System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting historical proposal data; means for pre-processing the proposal data; means for extracting features from the pre-processed data and training a model to evaluate similarity, creativity, and feasibility; means for inputting a newly proposed idea; means for pre-processing and analyzing the newly input idea using the model; means for generating feedback based on the analysis; and means for displaying the feedback to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Idea contests attract many proposals, but participants often find it difficult to objectively assess how their ideas differ from past proposals and how innovative they are. As a result, many ideas may be overlooked without being properly scrutinized for evaluation. Furthermore, participants have limited means of receiving specific feedback on how to improve their proposals to receive high evaluation in the contest. This makes it difficult to improve the quality of their ideas, resulting in an unhealthy competition in the contest. Based on this background, the present invention aims to provide a system that compares new ideas with past proposals, evaluates similarities, originality, and feasibility, and provides feedback to help participants objectively evaluate their proposals and identify areas for improvement. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including: means for collecting past proposal data; means for preprocessing the proposal data; means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility; means for inputting newly proposed ideas; means for preprocessing the newly input ideas and analyzing them using the model; means for generating feedback based on the analysis results; and means for displaying the feedback to a user.

[0006] The proposal data includes text data and image data, allowing for multifaceted evaluation of the data. Furthermore, the model uses a language processing model based on deep learning to achieve advanced analysis. This system allows users to predict how their ideas will be evaluated in the contest and provides specific directions for improvement, helping to improve the quality of their ideas.

[0007] "Past proposal data" refers to data containing information about ideas that have been submitted to idea contests in the past, and includes text data and image data.

[0008] "Means of collection" refers to the software and hardware capabilities for capturing information from databases and external sources.

[0009] "Preprocessing means" refers to a function that performs processing to convert data into a format suitable for analysis, and includes things like tokenizing text and resizing images.

[0010] "Features" refer to important parts or patterns extracted from data and used for analysis and model training.

[0011] "Means for training a model" refers to the processes and functions that use deep learning algorithms to learn patterns from data and generate models that make predictions or evaluations.

[0012] A "newly proposed idea" is an idea that a user newly inputs into the system and includes information that has not yet been analyzed.

[0013] "Input means" refers to an interface that allows a user to input ideas into the system and a function for receiving such inputs.

[0014] "Means for analysis using preprocessed data" refers to the process and function of inputting preprocessed data into a model to evaluate the similarity, originality, and feasibility of ideas.

[0015] "Means for generating feedback" refers to the process and function for presenting the evaluation results and points for improvement of an idea to the user based on the analysis results.

[0016] "Means for displaying to the user" refers to the interface and functionality for visually displaying the generated feedback to the user. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

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

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

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

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

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

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

[0038] The present invention relates to a system that analyzes data from past idea contests and predicts the evaluation of newly submitted ideas. First, a means for collecting and preprocessing past proposal data is provided. Next, a means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility is provided. A means for inputting newly proposed ideas is provided, and the input ideas are preprocessed and analyzed using the model. Next, a means for generating feedback based on the analysis results is provided, and finally, a means for displaying the feedback to the user is provided.

[0039] Program processing overview

[0040] Data collection

[0041] The server collects proposal data from a database of past idea contests, including text data (titles and descriptions of ideas) and image data (visual descriptions of ideas).

[0042] Data Preprocessing

[0043] The server preprocesses the collected text data. Specifically, it tokenizes the text, removes stop words, normalizes characters, etc. For image data, it resizes the data and extracts features.

[0044] Model training

[0045] The server trains the model using the preprocessed data. It uses a deep learning algorithm (e.g., GPT-4® V) to generate a model that evaluates the similarity, originality, and feasibility of ideas. 80% of the training data is used for training, and 20% is used for validation.

[0046] Input and preprocessing of new ideas

[0047] Users input new ideas into the system, including text entry and (optionally) image uploads. The device sends this data to the server, which then pre-processes it.

[0048] Idea Analysis

[0049] The server uses the pre-processed new idea data to perform analysis with the trained model, including calculating a similarity score by comparing it with past idea data and generating an originality score and a feasibility score.

[0050] Feedback Generation

[0051] The server generates feedback based on the analysis results, specifically a report containing a list of similar past ideas, an analysis of originality, a feasibility assessment, and specific improvements.

[0052] Feedback Display

[0053] The device receives feedback from the server and displays it to the user, including visual graphs and detailed text, presented in a format that is intuitively understandable to the user.

[0054] Specific examples

[0055] For example, suppose a user proposes an "innovative recycling system." The user enters a detailed description of the idea in text and uploads related images. The device sends this data to the server, which then performs preprocessing.

[0056] The server uses the preprocessed data to evaluate the similarity, originality, and feasibility of new ideas. The evaluation results in a similarity score of 75%, an originality score of 85 / 100, and a feasibility score of 70 / 100. Based on this information, specific improvements (e.g., improving cost efficiency, linking with other recycling technologies, etc.) are suggested.

[0057] Finally, the device visually displays this feedback to the user, allowing them to understand how their ideas are evaluated and providing specific directions for improvement.

[0058] In this way, the present invention is a system that helps participants objectively evaluate and effectively improve their ideas, thereby improving the quality and soundness of idea contests.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The server collects proposal data from past idea contests from a database, including text data (e.g., idea titles, detailed descriptions) and image designs (e.g., visual descriptions of ideas).

[0062] Step 2:

[0063] The server preprocesses the collected text data by tokenizing the text (splitting sentences into words and phrases), removing stop words (common words not needed for analysis), and normalizing characters (converting all to lowercase and removing special characters).

[0064] Step 3:

[0065] The server preprocesses the image data collected by resizing the images to a uniform size and extracting features (edges, color, shape, etc.).

[0066] Step 4:

[0067] The server trains the model using the preprocessed data. It uses deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of the proposals. 80% of the training data is used for training, and 20% is used for validation.

[0068] Step 5:

[0069] A user enters a new idea into the system by entering a title and detailed description of the idea in text boxes, and optionally uploading an associated image.

[0070] Step 6:

[0071] The terminal transmits the data input by the user to the server.

[0072] Step 7:

[0073] The server preprocesses the text data of new ideas. Similar to the preprocessing of collected data, it performs tokenization, stopword removal, and character normalization.

[0074] Step 8:

[0075] The server preprocesses the image data of the new idea. Similar to the preprocessing of collected data, it resizes and extracts features.

[0076] Step 9:

[0077] The server inputs the preprocessed new idea data into the model and performs analysis, calculating the idea similarity score, originality score, and feasibility score.

[0078] Step 10:

[0079] The server generates feedback based on the analysis, including a list of similar ideas from previous ideas, an analysis of originality, and an assessment of feasibility, as well as specific improvements and recommendations.

[0080] Step 11:

[0081] The device receives feedback from the server and displays it to the user in the form of visual graphs and detailed text, in a format that is intuitively understandable to the user.

[0082] Example 1

[0083] 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."

[0084] Conventional idea contests often lack fairness and objectivity because submitted ideas are evaluated subjectively by human judges. Furthermore, systems for efficiently analyzing proposed ideas and suggesting areas for improvement are inadequate, making it difficult to improve the quality of diverse ideas. Furthermore, while rapid and accurate evaluation of the similarity, originality, and feasibility of new ideas is required, achieving this is not easy.

[0085] 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.

[0086] In this invention, the server includes: means for collecting past proposal data; means for preprocessing the proposal data; means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility; means for inputting newly proposed ideas; means for preprocessing the newly input ideas and analyzing them using the model; means for generating feedback based on the analysis results; means for displaying the feedback to a user; data preprocessing means for tokenizing the text data, removing stop words, and normalizing characters; data preprocessing means for resizing the image data and extracting features; and means for dividing the model into a training set and a validation set for training and generating an optimal model. This makes it possible to objectively and efficiently evaluate newly proposed ideas and present specific areas for improvement.

[0087] "Past proposal data" refers to information on proposals submitted to previous idea contests, and includes text data and image data.

[0088] "Means of collection" refers to the function that allows the server to obtain and store past proposal data through a database or API.

[0089] "Preprocessing means" refers to a function that processes the data collected by the server, such as tokenizing, removing stop words, normalizing characters, resizing, and extracting features, to optimize it for subsequent analysis and training.

[0090] "Means for extracting features" is a function for deriving the information (features) required for the model from preprocessed data.

[0091] "Means for training a model" refers to the function by which the server uses deep learning algorithms to build and optimize a model based on collected and preprocessed data.

[0092] A "newly proposed idea" is an idea that a user newly submits to the system, and includes text data and image data.

[0093] "Input means" refers to an interface or function that allows users to submit new ideas to the system.

[0094] "Means for analysis" refers to the function by which the server preprocesses newly proposed ideas and evaluates them for similarity, originality, feasibility, etc. using a trained model.

[0095] The "means for generating feedback" is a function in which the server creates a report containing specific evaluations and areas for improvement for the user based on the analysis results.

[0096] The "means for displaying feedback to the user" is a function by which the terminal presents the generated feedback to the user in a format that can be visually and intuitively understood.

[0097] "Tokenization" is the process of dividing text data into smaller units (tokens) such as words or phrases.

[0098] "Stop word removal" is the process of removing words that occur frequently but are semantically insignificant (e.g., the, and).

[0099] "Character normalization" is the process of transforming characters from different writing forms to make them uniform.

[0100] "Resizing" is the process of changing and unifying the size of an image.

[0101] "Feature extraction" is the process of extracting important information (features) from image or text data for the model to analyze.

[0102] A "training set" is the portion of a dataset used to train a model, accounting for approximately 80% of the total data.

[0103] A "validation set" is a portion of the dataset used to evaluate the performance and accuracy of a model, and accounts for approximately 20% of the total data.

[0104] The "optimal model" is the model that has been adjusted to show the highest accuracy and performance as a result of evaluation using training data and validation data.

[0105] The present invention relates to a system for analyzing data from past idea contests and predicting the evaluation of newly submitted ideas. The embodiments for carrying out the present invention will be described in detail below.

[0106] First, the hardware configuration of this system includes a server and a terminal. The server is mainly responsible for data collection, preprocessing, model training and evaluation, and feedback generation. The terminal provides an interface for users to input new ideas and receive feedback.

[0107] 1. Data Collection

[0108] The server collects proposal data from a database of past idea contests via API. The proposal data includes text data (titles and descriptions of ideas) and image data (visual descriptions of ideas). The collected data is stored in the server's local data storage.

[0109] 2. Data Preprocessing

[0110] The server preprocesses the collected text data using a natural language processing tool (e.g., NLTK). Specifically, the process includes the following steps:

[0111] Tokenization: Breaking text into words and phrases.

[0112] Stop word removal: removes frequently occurring but semantically insignificant words.

[0113] Character normalization: unifying different writing forms.

[0114] Additionally, the image data is pre-processed using a computer vision library (e.g., OpenCV):

[0115] Resize: Resize images to a uniform size.

[0116] Feature extraction: Features are extracted from images using SIFT (Scale-Invariant Feature Transform).

[0117] 3. Model training

[0118] Based on the preprocessed data, the server trains a model using a deep learning algorithm (e.g., GPT-4V). The dataset is divided into a training set (80%) and a validation set (20%). The server uses these datasets to build and optimize a model to evaluate the similarity, originality, and feasibility of ideas.

[0119] 4. Enter a new idea

[0120] The user inputs new ideas in text format and uploads related images through the device, which then sends this data to the server using an HTTP request.

[0121] 5. Idea Analysis

[0122] The server pre-processes new ideas and feeds them into a trained model for analysis, which involves comparing them with past idea data to calculate a similarity score and generating originality and feasibility scores.

[0123] 6. Feedback Generation and Display

[0124] The server generates feedback based on the analysis results and creates a report containing specific improvements and evaluation results. The device displays this report to the user in a visually and intuitive format.

[0125] Specific examples

[0126] For example, suppose a user proposes an "innovative recycling system." The user enters a detailed description of the idea in text and uploads related images. The device sends this data to the server, which performs preprocessing. An example of a specific prompt is as follows:

[0127] "Please rate the following idea: It is titled 'Innovative Recycling System' and proposes an environmentally friendly recycling process. Please provide details below. {Detailed Description} Also, upload relevant images. Please provide your rating results with a similarity score, originality score, feasibility score, and specific suggestions for improvement."

