the idea to the emotion recognition engine for emotion analysis. The emotion recognition engine analyzes the voice and facial expression data and generates an emotional score, such as positive or negative. This emotional score is returned to the server and added to the evaluation data.

[1777] Step 7:

[1778] The server combines the scores obtained from the generative AI model and the emotion recognition engine to calculate an overall evaluation score. It then calculates a weighted average of each score based on the weights of the set evaluation criteria to calculate a final overall score. Ideas whose overall score meets certain criteria are selected as valuable ideas.

[1779] Step 8:

[1780] The server stores the evaluation results of the selected worthy ideas in a database. It then generates emails or in-app notifications to inform users of the results of the selected ideas. The notifications include details of the evaluation results (individual scores, overall score, and sentiment score) to ensure users fully understand the evaluation process.

[1781] Step 9:

[1782] Users will receive a notification to check the results of their idea evaluation. By clicking the link in the notification, they can view the detailed evaluation results through a web interface or application. This allows users to understand how their idea was evaluated and get hints for improvement.

[1783] Through this series of processes, users submit ideas and receive evaluation results, which motivates them to submit higher quality ideas and improves the quality of the entire system.

[1784] 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.

[1785] 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.

[1786] 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.

[1787] 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.

[1788] FIG. 9 illustrates 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 behaviors 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.

[1789] 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.

[1790] 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).

[1791] 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.

[1792] 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."

[1793] 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.

[1794] 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).

[1795] 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.

[1796] 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.

[1797] 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.

[1798] 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.

[1799] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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 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.

[1800] 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.

[1801] 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.

[1802] 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.

[1803] 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.

[1804] 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.

[1805] The following is further disclosed regarding the above embodiment.

[1806] (Claim 1)

[1807] a means for storing ideas received from users;

[1808] A means for saving the review criteria set by the administrator;

[1809] a means for evaluating ideas using generative AI based on the stored ideas;

[1810] A means of selecting valuable ideas based on the evaluation results;

[1811] a means for notifying the user of the results of the selected ideas;

[1812] A system including:

[1813] (Claim 2)

[1814] The system of claim 1, wherein the ideas are evaluated based on weighting using evaluation criteria set by an administrator.

[1815] (Claim 3)

[1816] The system of claim 1 uses generative AI to evaluate ideas, and employs text analysis and natural language processing techniques.

[1817] "Example 1"

[1818] (Claim 1)

[1819] a means for storing ideas received from users;

[1820] A means for saving the review criteria set by the administrator;

[1821] a means for evaluating the ideas using a generative AI model based on the stored ideas;

[1822] A method for selecting valuable ideas that exceed the standard score based on the evaluation score;

[1823] a means for notifying users of the evaluation results of the selected ideas;

[1824] A system including:

[1825] (Claim 2)

[1826] The system of claim 1, wherein the ideas are evaluated based on weighting using evaluation criteria set by an administrator.

[1827] (Claim 3)

[1828] 10. The system of claim 1, which uses a generative AI model to evaluate ideas and employs text analysis and natural language processing techniques.

[1829] "Application Example 1"

[1830] (Claim 1)

[1831] a means for storing ideas received from users;

[1832] a means for storing evaluation criteria set by an administrator;

[1833] means for evaluating ideas using generative artificial intelligence based on the stored ideas;

[1834] A means of selecting valuable ideas based on the evaluation results;

[1835] a means for notifying the user of the results of the selected ideas;

[1836] a means for generating prompt statements for ideas to be evaluated;

[1837] a means for requesting an evaluation of an idea from a generative artificial intelligence using a prompt;

[1838] A system including:

[1839] (Claim 2)

[1840] The system of claim 1, wherein the ideas are evaluated based on weights using evaluation criteria set by an administrator.

[1841] (Claim 3)

[1842] The system of claim 1 uses generative artificial intelligence to evaluate ideas, and employs text analysis and natural language processing techniques.

[1843] "Example 2: Combining Emotion Engines"

[1844] (Claim 1)

[1845] a means for storing ideas received from users;

[1846] A means for saving the review criteria set by the administrator;

[1847] a means for evaluating the ideas using a generative AI model based on the stored ideas;

[1848] means for using an emotion engine to analyze the user's emotion data and generate an emotion score;

[1849] A means for selecting valuable ideas based on the evaluation results and sentiment scores;

[1850] a means for notifying the user of the results of the selected ideas;

[1851] A system including:

[1852] (Claim 2)

[1853] The system of claim 1, wherein the ideas are evaluated based on weighting using evaluation criteria set by an administrator.

[1854] (Claim 3)

[1855] 10. The system of claim 1, which uses a generative AI model to evaluate ideas and employs text analysis and natural language processing techniques.

[1856] "Application example 2 when combining emotion engines"

[1857] (Claim 1)

[1858] a means for storing ideas received from users;

[1859] A means for saving the review criteria set by the administrator;

[1860] a means for evaluating ideas using generative AI based on the stored ideas;

[1861] A means for acquiring user emotion data and performing emotion recognition;

[1862] a means for selecting valuable ideas based on the evaluation results and sentiment data;

[1863] a means for notifying the user of the results of the selected ideas;

[1864] A system including:

[1865] (Claim 2)

[1866] The system according to claim 1, wherein the ideas are evaluated based on evaluation criteria set by an administrator and weighting using emotional data.

[1867] (Claim 3)

[1868] The system of claim 1 uses generative AI to evaluate ideas, and employs text analysis, natural language processing, and emotion recognition technologies. [Explanation of symbols]

[1869] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for storing ideas received from users; A means for saving the review criteria set by the administrator; a means for evaluating ideas using generative AI based on the stored ideas; A means of selecting valuable ideas based on the evaluation results; a means for notifying the user of the results of the selected ideas; A system including:

2. The system of claim 1, wherein the ideas are evaluated based on weights using evaluation criteria set by an administrator.

3. The system of claim 1 uses generative AI to evaluate ideas, and employs text analysis and natural language processing techniques.

Images