[0128] The server tokenizes the text data using NLTK, removes stop words, and performs Unicode normalization. It also resizes images using OpenCV and extracts features using SIFT. It then uses a pre-trained GPT-4V model to evaluate the similarity, originality, and feasibility scores of new ideas. For example, a similarity score of 75%, an originality score of 85 / 100, and a feasibility score of 70 / 100 are calculated.

[0129] Finally, the terminal visually displays this feedback to the user, allowing the user to understand the evaluation of their idea and specific areas for improvement. Through this process, the present invention enables the improvement of the quality and soundness of ideas.

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Step 1:

[0132] The server connects to a database of past idea contests. The input includes database access information and collection criteria. Specifically, the server calls an API and retrieves proposal data (text data and image data). The retrieved proposal data is saved in the server's local storage as an output.

[0133] Step 2:

[0134] The server preprocesses the collected text data. The input contains the acquired text data. Specifically, the server uses a natural language processing tool (e.g., NLTK) to tokenize the data, remove stop words, and normalize characters. The output is the preprocessed text data.

[0135] Step 3:

[0136] The server preprocesses the collected image data. The input contains the acquired image data. Specifically, the server resizes the image using a computer vision library (e.g., OpenCV) and extracts features using SIFT (Scale-Invariant Feature Transform). The output is the preprocessed image data.

[0137] Step 4:

[0138] The server uses the preprocessed data to train a model. The inputs include preprocessed text and image data and a deep learning algorithm (e.g., GPT-4V). Specifically, the server splits the data into a training set (80%) and a validation set (20%) and trains the deep learning model. The output is an optimized model.

[0139] Step 5:

[0140] A user uses a terminal to input a new idea in text format. The input includes a detailed description of the new idea and related images. Specific operations involve the user entering text and uploading images through the system interface. The output is the input data stored in the terminal.

[0141] Step 6:

[0142] The device sends input data for a new idea to the server. The input includes a detailed description and image of the idea stored on the device. In concrete terms, the device sends the data to the server using an HTTP request. The output is the data arriving at the server.

[0143] Step 7:

[0144] The server preprocesses the text data of new ideas. The input includes the submitted text data. Specific operations include tokenization, removal of stop words, and character normalization. The output is the preprocessed text data.

[0145] Step 8:

[0146] The server preprocesses the image data of the new idea. The input includes the transmitted image data. Specifically, the server resizes the image and extracts features. The output is the preprocessed image data.

[0147] Step 9:

[0148] The server analyzes the new idea using the trained model. The input includes preprocessed text data and image data of the new idea and the trained model. Specifically, the server inputs the data into the model and calculates a similarity score, originality score, and feasibility score. The output is the analysis result.

[0149] Step 10:

[0150] The server generates feedback based on the analysis results. The analysis results are included as input. In concrete terms, the server creates a feedback report, including improvements and evaluation results. The feedback report is obtained as output.

[0151] Step 11:

[0152] The terminal displays the feedback received from the server to the user. The input includes a feedback report. As a specific operation, the terminal visually displays the feedback through a user interface and presents it to the user. As an output, the user can confirm the feedback.

[0153] (Application example 1)

[0154] 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."

[0155] In recent years, factories and manufacturing industries have been required to improve efficiency and optimize designs, but evaluating new ideas and proposals requires a great deal of time and effort. It is also difficult to objectively evaluate ideas' similarity, originality, and feasibility, leaving employees with a lack of means to identify effective improvements. This makes it difficult to adopt and realize innovative ideas.

[0156] 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.

[0157] In this invention, the server includes means for collecting past proposal data, means for preprocessing the proposal data, means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility, means for inputting newly proposed ideas, means for preprocessing the newly input ideas and analyzing them using the model, means for generating feedback based on the analysis results, means for displaying the feedback to a user, and means for presenting specific improvements based on scores of similarity, originality, and feasibility of the new proposal. This allows a user to input a new idea via a smart device and quickly receive its evaluation results and improvements.

[0158] "Proposal data" is information about past proposals, and includes text data and image data.

[0159] "Preprocessing" is the process of converting collected proposal data into an analyzable format, including text tokenization, stopword removal, image resizing, and feature extraction.

[0160] "Features" are salient indicators or attributes extracted from data, and are information used for model training and analysis.

[0161] "Similarity" is an index that evaluates how similar a new proposal is to past proposals.

[0162] "Originality" is an index used to evaluate how novel a new proposal is.

[0163] "Feasibility" is an indicator used to evaluate whether a new proposal is technically feasible.

[0164] A "model" is an algorithm that learns from past data and evaluates the similarity, originality, and feasibility of new proposals. Specifically, it refers to a language processing model based on deep learning.

[0165] "Newly input ideas" are new ideas for factory efficiency or design proposed by the user.

[0166] "Feedback" is information that includes an evaluation and specific improvements provided to the user based on the analysis results.

[0167] "Users" are people who use the system, such as factory employees and engineers, who input proposals and receive evaluations.

[0168] The "scores of similarity, originality, and feasibility of new proposals" are indicators calculated by the model for new proposals, and are numerical values ​​that indicate the evaluation results of each.

[0169] "Specific improvements" are advice and suggestions based on the evaluation results of new proposals to make the ideas more feasible and effective.

[0170] A "visual graph" is a diagram that intuitively shows the evaluation results and is provided to the user as part of the feedback.

[0171] "Detailed text" is a detailed explanation of the evaluation results that is provided to the user as part of the feedback.

[0172] This invention relates to a system that analyzes data from past idea contests and predicts the evaluation of newly submitted ideas. This system aims to improve factory efficiency and optimize designs, and allows users to input new ideas via smart devices, and provides evaluation results and suggestions for improvement.

[0173] System configuration

[0174] The system consists of the following elements:

[0175] 1. Server: Data collection, preprocessing, model training, analysis, and feedback generation.

[0176] 2. Terminal: Used by users to input ideas and receive feedback. This can be a smart device such as a smartphone or tablet.

[0177] 3. Model: Based on a generative AI model (e.g., GPT-4V), we evaluate similarity, originality, and feasibility.

[0178] Processing flow

[0179] 1. Data Collection

[0180] The server collects past idea contest data, including text data (titles and descriptions of ideas) and image data (visual descriptions of ideas).

[0181] 2. Data Preprocessing

[0182] The server performs preprocessing on the collected text data, such as tokenizing, removing stop words, and normalizing characters. Image data is resized and features are extracted.

[0183] 3. Model training

[0184] The server extracts features from the preprocessed data and trains a generative AI model that evaluates the similarity, originality, and feasibility of new ideas.

[0185] 4. Enter a new idea

[0186] Users use their smart devices to input new ideas into the system, including text entry and (optionally) image uploads, which are then sent to the server, where preprocessing is performed.

[0187] 5. Idea Analysis

[0188] The server uses the pre-processed new idea data to perform analysis with the trained model, including comparing it with past idea data to calculate a similarity score and generating an originality score and a feasibility score.

[0189] 6. Feedback Generation

[0190] The server generates feedback based on the analysis, including a list of similar past ideas, an analysis of originality, a feasibility assessment, and specific improvements. This feedback includes visual graphs and detailed text.

[0191] 7. Feedback Display

[0192] The device displays the feedback received from the server to the user, allowing them to evaluate their ideas and get specific directions for improvement.

[0193] Specific examples

[0194] For example, a user might propose "Optimizing the transport robots in a factory." The user enters the proposal in text and uploads related images (if available). The data is entered using prompts like this:

[0195] Prompt: "Evaluate new ideas for optimizing transport robots in factories."

[0196] The server preprocesses this input data and analyzes it using a pre-trained model. The analysis results include similarity scores, originality scores, and feasibility scores, and specific improvements are suggested. Feedback includes visual graphs and detailed text, allowing users to intuitively understand the evaluation results and identify areas for improvement.

[0197] In this way, the present invention can effectively support the evaluation and improvement of new ideas in factories and manufacturing industries, contributing to business efficiency and technological advances.

[0198] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0199] Step 1:

[0200] The server collects past idea contest data. This data includes text data (e.g., idea titles and descriptions) and image data (e.g., visual descriptions of ideas). The input of the data collection is data from a database or external API, and the output is the collected raw proposal data.

[0201] Specifically, the server accesses the database and calls an API to retrieve past suggestion data, which returns a dataset containing suggestion titles, detailed descriptions, and associated images.

[0202] Step 2:

[0203] The server preprocesses the collected text and image data. For text data, tokenization, stop word removal, and character normalization are performed. For image data, resizing and feature extraction are performed. The input is the collected raw proposal data, and the output is the preprocessed data.

[0204] Specifically, the server uses a natural language processing library (e.g., NLTK, spaCy) to tokenize the text data and remove stop words, and an image processing library (e.g., OpenCV) to resize images and extract features.

[0205] Step 3:

[0206] The server extracts features from the preprocessed data and trains a generative AI model (e.g., GPT-4V) to evaluate the similarity, originality, and feasibility of new ideas. The input is the preprocessed data, and the output is the trained model.

[0207] Specifically, the server converts the preprocessed text and image data into feature vectors, which are then fed to an AI model to train it. Model training involves splitting the dataset into a training set and a test set and evaluating the model's performance.

[0208] Step 4:

[0209] Users use their smart devices to input new ideas into the system, which involves text input and (optionally) image upload. The input is the user's proposed idea, and the output is the data sent from the device.

[0210] Specifically, a user opens the application on their smart device, enters the title and detailed description of a new idea in text, and uploads related images if necessary. The device then calls an API that sends this data to the server.

[0211] Step 5:

[0212] The server preprocesses the submitted new idea data, which, similar to step 2, includes tokenizing text data, removing stop words, normalizing characters, and resizing and feature extraction of images. The input is the raw proposal data submitted by the user, and the output is the preprocessed new idea data.

[0213] Specifically, the server applies pre-processing algorithms to the new idea data to convert it into a format acceptable to the model.

[0214] Step 6:

[0215] The server uses the preprocessed new idea data to perform analysis with the trained model. This analysis includes calculating a similarity score with past idea data, generating an originality score, and generating a feasibility score. The input is the preprocessed new idea data, and the output is a score of the analysis result.

[0216] Specifically, the server inputs the features of the new idea into the model and calculates similarity scores, originality scores, and feasibility scores. These scores are evaluation results based on past data.

[0217] Step 7:

[0218] The server generates feedback based on the analysis results. This feedback includes a list of similar past ideas, originality analysis results, feasibility assessment, and specific improvement points. The input is the score of the analysis results, and the output is the generated feedback.

[0219] Specifically, the server organizes the evaluation results and creates detailed text and visual graphs containing useful improvements for the user.

[0220] Step 8:

[0221] The terminal displays the feedback received from the server to the user. The input is the generated feedback and the output is the information displayed to the user in visual and detailed text format.

[0222] Specifically, the device receives the feedback data and displays it in an intuitive format within the application, allowing users to evaluate their ideas and make any necessary improvements based on the displayed feedback.

[0223] 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.

[0224] This invention relates to a system that collects and analyzes data from past idea contests to predict how much a new idea submitted by a user will be evaluated. Furthermore, by combining this with an emotion engine that recognizes the user's emotions, the system provides the user with more appropriate feedback.

[0225] System configuration and operation

[0226] Data collection and preprocessing

[0227] The server collects proposal data from a database of past idea contests, including text data (titles and detailed descriptions of ideas) and image data (visual descriptions of ideas).

[0228] The server preprocesses the text data. Specifically, it tokenizes the text, removes stop words, and normalizes characters. Image data is resized to a uniform size and key features (edges, color, shape, etc.) are extracted.

[0229] Training the model

[0230] The server trains the model using the preprocessed data. It uses deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of the proposal. It uses 80% of the training data for training and 20% for validation.

[0231] Emotion engine integration

[0232] The emotion engine is used to recognize emotions from user input data. The server integrates a module that analyzes emotions from text data and a module that analyzes emotions from image and video data.

[0233] Entering and analyzing new ideas

[0234] A user inputs a new idea into the system, entering the title and detailed description of the idea in the text boxes, and uploading image data if necessary.

[0235] The device sends the input data to the server, which then preprocesses the text data of the new idea and analyzes the user's emotions using an emotion engine.

[0236] Analyzing ideas and generating feedback

[0237] The server inputs the preprocessed new idea data into the existing model and calculates similarity scores, originality scores, and feasibility scores, taking into account the user's emotional information analyzed by the emotion engine.

[0238] The server generates feedback based on these analysis results, including a list of similar past ideas, an analysis of originality, and an assessment of feasibility, and provides specific recommendations and suggestions for improvements based on the user's feelings.

[0239] View Feedback

[0240] The device receives feedback from the server and displays it to the user. The feedback is provided as visual graphs and text, and is presented in a format that the user can intuitively understand. In addition, the analysis results from the emotion engine are also displayed, allowing the user to receive appropriate feedback that reflects their emotional state.

[0241] Specific examples

[0242] For example, if a user proposes an idea for an "innovative recycling system," the user enters a detailed description of the idea in text and uploads related images. The device then sends this data to the server, which then performs preprocessing and user sentiment analysis.

[0243] Based on the analysis results, the similarity score is 75%, the originality score is 85 / 100, and the feasibility score is 70 / 100. Furthermore, if the emotion engine detects a positive emotion from the user's input data, the feedback will include specific improvements such as "This idea is very original. To further develop it, please focus on the following points."

[0244] In this way, the present invention is a system that can improve the quality of ideas by predicting how well a user's idea will be evaluated in a contest and providing feedback that takes into account the user's emotional state.

[0245] The processing flow will be explained below.

[0246] Step 1:

[0247] The server collects proposal data from past idea contests from a database, including text data such as idea titles and detailed descriptions, and image data that visually represent the ideas.

[0248] Step 2:

[0249] The server pre-processes the text data, which includes tokenization to split sentences into words and phrases, stopword removal to remove meaningless common words, and character normalization to lowercase all letters and remove special characters.

[0250] Step 3:

[0251] The server preprocesses the image data: resizes the images to a uniform size and extracts key features (edges, color, shape, etc.).

[0252] Step 4:

[0253] The server trains the model using the preprocessed data. It uses deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of ideas. For training, 80% of the data is used to train the model, and the remaining 20% ​​is used for validation.

[0254] Step 5:

[0255] A user inputs a new idea into the system by entering the title and detailed description of the idea in the text boxes, and uploading related image data if necessary.

[0256] Step 6:

[0257] The terminal transmits the data input by the user to the server.

[0258] Step 7:

[0259] The server preprocesses the text data of new ideas, tokenizing, removing stop words, and normalizing characters, similar to the processing in step 2.

[0260] Step 8:

[0261] The server preprocesses the image data of the new idea. As in step 3, it resizes and extracts features.

[0262] Step 9:

[0263] The server analyzes the user's emotions using an emotion engine, which analyzes the user's emotional state from the content of the text data and (optionally) from the uploaded image data.

[0264] Step 10:

[0265] The server inputs the preprocessed new idea data and user sentiment data into the evaluation model and performs analysis, calculating the idea similarity score, originality score, and feasibility score.

[0266] Step 11:

[0267] The server generates feedback based on the analysis results, including a list of similar past ideas, an analysis of originality, and an evaluation of feasibility. It also provides specific improvements and recommendations based on the results of the emotion engine's analysis of the user's emotions.

[0268] Step 12:

[0269] The device receives feedback from the server and displays it to the user. The feedback is presented in a format that is intuitively understandable to the user, such as visual graphs and detailed text. The analysis results from the emotion engine are also displayed, allowing the user to receive appropriate feedback that reflects their own emotional state.

[0270] In this way, the present invention is a system that can improve the quality of ideas by predicting how well a user's idea will be evaluated in a contest and providing feedback that takes into account the user's emotional state.

[0271] Example 2

[0272] 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."

[0273] Systems that predict the evaluation of newly submitted ideas based on evaluation data from past idea contests take time to process and analyze existing proposal data and can lack accuracy. Furthermore, they do not provide feedback that takes into account the user's emotional state, making it difficult to motivate users to improve. Therefore, there is a need for a system that can quickly and accurately predict the evaluation of ideas and provide appropriate feedback that reflects the user's emotional state.

[0274] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0275] In this invention, the server includes a means for collecting past proposal data, a means for preprocessing the proposal data, and a means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility, thereby enabling rapid and accurate analysis of newly proposed ideas.

[0276] The system also includes a means for inputting a newly proposed idea, a means for preprocessing the newly input idea and analyzing emotions using an emotion analysis module, a means for analyzing the idea using the emotion analysis result and a model, a means for generating feedback based on the analysis result, and a means for displaying the feedback to the user, thereby making it possible to provide appropriate feedback that reflects the emotional state of the user.

[0277] "Past proposal data" refers to information about ideas collected through previous idea contests, proposal activities, etc.

[0278] "Preprocessing" refers to a series of processes performed to make data easier to analyze, and specifically includes tokenizing text, removing stop words, resizing images, and extracting features.

[0279] "Features" refer to useful attributes and patterns extracted from data, and are used for algorithmic analysis and classification.

[0280] "Similarity" refers to an evaluation metric that indicates how similar two or more ideas or data are.

[0281] "Originality" refers to the degree to which an idea is novel and different from other ideas or existing ideas.

[0282] "Feasibility" refers to an evaluation metric that indicates whether an idea can be realistically implemented.

[0283] "Model" refers to a computer program using mathematical or machine learning algorithms built on collected data.

[0284] "Sentiment Analysis Module" refers to a system component for automatically analyzing emotions from user-entered data.

[0285] "Feedback" refers to advice and evaluation results provided to the user based on the analysis results.

[0286] "Input Form" refers to an interface for users to input new ideas, including text boxes and image upload functionality.

[0287] "Deep learning" refers to a machine learning technique that uses large amounts of data and multi-layered neural networks to make highly accurate predictions and classifications.

[0288] MODE FOR CARRYING OUT THE INVENTION

[0289] This invention relates to a system that collects and analyzes data from past idea contests and predicts the evaluation of new ideas submitted by users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides more appropriate feedback to the user.

[0290] Data collection and preprocessing

[0291] The server collects proposal data from a database of past idea contests. This data includes text data (titles and detailed descriptions of ideas) and image data (visual descriptions of ideas). It communicates with the database using SQL queries and API requests to retrieve the required data.

[0292] The server preprocesses the text data. Specifically, it uses natural language processing software to tokenize the text, remove stop words, and normalize characters. Furthermore, it uses image processing software to resize the image data to a uniform size and extract key features (edges, color, shape, etc.).

[0293] Training the model

[0294] The server trains a model using the preprocessed data. It uses a deep learning algorithm (e.g., BERT model or ResNet) to build a model that evaluates the similarity, originality, and feasibility of proposals. 80% of the training data is used for training, and the remaining 20% ​​is used for validation.

[0295] Emotion engine integration

[0296] Integrate an emotion engine into the server, including a Natural Language Processing (NLP) module for analyzing emotions from text data and a computer vision module (e.g., OpenCV or DeepFace) for analyzing emotions from image and video data.

[0297] Entering and analyzing new ideas

[0298] The user enters a new idea into the system. They enter the idea title and detailed description in the text boxes, and upload image data if necessary. The device then sends the entered data to the server. The data is sent securely using the HTTPS protocol.

[0299] The server preprocesses the text data of the new ideas and performs user sentiment analysis using an emotion engine. For example, the emotion analysis module extracts emotional information from the user's input.

[0300] Analyzing ideas and generating feedback

[0301] The server inputs the preprocessed new idea data into the existing evaluation model and calculates the idea's similarity score, originality score, and feasibility score. The server also takes into account the user's emotional information analyzed by the emotion engine. This allows the server to generate appropriate feedback that reflects the user's emotions.

[0302] View Feedback

[0303] The device receives feedback from the server and displays it to the user. The feedback is presented as visual graphs and text in a format that is intuitively understandable to the user. The generated feedback also includes specific improvements and recommendations based on similar past ideas, originality evaluation results, feasibility evaluation, and sentiment.

[0304] Specific examples

[0305] For example, if a user proposes an idea for an "innovative recycling system," the user enters a detailed description of the idea in text and uploads related images. The device then sends this data to the server, which then performs data preprocessing and user sentiment analysis. Based on the analysis results, the similarity score is 75%, the originality score is 85 / 100, and the feasibility score is 70 / 100. Furthermore, if the sentiment engine detects positive sentiment from the user's input data, the feedback includes specific suggestions for improvement, such as "This idea is very original. Please focus on the following points." An example of a prompt sentence to input to the generative AI model is, "Please generate a score and feedback for the idea 'innovative recycling system' proposed by the user."

[0306] In this way, the present invention can predict how well a user's idea will perform in a contest and provide feedback that takes into account the user's emotional state, thereby improving the quality of the idea.

[0307] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0308] System program processing flow

[0309] Step 1: Data collection

[0310] The server collects past proposal data by making SQL queries or API requests to the database to retrieve text data (idea titles, detailed descriptions) and image data (visual descriptions of ideas).

[0311] Input: Database query

[0312] Output: A set of text and image data

[0313] Step 2: Preprocessing the text data

[0314] The server preprocesses the collected text data: first, it uses natural language processing software to tokenize the text, then it removes stop words, and finally it normalizes the characters.

[0315] Input: Raw text data

[0316] Output: Preprocessed text data

[0317] Step 3: Preprocessing the image data

[0318] The server preprocesses the image data. It uses image processing software to resize all images to a uniform size. It then extracts key features from the images (edges, color, shape, etc.).

[0319] Input: Raw image data

[0320] Output: Preprocessed image data

[0321] Step 4: Prepare training data for the model

[0322] The server splits the preprocessed text and image data into a training dataset and a validation dataset, allowing the performance of the model to be evaluated.

[0323] Input: Preprocessed text and image data

[0324] Output: training dataset, validation dataset

[0325] Step 5: Train the model

[0326] The server trains a model using a deep learning algorithm (e.g., BERT model or ResNet). Using the training dataset, it builds a model to evaluate the similarity, originality, and feasibility of proposals.

[0327] Input: training dataset

[0328] Output: A trained model

[0329] Step 6: Prepare the Emotion Engine

[0330] The server implements an emotion engine, which includes an NLP module and an image recognition module (e.g., OpenCV or DeepFace), to analyze emotion information from user input data.

[0331] Input: Emotion Engine Software

[0332] Output: Sentiment analysis module

[0333] Step 7: User Ideas

[0334] To enter a new idea, users use the system's input form, enter a title and description in the text boxes, and upload an image if necessary.

[0335] Input: Text and image data of new ideas

[0336] Output: Idea input dataset

[0337] Step 8: Send data from the device to the server

[0338] The device sends the input data of the new idea to the server, which is securely transmitted using the HTTPS protocol.

[0339] Input: Idea input dataset

[0340] Output: Data sent to the server

[0341] Step 9: Preprocessing and sentiment analysis of new ideas

[0342] The server preprocesses the text data of new ideas and analyzes user sentiment using an emotion engine, which includes tokenizing the text, removing stop words, and normalizing characters. It also resizes the image data and extracts features.

[0343] Input: Text and image data of new ideas

[0344] Output: Preprocessed idea data and sentiment analysis results

[0345] Step 10: Analyze your idea

[0346] The server inputs the pre-processed new idea data into the trained model and calculates similarity scores, originality scores, and feasibility scores, while also taking into account the analysis results of the emotion engine.

[0347] Input: Preprocessed idea data and sentiment analysis results

[0348] Output: Idea rating score

[0349] Step 11: Generate feedback

[0350] The server generates feedback based on the analysis results, including a list of similar past ideas, an evaluation of originality and feasibility, and specific improvements and recommendations that take into account user sentiment.

[0351] Input: Idea rating scores and sentiment analysis results

[0352] Output: Feedback content

[0353] Step 12: Submit and view feedback

[0354] The device displays the feedback received from the server to the user, which is presented as visual graphs and text in a way that is intuitive to the user.

[0355] Input: Feedback

[0356] Output: Feedback displayed to the user

[0357] (Application example 2)

[0358] 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."

[0359] Existing systems often have inefficient processes for users to submit new ideas and receive feedback. In particular, the feedback provided may be insufficient because it does not take into account the user's emotional state, the originality of the proposal, or the feasibility of the proposal. Furthermore, when content creators submit new ideas, it is difficult to accurately predict how their ideas will be evaluated and receive feedback that takes their emotions into account.

[0360] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0361] In this invention, the server includes means for collecting past proposal data, means for preprocessing the proposal data, means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility, means for inputting newly proposed ideas, means for preprocessing the newly input ideas and analyzing them using the model, means for generating feedback based on the analysis results, means for displaying the feedback to the user, means for analyzing the user's emotions at the time of input, and means for reflecting the emotion analysis results in the feedback. This makes it possible to provide specific and useful feedback that takes into account the user's emotions, the originality, and feasibility of the idea.

[0362] "Past proposal data" refers to proposal information previously collected and recorded, including text data and image data.

[0363] "Preprocessing" refers to the process of converting raw data into a format that is easier to analyze, specifically tokenizing text, removing stop words, normalizing characters, and resizing and extracting features from images.

[0364] "Features" indicate specific attributes or aspects of data, and are important information that serves as input for model learning.

[0365] "Similarity" is an indicator of how similar a newly proposed idea is to past proposals.

[0366] "Originality" is an indicator of how unique and novel a newly proposed idea is.

[0367] "Feasibility" is an indicator of whether a newly proposed idea can be realized.

[0368] "Training a model" is the process of using historical data to tune an algorithm so that it can make predictions or classifications.

[0369] "Inputting an idea" refers to the act of a user providing information to the system, such as the title of the proposal, a detailed description, and related images and videos.

[0370] "Feedback" refers to advice and evaluations provided based on the analysis results, and is information that allows users to refine and improve their ideas.

[0371] "Analyzing emotions" is the process of identifying emotions from the user's input, facial expressions, etc., and specifying the type and intensity of those emotions.

[0372] In the system that realizes this application example, the program is implemented according to the following steps.

[0373] Data collection and preprocessing

[0374] The server collects past proposal data, including text data and image data. The server then preprocesses the collected data. Specifically, the server tokenizes the text data, removes stop words, and normalizes characters, and resizes the image data to extract key features (edges, color, shape, etc.).

[0375] Training the model

[0376] The server uses the preprocessed data to train a generative AI model, using deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of proposals, using 80% of the training data for training and 20% for validation.

[0377] Emotion engine integration

[0378] The server is integrated with emotion analysis modules, including a module for analyzing emotions from text data and a module for analyzing emotions from image and video data. This emotion engine is used to recognize emotions from user input data.

[0379] Entering and analyzing new ideas

[0380] The user inputs a new idea into the system. They enter the title and detailed description of the idea in the text boxes, and upload image data if necessary. The device then sends the input data to the server. The server then preprocesses the text data of the new idea and analyzes the user's emotions using an emotion engine.

[0381] Analyzing ideas and generating feedback

[0382] The server inputs the preprocessed new idea data into the existing model and calculates similarity, originality, and feasibility scores. The server also takes into account the user's emotional information analyzed by the emotion engine. The server generates feedback based on these analysis results. The feedback includes a list of similar past ideas, originality analysis results, and feasibility assessment. It also provides specific recommendations and suggestions for improvements appropriate to the user's emotions.

[0383] View Feedback

[0384] The device receives feedback from the server and displays it to the user. The feedback is provided as visual graphs and text, and is presented in a format that the user can intuitively understand. In addition, the analysis results from the emotion engine are also displayed, allowing the user to receive appropriate feedback that reflects their emotional state.

[0385] Specific examples

[0386] For example, if a user proposes an idea for an "innovative recycling system," they enter a detailed description of their idea in text and upload related images. The device then sends this data to the server, which then preprocesses the data and analyzes the user's sentiment. Based on the analysis results, the similarity score is 75%, the originality score is 85 / 100, and the feasibility score is 70 / 100. Furthermore, if the sentiment engine detects positive sentiment from the user's input data, the feedback will include specific improvements such as, "This idea is very original. To further develop it, please focus on the following points."

[0387] Prompt Sentence Examples

[0388] title = "Innovative recycling system ideas"

[0389] description = "My new recycling system idea is..."

[0390] image_path = "example.jpg"

[0391] In this way, the system helps content creators improve the quality of their ideas by predicting their ratings and providing emotionally sensitive feedback when they submit new ideas.

[0392] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0393] Step 1: Data collection and preprocessing

[0394] The server collects past proposal data from a database. The collected data includes text data (idea titles, detailed descriptions) and image data (visual descriptions of ideas). The input data is in text and image formats. The server tokenizes the text data, removes stop words, normalizes characters, resizes the image data to a uniform size, and extracts key features (edges, color, shape, etc.). The output is preprocessed text and image data.

[0395] Step 2: Training the model

[0396] The server uses the preprocessed data to train a generative AI model. Specifically, it uses a deep learning algorithm to build a model that evaluates the similarity, originality, and feasibility of proposals. 80% of the training data is used for training, and 20% is used for validation. The input is preprocessed text and image data, and the output is a trained evaluation model.

[0397] Step 3: Integrating the Emotion Engine

[0398] The server is integrated with an emotion analysis module, which can analyze emotions from user-supplied text and image data. The input is the text and image data provided by the user, and the output is the analyzed emotion information.

[0399] Step 4: Enter a new idea

[0400] A user uses a terminal to input a new idea into the system. Specifically, the user enters the title and detailed description of the idea in the text boxes, and uploads image data if necessary. The input is the text and image data entered by the user, and the output is the data sent from the terminal to the server.

[0401] Step 5: Data preprocessing and sentiment analysis

[0402] The server preprocesses the text data of new ideas received from the terminal and analyzes the user's emotions using an emotion engine. The input is the text and image data of the newly proposed idea, and the output is the preprocessed data and the user's emotional information.

[0403] Step 6: Analyze ideas and generate feedback

[0404] The server inputs the preprocessed new idea data into the existing evaluation model and calculates similarity scores, originality scores, and feasibility scores, taking into account the results of sentiment analysis. The input is the new idea data and the results of sentiment analysis, and the output is the idea's evaluation score and feedback based on the sentiment.

[0405] Step 7: View your feedback

[0406] The terminal receives feedback from the server and displays it to the user. The feedback is provided as visual graphs or text, and is displayed in a format that the user can intuitively understand. The input is the feedback data sent from the server, and the output is a display format that the user can view.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] [Second embodiment]

[0411] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0412] 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.

[0413] 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).

[0414] 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.

[0415] 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.

[0416] 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).

[0417] 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. 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.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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."

[0423] The present invention relates to a system that analyzes data from past idea contests and predicts the evaluation of newly submitted ideas. First, a means for collecting and preprocessing past proposal data is provided. Next, a means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility is provided. A means for inputting newly proposed ideas is provided, and the input ideas are preprocessed and analyzed using the model. Next, a means for generating feedback based on the analysis results is provided, and finally, a means for displaying the feedback to the user is provided.

[0424] Program processing overview

[0425] Data collection

[0426] The server collects proposal data from a database of past idea contests, including text data (titles and descriptions of ideas) and image data (visual descriptions of ideas).

[0427] Data Preprocessing

[0428] The server preprocesses the collected text data. Specifically, it tokenizes the text, removes stop words, normalizes characters, etc. For image data, it resizes the data and extracts features.

[0429] Model training

[0430] The server trains the model using the preprocessed data. It uses a deep learning algorithm (e.g., GPT-4V) to generate a model that evaluates the similarity, originality, and feasibility of ideas. 80% of the training data is used for training, and 20% is used for validation.

[0431] Input and preprocessing of new ideas

[0432] Users input new ideas into the system, including text entry and (optionally) image uploads. The device sends this data to the server, which then pre-processes it.

[0433] Idea Analysis

[0434] The server uses the pre-processed new idea data to perform analysis with the trained model, including calculating a similarity score by comparing it with past idea data and generating an originality score and a feasibility score.

[0435] Feedback Generation

[0436] The server generates feedback based on the analysis results, specifically a report containing a list of similar past ideas, an analysis of originality, a feasibility assessment, and specific improvements.

[0437] Feedback Display

[0438] The device receives feedback from the server and displays it to the user, including visual graphs and detailed text, presented in a format that is intuitively understandable to the user.

[0439] Specific examples

[0440] For example, suppose a user proposes an "innovative recycling system." The user enters a detailed description of the idea in text and uploads related images. The device sends this data to the server, which then performs preprocessing.

[0441] The server uses the preprocessed data to evaluate the similarity, originality, and feasibility of new ideas. The evaluation results in a similarity score of 75%, an originality score of 85 / 100, and a feasibility score of 70 / 100. Based on this information, specific improvements (e.g., improving cost efficiency, linking with other recycling technologies, etc.) are suggested.

[0442] Finally, the device visually displays this feedback to the user, allowing them to understand how their ideas are evaluated and providing specific directions for improvement.

[0443] In this way, the present invention is a system that helps participants objectively evaluate and effectively improve their ideas, thereby improving the quality and soundness of idea contests.

[0444] The processing flow will be explained below.

[0445] Step 1:

[0446] The server collects proposal data from past idea contests from a database, including text data (e.g., idea titles, detailed descriptions) and image designs (e.g., visual descriptions of ideas).

[0447] Step 2:

[0448] The server preprocesses the collected text data by tokenizing the text (splitting sentences into words and phrases), removing stop words (common words not needed for analysis), and normalizing characters (converting all to lowercase and removing special characters).

[0449] Step 3:

[0450] The server preprocesses the image data collected by resizing the images to a uniform size and extracting features (edges, color, shape, etc.).

[0451] Step 4:

[0452] The server trains the model using the preprocessed data. It uses deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of the proposals. 80% of the training data is used for training, and 20% is used for validation.

[0453] Step 5:

[0454] A user enters a new idea into the system by entering a title and detailed description of the idea in text boxes, and optionally uploading an associated image.

[0455] Step 6:

[0456] The terminal transmits the data input by the user to the server.

[0457] Step 7:

[0458] The server preprocesses the text data of new ideas. Similar to the preprocessing of collected data, it performs tokenization, stopword removal, and character normalization.

[0459] Step 8:

[0460] The server preprocesses the image data of the new idea. Similar to the preprocessing of collected data, it resizes and extracts features.

[0461] Step 9:

[0462] The server inputs the preprocessed new idea data into the model and performs analysis, calculating the idea similarity score, originality score, and feasibility score.

[0463] Step 10:

[0464] The server generates feedback based on the analysis, including a list of similar ideas from previous ideas, an analysis of originality, and an assessment of feasibility, as well as specific improvements and recommendations.

[0465] Step 11:

[0466] The device receives feedback from the server and displays it to the user in the form of visual graphs and detailed text, in a format that is intuitively understandable to the user.

[0467] Example 1

[0468] 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."

[0469] Conventional idea contests often lack fairness and objectivity because submitted ideas are evaluated subjectively by human judges. Furthermore, systems for efficiently analyzing proposed ideas and suggesting areas for improvement are inadequate, making it difficult to improve the quality of diverse ideas. Furthermore, while rapid and accurate evaluation of the similarity, originality, and feasibility of new ideas is required, achieving this is not easy.

[0470] 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.

[0471] In this invention, the server includes: means for collecting past proposal data; means for preprocessing the proposal data; means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility; means for inputting newly proposed ideas; means for preprocessing the newly input ideas and analyzing them using the model; means for generating feedback based on the analysis results; means for displaying the feedback to a user; data preprocessing means for tokenizing the text data, removing stop words, and normalizing characters; data preprocessing means for resizing the image data and extracting features; and means for dividing the model into a training set and a validation set for training and generating an optimal model. This makes it possible to objectively and efficiently evaluate newly proposed ideas and present specific areas for improvement.

[0472] "Past proposal data" refers to information on proposals submitted to previous idea contests, and includes text data and image data.

[0473] "Means of collection" refers to the function that allows the server to obtain and store past proposal data through a database or API.

[0474] "Preprocessing means" refers to a function that processes the data collected by the server, such as tokenizing, removing stop words, normalizing characters, resizing, and extracting features, to optimize it for subsequent analysis and training.

[0475] "Means for extracting features" is a function for deriving the information (features) required for the model from preprocessed data.

[0476] "Means for training a model" refers to the function by which the server uses deep learning algorithms to build and optimize a model based on collected and preprocessed data.

[0477] A "newly proposed idea" is an idea that a user newly submits to the system, and includes text data and image data.

[0478] "Input means" refers to an interface or function that allows users to submit new ideas to the system.

[0479] "Means for analysis" refers to the function by which the server preprocesses newly proposed ideas and evaluates them for similarity, originality, feasibility, etc. using a trained model.

[0480] The "means for generating feedback" is a function in which the server creates a report containing specific evaluations and areas for improvement for the user based on the analysis results.

[0481] The "means for displaying feedback to the user" is a function by which the terminal presents the generated feedback to the user in a format that can be visually and intuitively understood.

[0482] "Tokenization" is the process of dividing text data into smaller units (tokens) such as words or phrases.

[0483] "Stop word removal" is the process of removing words that occur frequently but are semantically insignificant (e.g., the, and).

[0484] "Character normalization" is the process of transforming characters from different writing forms to make them uniform.

[0485] "Resizing" is the process of changing and unifying the size of an image.

[0486] "Feature extraction" is the process of extracting important information (features) from image or text data for the model to analyze.

[0487] A "training set" is the portion of a dataset used to train a model, accounting for approximately 80% of the total data.

[0488] A "validation set" is a portion of the dataset used to evaluate the performance and accuracy of a model, and accounts for approximately 20% of the total data.

[0489] The "optimal model" is the model that has been adjusted to show the highest accuracy and performance as a result of evaluation using training data and validation data.

[0490] The present invention relates to a system for analyzing data from past idea contests and predicting the evaluation of newly submitted ideas. The embodiments for carrying out the present invention will be described in detail below.

[0491] The hardware configuration of this system includes a server and a terminal. The server is mainly responsible for data collection, preprocessing, model training and evaluation, and feedback generation. The terminal provides an interface for users to input new ideas and receive feedback.

[0492] 1. Data Collection

[0493] The server collects proposal data from a database of past idea contests via API. The proposal data includes text data (titles and descriptions of ideas) and image data (visual descriptions of ideas). The collected data is stored in the server's local data storage.

[0494] 2. Data Preprocessing

[0495] The server preprocesses the collected text data using a natural language processing tool (e.g., NLTK). Specifically, the process includes the following steps:

[0496] Tokenization: Breaking text into words and phrases.

[0497] Stop word removal: removes frequently occurring but semantically insignificant words.

[0498] Character normalization: unifying different writing forms.

[0499] Additionally, the image data is pre-processed using a computer vision library (e.g., OpenCV):

[0500] Resize: Resize images to a uniform size.

[0501] Feature extraction: Features are extracted from images using SIFT (Scale-Invariant Feature Transform).

[0502] 3. Model training

[0503] Based on the preprocessed data, the server trains a model using a deep learning algorithm (e.g., GPT-4V). The dataset is divided into a training set (80%) and a validation set (20%). The server uses these datasets to build and optimize a model to evaluate the similarity, originality, and feasibility of ideas.

[0504] 4. Enter a new idea

[0505] The user inputs new ideas in text format and uploads related images through the device, which then sends this data to the server using an HTTP request.

[0506] 5. Idea Analysis

[0507] The server pre-processes new ideas and feeds them into a trained model for analysis, which involves comparing them with past idea data to calculate a similarity score and generating originality and feasibility scores.

[0508] 6. Feedback Generation and Display

[0509] The server generates feedback based on the analysis results and creates a report containing specific improvements and evaluation results. The device displays this report to the user in a visually and intuitive format.

[0510] Specific examples

[0511] For example, suppose a user proposes an "innovative recycling system." The user enters a detailed description of the idea in text and uploads related images. The device sends this data to the server, which performs preprocessing. An example of a specific prompt is as follows:

[0512] "Please rate the following idea: It is titled 'Innovative Recycling System' and proposes an environmentally friendly recycling process. Please provide details below. {Detailed Description} Also, upload relevant images. Please provide your rating results with a similarity score, originality score, feasibility score, and specific suggestions for improvement."

[0513] The server tokenizes the text data using NLTK, removes stop words, and performs Unicode normalization. It also resizes images using OpenCV and extracts features using SIFT. It then uses a pre-trained GPT-4V model to evaluate the similarity, originality, and feasibility scores of new ideas. For example, a similarity score of 75%, an originality score of 85 / 100, and a feasibility score of 70 / 100 are calculated.

[0514] Finally, the terminal visually displays this feedback to the user, allowing the user to understand the evaluation of their idea and specific areas for improvement. Through this process, the present invention enables the improvement of the quality and soundness of ideas.

[0515] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0516] Step 1:

[0517] The server connects to a database of past idea contests. The input includes database access information and collection criteria. Specifically, the server calls an API and retrieves proposal data (text data and image data). The retrieved proposal data is saved in the server's local storage as an output.

[0518] Step 2:

[0519] The server preprocesses the collected text data. The input contains the acquired text data. Specifically, the server uses a natural language processing tool (e.g., NLTK) to tokenize the data, remove stop words, and normalize characters. The output is the preprocessed text data.

[0520] Step 3:

[0521] The server preprocesses the collected image data. The input contains the acquired image data. Specifically, the server resizes the image using a computer vision library (e.g., OpenCV) and extracts features using SIFT (Scale-Invariant Feature Transform). The output is the preprocessed image data.

[0522] Step 4:

[0523] The server uses the preprocessed data to train a model. The inputs include preprocessed text and image data and a deep learning algorithm (e.g., GPT-4V). Specifically, the server splits the data into a training set (80%) and a validation set (20%) and trains the deep learning model. The output is an optimized model.

[0524] Step 5:

[0525] A user uses a terminal to input a new idea in text format. The input includes a detailed description of the new idea and related images. Specific operations involve the user entering text and uploading images through the system interface. The output is the input data stored in the terminal.

[0526] Step 6:

[0527] The device sends input data for a new idea to the server. The input includes a detailed description and image of the idea stored on the device. In concrete terms, the device sends the data to the server using an HTTP request. The output is the data arriving at the server.

[0528] Step 7:

[0529] The server preprocesses the text data of new ideas. The input includes the submitted text data. Specific operations include tokenization, removal of stop words, and character normalization. The output is the preprocessed text data.

[0530] Step 8:

[0531] The server preprocesses the image data of the new idea. The input includes the transmitted image data. Specifically, the server resizes the image and extracts features. The output is the preprocessed image data.

[0532] Step 9:

[0533] The server analyzes the new idea using the trained model. The input includes preprocessed text data and image data of the new idea and the trained model. Specifically, the server inputs the data into the model and calculates a similarity score, originality score, and feasibility score. The output is the analysis result.

[0534] Step 10:

[0535] The server generates feedback based on the analysis results. The analysis results are included as input. In concrete terms, the server creates a feedback report, including improvements and evaluation results. The feedback report is obtained as output.

[0536] Step 11:

[0537] The terminal displays the feedback received from the server to the user. The input includes a feedback report. As a specific operation, the terminal visually displays the feedback through a user interface and presents it to the user. As an output, the user can confirm the feedback.

[0538] (Application example 1)

[0539] 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."

[0540] In recent years, factories and manufacturing industries have been required to improve efficiency and optimize designs, but evaluating new ideas and proposals requires a great deal of time and effort. It is also difficult to objectively evaluate ideas' similarity, originality, and feasibility, leaving employees with a lack of means to identify effective improvements. This makes it difficult to adopt and realize innovative ideas.

[0541] 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.

[0542] In this invention, the server includes means for collecting past proposal data, means for preprocessing the proposal data, means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility, means for inputting newly proposed ideas, means for preprocessing the newly input ideas and analyzing them using the model, means for generating feedback based on the analysis results, means for displaying the feedback to a user, and means for presenting specific improvements based on scores of similarity, originality, and feasibility of the new proposal. This allows a user to input a new idea via a smart device and quickly receive its evaluation results and improvements.

[0543] "Proposal data" is information about past proposals, and includes text data and image data.

[0544] "Preprocessing" is the process of converting collected proposal data into an analyzable format, including text tokenization, stopword removal, image resizing, and feature extraction.

[0545] "Features" are salient indicators or attributes extracted from data, and are information used for model training and analysis.

[0546] "Similarity" is an index that evaluates how similar a new proposal is to past proposals.

[0547] "Originality" is an index used to evaluate how novel a new proposal is.

[0548] "Feasibility" is an indicator used to evaluate whether a new proposal is technically feasible.

[0549] A "model" is an algorithm that learns from past data and evaluates the similarity, originality, and feasibility of new proposals. Specifically, it refers to a language processing model based on deep learning.

[0550] "Newly input ideas" are new ideas for factory efficiency or design proposed by the user.

[0551] "Feedback" is information that includes an evaluation and specific improvements provided to the user based on the analysis results.

[0552] "Users" are people who use the system, such as factory employees and engineers, who input proposals and receive evaluations.

[0553] The "scores of similarity, originality, and feasibility of new proposals" are indicators calculated by the model for new proposals, and are numerical values ​​that indicate the evaluation results of each.

[0554] "Specific improvements" are advice and suggestions based on the evaluation results of new proposals to make the ideas more feasible and effective.

[0555] A "visual graph" is a diagram that intuitively shows the evaluation results and is provided to the user as part of the feedback.

[0556] "Detailed text" is a detailed explanation of the evaluation results that is provided to the user as part of the feedback.

[0557] This invention relates to a system that analyzes data from past idea contests and predicts the evaluation of newly submitted ideas. This system aims to improve factory efficiency and optimize designs, and allows users to input new ideas via smart devices, and provides evaluation results and suggestions for improvement.

[0558] System configuration

[0559] The system consists of the following elements:

[0560] 1. Server: Data collection, preprocessing, model training, analysis, and feedback generation.

[0561] 2. Terminal: Used by users to input ideas and receive feedback. This can be a smart device such as a smartphone or tablet.

[0562] 3. Model: Based on a generative AI model (e.g., GPT-4V), we evaluate similarity, originality, and feasibility.

[0563] Processing flow

[0564] 1. Data Collection

[0565] The server collects past idea contest data, including text data (titles and descriptions of ideas) and image data (visual descriptions of ideas).

[0566] 2. Data Preprocessing

[0567] The server performs preprocessing on the collected text data, such as tokenizing, removing stop words, and normalizing characters. Image data is resized and features are extracted.

[0568] 3. Model training

[0569] The server extracts features from the preprocessed data and trains a generative AI model that evaluates the similarity, originality, and feasibility of new ideas.

[0570] 4. Enter a new idea

[0571] Users use their smart devices to input new ideas into the system, including text entry and (optionally) image uploads, which are then sent to the server, where preprocessing is performed.

[0572] 5. Idea Analysis

[0573] The server uses the pre-processed new idea data to perform analysis with the trained model, including calculating a similarity score by comparing it with past idea data, and generating an originality score and a feasibility score.

[0574] 6. Feedback Generation

[0575] The server generates feedback based on the analysis, including a list of similar past ideas, an analysis of originality, a feasibility assessment, and specific improvements. This feedback includes visual graphs and detailed text.

[0576] 7. Feedback Display

[0577] The device displays the feedback received from the server to the user, allowing the user to evaluate their idea and obtain specific directions for improvement.

[0578] Specific examples

[0579] For example, a user might propose "Optimizing the transport robots in a factory." The user enters the proposal in text and uploads related images (if available). The data is entered using prompts like this:

[0580] Prompt: "Evaluate new ideas for optimizing transport robots in factories."

[0581] The server preprocesses this input data and analyzes it using a pre-trained model. The analysis results include similarity scores, originality scores, and feasibility scores, and specific improvements are suggested. Feedback includes visual graphs and detailed text, allowing users to intuitively understand the evaluation results and identify areas for improvement.

[0582] In this way, the present invention can effectively support the evaluation and improvement of new ideas in factories and manufacturing industries, contributing to business efficiency and technological advances.

[0583] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0584] Step 1:

[0585] The server collects past idea contest data. This data includes text data (e.g., idea titles and descriptions) and image data (e.g., visual descriptions of ideas). The input of the data collection is data from a database or external API, and the output is the collected raw proposal data.

[0586] Specifically, the server accesses the database and calls an API to retrieve past suggestion data, which returns a dataset containing suggestion titles, detailed descriptions, and associated images.

[0587] Step 2:

[0588] The server preprocesses the collected text and image data. For text data, tokenization, stop word removal, and character normalization are performed. For image data, resizing and feature extraction are performed. The input is the collected raw proposal data, and the output is the preprocessed data.

[0589] Specifically, the server uses a natural language processing library (e.g., NLTK, spaCy) to tokenize the text data and remove stop words, and an image processing library (e.g., OpenCV) to resize images and extract features.

[0590] Step 3:

[0591] The server extracts features from the preprocessed data and trains a generative AI model (e.g., GPT-4V) to evaluate the similarity, originality, and feasibility of new ideas. The input is the preprocessed data, and the output is the trained model.

[0592] Specifically, the server converts the preprocessed text and image data into feature vectors, which are then fed to an AI model to train it. Model training involves splitting the dataset into a training set and a test set and evaluating the model's performance.

[0593] Step 4:

[0594] Users use their smart devices to input new ideas into the system, which involves text input and (optionally) image upload. The input is the user's proposed idea, and the output is the data sent from the device.

[0595] Specifically, a user opens the application on their smart device, enters the title and detailed description of a new idea in text, and uploads related images if necessary. The device then calls an API that sends this data to the server.

[0596] Step 5:

[0597] The server preprocesses the submitted new idea data, which, similar to step 2, includes tokenizing text data, removing stop words, normalizing characters, and resizing and feature extraction of images. The input is the raw proposal data submitted by the user, and the output is the preprocessed new idea data.

[0598] Specifically, the server applies pre-processing algorithms to the new idea data to convert it into a format acceptable to the model.

[0599] Step 6:

[0600] The server uses the preprocessed new idea data to perform analysis with the trained model. This analysis includes calculating a similarity score with past idea data, generating an originality score, and generating a feasibility score. The input is the preprocessed new idea data, and the output is a score of the analysis result.

[0601] Specifically, the server inputs the features of the new idea into the model and calculates similarity scores, originality scores, and feasibility scores. These scores are evaluation results based on past data.

[0602] Step 7:

[0603] The server generates feedback based on the analysis results. This feedback includes a list of similar past ideas, originality analysis results, feasibility assessment, and specific improvement points. The input is the score of the analysis results, and the output is the generated feedback.

[0604] Specifically, the server organizes the evaluation results and creates detailed text and visual graphs containing useful improvements for the user.

[0605] Step 8:

[0606] The terminal displays the feedback received from the server to the user. The input is the generated feedback and the output is the information displayed to the user in visual and detailed text format.

[0607] Specifically, the device receives the feedback data and displays it in an intuitive format within the application, allowing users to evaluate their ideas and make any necessary improvements based on the displayed feedback.

[0608] 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.

[0609] This invention relates to a system that collects and analyzes data from past idea contests to predict how much a new idea submitted by a user will be evaluated. Furthermore, by combining this with an emotion engine that recognizes the user's emotions, the system provides the user with more appropriate feedback.

[0610] System configuration and operation

[0611] Data collection and preprocessing

[0612] The server collects proposal data from a database of past idea contests, including text data (titles and detailed descriptions of ideas) and image data (visual descriptions of ideas).

[0613] The server preprocesses the text data. Specifically, it tokenizes the text, removes stop words, and normalizes characters. Image data is resized to a uniform size and key features (edges, color, shape, etc.) are extracted.

[0614] Training the model

[0615] The server trains the model using the preprocessed data. It uses deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of the proposal. It uses 80% of the training data for training and 20% for validation.

[0616] Emotion engine integration

[0617] The emotion engine is used to recognize emotions from user input data. The server integrates a module that analyzes emotions from text data and a module that analyzes emotions from image and video data.

[0618] Entering and analyzing new ideas

[0619] A user inputs a new idea into the system, entering the title and detailed description of the idea in the text boxes, and uploading image data if necessary.

[0620] The device sends the input data to the server, which then preprocesses the text data of the new idea and analyzes the user's emotions using an emotion engine.

[0621] Analyzing ideas and generating feedback

[0622] The server inputs the preprocessed new idea data into the existing model and calculates similarity scores, originality scores, and feasibility scores, taking into account the user's emotional information analyzed by the emotion engine.

[0623] The server generates feedback based on these analysis results, including a list of similar past ideas, an analysis of originality, and an assessment of feasibility, and provides specific recommendations and suggestions for improvements based on the user's feelings.

[0624] View Feedback

[0625] The device receives feedback from the server and displays it to the user. The feedback is provided as visual graphs and text, and is presented in a format that the user can intuitively understand. In addition, the analysis results from the emotion engine are also displayed, allowing the user to receive appropriate feedback that reflects their emotional state.

[0626] Specific examples

[0627] For example, if a user proposes an idea for an "innovative recycling system," the user enters a detailed description of the idea in text and uploads related images. The device then sends this data to the server, which then performs preprocessing and user sentiment analysis.

[0628] Based on the analysis results, the similarity score is 75%, the originality score is 85 / 100, and the feasibility score is 70 / 100. Furthermore, if the emotion engine detects a positive emotion from the user's input data, the feedback will include specific improvements such as "This idea is very original. To further develop it, please focus on the following points."

[0629] In this way, the present invention is a system that can improve the quality of ideas by predicting how well a user's idea will be evaluated in a contest and providing feedback that takes into account the user's emotional state.

[0630] The processing flow will be explained below.

[0631] Step 1:

[0632] The server collects proposal data from past idea contests from a database, including text data such as idea titles and detailed descriptions, and image data that visually represent the ideas.

[0633] Step 2:

[0634] The server pre-processes the text data, which includes tokenization to split sentences into words and phrases, stopword removal to remove meaningless common words, and character normalization to lowercase all letters and remove special characters.

[0635] Step 3:

[0636] The server preprocesses the image data: resizes the images to a uniform size and extracts key features (edges, color, shape, etc.).

[0637] Step 4:

[0638] The server trains the model using the preprocessed data. It uses deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of ideas. For training, 80% of the data is used to train the model, and the remaining 20% ​​is used for validation.

[0639] Step 5:

[0640] A user inputs a new idea into the system by entering the title and detailed description of the idea in the text boxes, and uploading related image data if necessary.

[0641] Step 6:

[0642] The terminal transmits the data input by the user to the server.

[0643] Step 7:

[0644] The server preprocesses the text data of new ideas, tokenizing, removing stop words, and normalizing characters, similar to the processing in step 2.

[0645] Step 8:

[0646] The server preprocesses the image data of the new idea. As in step 3, it resizes and extracts features.

[0647] Step 9:

[0648] The server analyzes the user's emotions using an emotion engine, which analyzes the user's emotional state from the content of the text data and (optionally) from the uploaded image data.

[0649] Step 10:

[0650] The server inputs the preprocessed new idea data and user sentiment data into the evaluation model and performs analysis, calculating the idea similarity score, originality score, and feasibility score.

[0651] Step 11:

[0652] The server generates feedback based on the analysis results, including a list of similar past ideas, an analysis of originality, and an evaluation of feasibility. It also provides specific improvements and recommendations based on the results of the emotion engine's analysis of the user's emotions.

[0653] Step 12:

[0654] The device receives feedback from the server and displays it to the user. The feedback is presented in a format that is intuitively understandable to the user, such as visual graphs and detailed text. The analysis results from the emotion engine are also displayed, allowing the user to receive appropriate feedback that reflects their own emotional state.

[0655] In this way, the present invention is a system that can improve the quality of ideas by predicting how well a user's idea will be evaluated in a contest and providing feedback that takes into account the user's emotional state.

[0656] Example 2

[0657] 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."

[0658] Systems that predict the evaluation of newly submitted ideas based on evaluation data from past idea contests take time to process and analyze existing proposal data and can lack accuracy. Furthermore, they do not provide feedback that takes into account the user's emotional state, making it difficult to motivate users to improve. Therefore, there is a need for a system that can quickly and accurately predict the evaluation of ideas and provide appropriate feedback that reflects the user's emotional state.

[0659] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0660] In this invention, the server includes a means for collecting past proposal data, a means for preprocessing the proposal data, and a means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility, thereby enabling rapid and accurate analysis of newly proposed ideas.

[0661] The system also includes a means for inputting a newly proposed idea, a means for preprocessing the newly input idea and analyzing emotions using an emotion analysis module, a means for analyzing the idea using the emotion analysis result and a model, a means for generating feedback based on the analysis result, and a means for displaying the feedback to the user, thereby making it possible to provide appropriate feedback that reflects the emotional state of the user.

[0662] "Past proposal data" refers to information about ideas collected through previous idea contests, proposal activities, etc.

[0663] "Preprocessing" refers to a series of processes performed to make data easier to analyze, and specifically includes tokenizing text, removing stop words, resizing images, and extracting features.

[0664] "Features" refer to useful attributes and patterns extracted from data, and are used for algorithmic analysis and classification.

[0665] "Similarity" refers to an evaluation metric that indicates how similar two or more ideas or data are.

[0666] "Originality" refers to the degree to which an idea is novel and different from other ideas or existing ideas.

[0667] "Feasibility" refers to an evaluation metric that indicates whether an idea can be realistically implemented.

[0668] "Model" refers to a computer program using mathematical or machine learning algorithms built on collected data.

[0669] "Sentiment Analysis Module" refers to a system component for automatically analyzing emotions from user-entered data.

[0670] "Feedback" refers to advice and evaluation results provided to the user based on the analysis results.

[0671] "Input Form" refers to an interface for users to input new ideas, including text boxes and image upload functionality.

[0672] "Deep learning" refers to a machine learning technique that uses large amounts of data and multi-layered neural networks to make highly accurate predictions and classifications.

[0673] MODE FOR CARRYING OUT THE INVENTION

[0674] This invention relates to a system that collects and analyzes data from past idea contests and predicts the evaluation of new ideas submitted by users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides more appropriate feedback to the user.

[0675] Data collection and preprocessing

[0676] The server collects proposal data from a database of past idea contests. This data includes text data (titles and detailed descriptions of ideas) and image data (visual descriptions of ideas). It communicates with the database using SQL queries and API requests to retrieve the required data.

[0677] The server preprocesses the text data. Specifically, it uses natural language processing software to tokenize the text, remove stop words, and normalize characters. Furthermore, it uses image processing software to resize the image data to a uniform size and extract key features (edges, color, shape, etc.).

[0678] Training the model

[0679] The server trains a model using the preprocessed data. It uses a deep learning algorithm (e.g., BERT model or ResNet) to build a model that evaluates the similarity, originality, and feasibility of proposals. 80% of the training data is used for training, and the remaining 20% ​​is used for validation.

[0680] Emotion engine integration

[0681] Integrate an emotion engine into the server, including a Natural Language Processing (NLP) module for analyzing emotions from text data and a computer vision module (e.g., OpenCV or DeepFace) for analyzing emotions from image and video data.

[0682] Entering and analyzing new ideas

[0683] The user enters a new idea into the system. They enter the idea title and detailed description in the text boxes, and upload image data if necessary. The device then sends the entered data to the server. The data is sent securely using the HTTPS protocol.

[0684] The server preprocesses the text data of the new ideas and performs user sentiment analysis using an emotion engine. For example, the emotion analysis module extracts emotional information from the user's input.

[0685] Analyzing ideas and generating feedback

[0686] The server inputs the preprocessed new idea data into the existing evaluation model and calculates the idea's similarity score, originality score, and feasibility score. The server also takes into account the user's emotional information analyzed by the emotion engine. This allows the server to generate appropriate feedback that reflects the user's emotions.

[0687] View Feedback

[0688] The device receives feedback from the server and displays it to the user. The feedback is presented as visual graphs and text in a format that is intuitively understandable to the user. The generated feedback also includes specific improvements and recommendations based on similar past ideas, originality evaluation results, feasibility evaluation, and sentiment.

[0689] Specific examples

[0690] For example, if a user proposes an idea for an "innovative recycling system," the user enters a detailed description of the idea in text and uploads related images. The device then sends this data to the server, which then performs data preprocessing and user sentiment analysis. Based on the analysis results, the similarity score is 75%, the originality score is 85 / 100, and the feasibility score is 70 / 100. Furthermore, if the sentiment engine detects positive sentiment from the user's input data, the feedback includes specific suggestions for improvement, such as "This idea is very original. Please focus on the following points." An example of a prompt sentence to input to the generative AI model is, "Please generate a score and feedback for the idea 'innovative recycling system' proposed by the user."

[0691] In this way, the present invention can predict how well a user's idea will perform in a contest and provide feedback that takes into account the user's emotional state, thereby improving the quality of the idea.

[0692] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0693] System program processing flow

[0694] Step 1: Data collection

[0695] The server collects past proposal data by making SQL queries or API requests to the database to retrieve text data (idea titles, detailed descriptions) and image data (visual descriptions of ideas).

[0696] Input: Database query

[0697] Output: A set of text and image data

[0698] Step 2: Preprocessing the text data

[0699] The server preprocesses the collected text data: first, it uses natural language processing software to tokenize the text, then it removes stop words, and finally it normalizes the characters.

[0700] Input: Raw text data

[0701] Output: Preprocessed text data

[0702] Step 3: Preprocessing the image data

[0703] The server preprocesses the image data. It uses image processing software to resize all images to a uniform size. It then extracts key features from the images (edges, color, shape, etc.).

[0704] Input: Raw image data

[0705] Output: Preprocessed image data

[0706] Step 4: Prepare training data for the model

[0707] The server splits the preprocessed text and image data into a training dataset and a validation dataset, allowing the performance of the model to be evaluated.

[0708] Input: Preprocessed text and image data

[0709] Output: training dataset, validation dataset

[0710] Step 5: Train the model

[0711] The server trains a model using a deep learning algorithm (e.g., BERT model or ResNet). Using the training dataset, it builds a model to evaluate the similarity, originality, and feasibility of proposals.

[0712] Input: training dataset

[0713] Output: A trained model

[0714] Step 6: Prepare the Emotion Engine

[0715] The server implements an emotion engine, which includes an NLP module and an image recognition module (e.g., OpenCV or DeepFace), to analyze emotion information from user input data.

[0716] Input: Emotion Engine Software

[0717] Output: Sentiment analysis module

[0718] Step 7: User Ideas

[0719] To enter a new idea, users use the system's input form, enter a title and description in the text boxes, and upload an image if necessary.

[0720] Input: Text and image data of new ideas

[0721] Output: Idea input dataset

[0722] Step 8: Send data from the device to the server

[0723] The device sends the input data of the new idea to the server, which is securely transmitted using the HTTPS protocol.

[0724] Input: Idea input dataset

[0725] Output: Data sent to the server

[0726] Step 9: Preprocessing and sentiment analysis of new ideas

[0727] The server preprocesses the text data of new ideas and analyzes user sentiment using an emotion engine, which includes tokenizing the text, removing stop words, and normalizing characters. It also resizes the image data and extracts features.

[0728] Input: Text and image data of new ideas

[0729] Output: Preprocessed idea data and sentiment analysis results

[0730] Step 10: Analyze your idea

[0731] The server inputs the pre-processed new idea data into the trained model and calculates similarity scores, originality scores, and feasibility scores, while also taking into account the analysis results of the emotion engine.

[0732] Input: Preprocessed idea data and sentiment analysis results

[0733] Output: Idea rating score

[0734] Step 11: Generate feedback

[0735] The server generates feedback based on the analysis results, including a list of similar past ideas, an evaluation of originality and feasibility, and specific improvements and recommendations that take into account user sentiment.

[0736] Input: Idea rating scores and sentiment analysis results

[0737] Output: Feedback content

[0738] Step 12: Submit and view feedback

[0739] The device displays the feedback received from the server to the user, which is presented as visual graphs and text in a way that is intuitive to the user.

[0740] Input: Feedback

[0741] Output: Feedback displayed to the user

[0742] (Application example 2)

[0743] 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."

[0744] Existing systems often have inefficient processes for users to submit new ideas and receive feedback. In particular, the feedback provided may be insufficient because it does not take into account the user's emotional state, the originality of the proposal, or the feasibility of the proposal. Furthermore, when content creators submit new ideas, it is difficult to accurately predict how their ideas will be evaluated and receive feedback that takes their emotions into account.

[0745] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0746] In this invention, the server includes means for collecting past proposal data, means for preprocessing the proposal data, means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility, means for inputting newly proposed ideas, means for preprocessing the newly input ideas and analyzing them using the model, means for generating feedback based on the analysis results, means for displaying the feedback to the user, means for analyzing the user's emotions at the time of input, and means for reflecting the emotion analysis results in the feedback. This makes it possible to provide specific and useful feedback that takes into account the user's emotions, the originality, and feasibility of the idea.

[0747] "Past proposal data" refers to proposal information previously collected and recorded, including text data and image data.

[0748] "Preprocessing" refers to the process of converting raw data into a format that is easier to analyze, specifically tokenizing text, removing stop words, normalizing characters, and resizing and extracting features from images.

[0749] "Features" indicate specific attributes or aspects of data, and are important information that serves as input for model learning.

[0750] "Similarity" is an indicator of how similar a newly proposed idea is to past proposals.

[0751] "Originality" is an indicator of how unique and novel a newly proposed idea is.

[0752] "Feasibility" is an indicator of whether a newly proposed idea can be realized.

[0753] "Training a model" is the process of using historical data to tune an algorithm so that it can make predictions or classifications.

[0754] "Inputting an idea" refers to the act of a user providing information to the system, such as the title of the proposal, a detailed description, and related images and videos.

[0755] "Feedback" refers to advice and evaluations provided based on the analysis results, and is information that allows users to refine and improve their ideas.

[0756] "Analyzing emotions" is the process of identifying emotions from the user's input, facial expressions, etc., and specifying the type and intensity of those emotions.

[0757] In the system that realizes this application example, the program is implemented according to the following steps.

[0758] Data collection and preprocessing

[0759] The server collects past proposal data, including text data and image data. The server then preprocesses the collected data. Specifically, the server tokenizes the text data, removes stop words, and normalizes characters, and resizes the image data to extract key features (edges, color, shape, etc.).

[0760] Training the model

[0761] The server uses the preprocessed data to train a generative AI model, using deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of proposals, using 80% of the training data for training and 20% for validation.

[0762] Emotion engine integration

[0763] The server is integrated with emotion analysis modules, including a module for analyzing emotions from text data and a module for analyzing emotions from image and video data. This emotion engine is used to recognize emotions from user input data.

[0764] Entering and analyzing new ideas

[0765] The user inputs a new idea into the system. They enter the title and detailed description of the idea in the text boxes, and upload image data if necessary. The device then sends the input data to the server. The server then preprocesses the text data of the new idea and analyzes the user's emotions using an emotion engine.

[0766] Analyzing ideas and generating feedback

[0767] The server inputs the preprocessed new idea data into the existing model and calculates similarity, originality, and feasibility scores. The server also takes into account the user's emotional information analyzed by the emotion engine. The server generates feedback based on these analysis results. The feedback includes a list of similar past ideas, originality analysis results, and feasibility assessment. It also provides specific recommendations and suggestions for improvements appropriate to the user's emotions.

[0768] View Feedback

[0769] The device receives feedback from the server and displays it to the user. The feedback is provided as visual graphs and text, and is presented in a format that the user can intuitively understand. In addition, the analysis results from the emotion engine are also displayed, allowing the user to receive appropriate feedback that reflects their emotional state.

[0770] Specific examples

[0771] For example, if a user proposes an idea for an "innovative recycling system," they enter a detailed description of their idea in text and upload related images. The device then sends this data to the server, which then preprocesses the data and analyzes the user's sentiment. Based on the analysis results, the similarity score is 75%, the originality score is 85 / 100, and the feasibility score is 70 / 100. Furthermore, if the sentiment engine detects positive sentiment from the user's input data, the feedback will include specific improvements such as, "This idea is very original. To further develop it, please focus on the following points."

[0772] Prompt Sentence Examples

[0773] title = "Innovative recycling system ideas"

[0774] description = "My new recycling system idea is..."

[0775] image_path = "example.jpg"

[0776] In this way, the system helps content creators improve the quality of their ideas by predicting their ratings and providing emotionally sensitive feedback when they submit new ideas.

[0777] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0778] Step 1: Data collection and preprocessing

[0779] The server collects past proposal data from a database. The collected data includes text data (idea titles, detailed descriptions) and image data (visual descriptions of ideas). The input data is in text and image formats. The server tokenizes the text data, removes stop words, normalizes characters, resizes the image data to a uniform size, and extracts key features (edges, color, shape, etc.). The output is preprocessed text and image data.

[0780] Step 2: Training the model

[0781] The server uses the preprocessed data to train a generative AI model. Specifically, it uses a deep learning algorithm to build a model that evaluates the similarity, originality, and feasibility of proposals. 80% of the training data is used for training, and 20% is used for validation. The input is preprocessed text and image data, and the output is a trained evaluation model.

[0782] Step 3: Integrating the Emotion Engine

[0783] The server is integrated with an emotion analysis module, which can analyze emotions from user-supplied text and image data. The input is the text and image data provided by the user, and the output is the analyzed emotion information.

[0784] Step 4: Enter a new idea

[0785] A user uses a terminal to input a new idea into the system. Specifically, the user enters the title and detailed description of the idea in the text boxes, and uploads image data if necessary. The input is the text and image data entered by the user, and the output is the data sent from the terminal to the server.

[0786] Step 5: Data preprocessing and sentiment analysis

[0787] The server preprocesses the text data of new ideas received from the terminal and analyzes the user's emotions using an emotion engine. The input is the text and image data of the newly proposed idea, and the output is the preprocessed data and the user's emotional information.

[0788] Step 6: Analyze ideas and generate feedback

[0789] The server inputs the preprocessed new idea data into the existing evaluation model and calculates similarity scores, originality scores, and feasibility scores, taking into account the results of sentiment analysis. The input is the new idea data and the results of sentiment analysis, and the output is the idea's evaluation score and feedback based on the sentiment.

[0790] Step 7: View your feedback

[0791] The terminal receives feedback from the server and displays it to the user. The feedback is provided as visual graphs or text, and is displayed in a format that the user can intuitively understand. The input is the feedback data sent from the server, and the output is a display format that the user can view.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] [Third embodiment]

[0796] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0797] 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.

[0798] 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).

[0799] 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.

[0800] 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.

[0801] 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).

[0802] 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. 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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."

[0808] The present invention relates to a system that analyzes data from past idea contests and predicts the evaluation of newly submitted ideas. First, a means for collecting and preprocessing past proposal data is provided. Next, a means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility is provided. A means for inputting newly proposed ideas is provided, and the input ideas are preprocessed and analyzed using the model. Next, a means for generating feedback based on the analysis results is provided, and finally, a means for displaying the feedback to the user is provided.

[0809] Program processing overview

[0810] Data collection

[0811] The server collects proposal data from a database of past idea contests, including text data (titles and descriptions of ideas) and image data (visual descriptions of ideas).

[0812] Data Preprocessing

[0813] The server preprocesses the collected text data. Specifically, it tokenizes the text, removes stop words, normalizes characters, etc. For image data, it resizes the data and extracts features.

[0814] Model training

[0815] The server trains the model using the preprocessed data. It uses a deep learning algorithm (e.g., GPT-4V) to generate a model that evaluates the similarity, originality, and feasibility of ideas. 80% of the training data is used for training, and 20% is used for validation.

[0816] Input and preprocessing of new ideas

[0817] Users input new ideas into the system, including text entry and (optionally) image uploads. The device sends this data to the server, which then pre-processes it.

[0818] Idea Analysis

[0819] The server uses the pre-processed new idea data to perform analysis with the trained model, including calculating a similarity score by comparing it with past idea data and generating an originality score and a feasibility score.

[0820] Feedback Generation

[0821] The server generates feedback based on the analysis results, specifically a report containing a list of similar past ideas, an analysis of originality, a feasibility assessment, and specific improvements.

[0822] Feedback Display

[0823] The device receives feedback from the server and displays it to the user, including visual graphs and detailed text, presented in a format that is intuitively understandable to the user.

[0824] Specific examples

[0825] For example, suppose a user proposes an "innovative recycling system." The user enters a detailed description of the idea in text and uploads related images. The device sends this data to the server, which then performs preprocessing.

[0826] The server uses the preprocessed data to evaluate the similarity, originality, and feasibility of new ideas. The evaluation results in a similarity score of 75%, an originality score of 85 / 100, and a feasibility score of 70 / 100. Based on this information, specific improvements (e.g., improving cost efficiency, linking with other recycling technologies, etc.) are suggested.

[0827] Finally, the device visually displays this feedback to the user, allowing them to understand how their ideas are evaluated and providing specific directions for improvement.

[0828] In this way, the present invention is a system that helps participants objectively evaluate and effectively improve their ideas, thereby improving the quality and soundness of idea contests.

[0829] The processing flow will be explained below.

[0830] Step 1:

[0831] The server collects proposal data from past idea contests from a database, including text data (e.g., idea titles, detailed descriptions) and image designs (e.g., visual descriptions of ideas).

[0832] Step 2:

[0833] The server preprocesses the collected text data by tokenizing the text (splitting sentences into words and phrases), removing stop words (common words not needed for analysis), and normalizing characters (converting all to lowercase and removing special characters).

[0834] Step 3:

[0835] The server preprocesses the image data collected by resizing the images to a uniform size and extracting features (edges, color, shape, etc.).

[0836] Step 4:

[0837] The server trains the model using the preprocessed data. It uses deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of the proposals. 80% of the training data is used for training, and 20% is used for validation.

[0838] Step 5:

[0839] A user enters a new idea into the system by entering a title and detailed description of the idea in text boxes, and optionally uploading an associated image.

[0840] Step 6:

[0841] The terminal transmits the data input by the user to the server.

[0842] Step 7:

[0843] The server preprocesses the text data of new ideas. Similar to the preprocessing of collected data, it performs tokenization, stopword removal, and character normalization.

[0844] Step 8:

[0845] The server preprocesses the image data of the new idea. Similar to the preprocessing of collected data, it resizes and extracts features.

[0846] Step 9:

[0847] The server inputs the preprocessed new idea data into the model and performs analysis, calculating the idea similarity score, originality score, and feasibility score.

[0848] Step 10:

[0849] The server generates feedback based on the analysis, including a list of similar ideas from previous ideas, an analysis of originality, and an assessment of feasibility, as well as specific improvements and recommendations.

[0850] Step 11:

[0851] The device receives feedback from the server and displays it to the user in the form of visual graphs and detailed text, in a format that is intuitively understandable to the user.

[0852] Example 1

[0853] 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."

[0854] Conventional idea contests often lack fairness and objectivity because submitted ideas are evaluated subjectively by human judges. Furthermore, systems for efficiently analyzing proposed ideas and suggesting areas for improvement are inadequate, making it difficult to improve the quality of diverse ideas. Furthermore, while rapid and accurate evaluation of the similarity, originality, and feasibility of new ideas is required, achieving this is not easy.

[0855] 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.

[0856] In this invention, the server includes: means for collecting past proposal data; means for preprocessing the proposal data; means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility; means for inputting newly proposed ideas; means for preprocessing the newly input ideas and analyzing them using the model; means for generating feedback based on the analysis results; means for displaying the feedback to a user; data preprocessing means for tokenizing the text data, removing stop words, and normalizing characters; data preprocessing means for resizing the image data and extracting features; and means for dividing the model into a training set and a validation set for training and generating an optimal model. This makes it possible to objectively and efficiently evaluate newly proposed ideas and present specific areas for improvement.

[0857] "Past proposal data" refers to information on proposals submitted to previous idea contests, and includes text data and image data.

[0858] "Means of collection" refers to the function that allows the server to obtain and store past proposal data through a database or API.

[0859] "Preprocessing means" refers to a function that processes the data collected by the server, such as tokenizing, removing stop words, normalizing characters, resizing, and extracting features, to optimize it for subsequent analysis and training.

[0860] "Means for extracting features" is a function for deriving the information (features) required for the model from preprocessed data.

[0861] "Means for training a model" refers to the function by which the server uses deep learning algorithms to build and optimize a model based on collected and preprocessed data.

[0862] A "newly proposed idea" is an idea that a user newly submits to the system, and includes text data and image data.

[0863] "Input means" refers to an interface or function that allows users to submit new ideas to the system.

[0864] "Means for analysis" refers to the function by which the server preprocesses newly proposed ideas and evaluates them for similarity, originality, feasibility, etc. using a trained model.

[0865] The "means for generating feedback" is a function in which the server creates a report containing specific evaluations and areas for improvement for the user based on the analysis results.

[0866] The "means for displaying feedback to the user" is a function by which the terminal presents the generated feedback to the user in a format that can be visually and intuitively understood.

[0867] "Tokenization" is the process of dividing text data into smaller units (tokens) such as words or phrases.

[0868] "Stop word removal" is the process of removing words that occur frequently but are semantically insignificant (e.g., the, and).

[0869] "Character normalization" is the process of transforming characters from different writing forms to make them uniform.

[0870] "Resizing" is the process of changing and unifying the size of an image.

[0871] "Feature extraction" is the process of extracting important information (features) from image or text data for the model to analyze.

[0872] A "training set" is the portion of a dataset used to train a model, accounting for approximately 80% of the total data.

[0873] A "validation set" is a portion of the dataset used to evaluate the performance and accuracy of a model, and accounts for approximately 20% of the total data.

[0874] The "optimal model" is the model that has been adjusted to show the highest accuracy and performance as a result of evaluation using training data and validation data.

[0875] The present invention relates to a system for analyzing data from past idea contests and predicting the evaluation of newly submitted ideas. The embodiments for carrying out the present invention will be described in detail below.

[0876] The hardware configuration of this system includes a server and a terminal. The server is mainly responsible for data collection, preprocessing, model training and evaluation, and feedback generation. The terminal provides an interface for users to input new ideas and receive feedback.

[0877] 1. Data Collection

[0878] The server collects proposal data from a database of past idea contests via API. The proposal data includes text data (titles and descriptions of ideas) and image data (visual descriptions of ideas). The collected data is stored in the server's local data storage.

[0879] 2. Data Preprocessing

[0880] The server preprocesses the collected text data using a natural language processing tool (e.g., NLTK). Specifically, the process includes the following steps:

[0881] Tokenization: Breaking text into words and phrases.

[0882] Stop word removal: removes frequently occurring but semantically insignificant words.

[0883] Character normalization: unifying different writing forms.

[0884] Additionally, the image data is pre-processed using a computer vision library (e.g., OpenCV):

[0885] Resize: Resize images to a uniform size.

[0886] Feature extraction: Features are extracted from images using SIFT (Scale-Invariant Feature Transform).

[0887] 3. Model training

[0888] Based on the preprocessed data, the server trains a model using a deep learning algorithm (e.g., GPT-4V). The dataset is divided into a training set (80%) and a validation set (20%). The server uses these datasets to build and optimize a model to evaluate the similarity, originality, and feasibility of ideas.

[0889] 4. Enter a new idea

[0890] The user inputs new ideas in text format and uploads related images through the device, which then sends this data to the server using an HTTP request.

[0891] 5. Idea Analysis

[0892] The server pre-processes new ideas and feeds them into a trained model for analysis, which involves comparing them with past idea data to calculate a similarity score and generating originality and feasibility scores.

[0893] 6. Feedback Generation and Display

[0894] The server generates feedback based on the analysis results and creates a report containing specific improvements and evaluation results. The device displays this report to the user in a visually and intuitive format.

[0895] Specific examples

[0896] For example, suppose a user proposes an "innovative recycling system." The user enters a detailed description of the idea in text and uploads related images. The device sends this data to the server, which performs preprocessing. An example of a specific prompt is as follows:

[0897] "Please rate the following idea: It is titled 'Innovative Recycling System' and proposes an environmentally friendly recycling process. Please provide details below. {Detailed Description} Also, upload relevant images. Please provide your rating results with a similarity score, originality score, feasibility score, and specific suggestions for improvement."

[0898] The server tokenizes the text data using NLTK, removes stop words, and performs Unicode normalization. It also resizes images using OpenCV and extracts features using SIFT. It then uses a pre-trained GPT-4V model to evaluate the similarity, originality, and feasibility scores of new ideas. For example, a similarity score of 75%, an originality score of 85 / 100, and a feasibility score of 70 / 100 are calculated.

[0899] Finally, the terminal visually displays this feedback to the user, allowing the user to understand the evaluation of their idea and specific areas for improvement. Through this process, the present invention enables the improvement of the quality and soundness of ideas.

[0900] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0901] Step 1:

[0902] The server connects to a database of past idea contests. The input includes database access information and collection criteria. Specifically, the server calls an API and retrieves proposal data (text data and image data). The retrieved proposal data is saved in the server's local storage as an output.

[0903] Step 2:

[0904] The server preprocesses the collected text data. The input contains the acquired text data. Specifically, the server uses a natural language processing tool (e.g., NLTK) to tokenize the data, remove stop words, and normalize characters. The output is the preprocessed text data.

[0905] Step 3:

[0906] The server preprocesses the collected image data. The input contains the acquired image data. Specifically, the server resizes the image using a computer vision library (e.g., OpenCV) and extracts features using SIFT (Scale-Invariant Feature Transform). The output is the preprocessed image data.

[0907] Step 4:

[0908] The server uses the preprocessed data to train a model. The inputs include preprocessed text and image data and a deep learning algorithm (e.g., GPT-4V). Specifically, the server splits the data into a training set (80%) and a validation set (20%) and trains the deep learning model. The output is an optimized model.

[0909] Step 5:

[0910] A user uses a terminal to input a new idea in text format. The input includes a detailed description of the new idea and related images. Specific operations involve the user entering text and uploading images through the system interface. The output is the input data stored in the terminal.

[0911] Step 6:

[0912] The device sends input data for a new idea to the server. The input includes a detailed description and image of the idea stored on the device. In concrete terms, the device sends the data to the server using an HTTP request. The output is the data arriving at the server.

[0913] Step 7:

[0914] The server preprocesses the text data of new ideas. The input includes the submitted text data. Specific operations include tokenization, removal of stop words, and character normalization. The output is the preprocessed text data.

[0915] Step 8:

[0916] The server preprocesses the image data of the new idea. The input includes the transmitted image data. Specifically, the server resizes the image and extracts features. The output is the preprocessed image data.

[0917] Step 9:

[0918] The server analyzes the new idea using the trained model. The input includes preprocessed text data and image data of the new idea and the trained model. Specifically, the server inputs the data into the model and calculates a similarity score, originality score, and feasibility score. The output is the analysis result.

[0919] Step 10:

[0920] The server generates feedback based on the analysis results. The analysis results are included as input. In concrete terms, the server creates a feedback report, including improvements and evaluation results. The feedback report is obtained as output.

[0921] Step 11:

[0922] The terminal displays the feedback received from the server to the user. The input includes a feedback report. As a specific operation, the terminal visually displays the feedback through a user interface and presents it to the user. As an output, the user can confirm the feedback.

[0923] (Application example 1)

[0924] 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."

[0925] In recent years, factories and manufacturing industries have been required to improve efficiency and optimize designs, but evaluating new ideas and proposals requires a great deal of time and effort. It is also difficult to objectively evaluate ideas' similarity, originality, and feasibility, leaving employees with a lack of means to identify effective improvements. This makes it difficult to adopt and realize innovative ideas.

[0926] 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.

[0927] In this invention, the server includes means for collecting past proposal data, means for preprocessing the proposal data, means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility, means for inputting newly proposed ideas, means for preprocessing the newly input ideas and analyzing them using the model, means for generating feedback based on the analysis results, means for displaying the feedback to a user, and means for presenting specific improvements based on scores of similarity, originality, and feasibility of the new proposal. This allows a user to input a new idea via a smart device and quickly receive its evaluation results and improvements.

[0928] "Proposal data" is information about past proposals, and includes text data and image data.

[0929] "Preprocessing" is the process of converting collected proposal data into an analyzable format, including text tokenization, stopword removal, image resizing, and feature extraction.

[0930] "Features" are salient indicators or attributes extracted from data, and are information used for model training and analysis.

[0931] "Similarity" is an index that evaluates how similar a new proposal is to past proposals.

[0932] "Originality" is an index used to evaluate how novel a new proposal is.

[0933] "Feasibility" is an indicator used to evaluate whether a new proposal is technically feasible.

[0934] A "model" is an algorithm that learns from past data and evaluates the similarity, originality, and feasibility of new proposals. Specifically, it refers to a language processing model based on deep learning.

[0935] "Newly input ideas" are new ideas for factory efficiency or design proposed by the user.

[0936] "Feedback" is information that includes an evaluation and specific improvements provided to the user based on the analysis results.

[0937] "Users" are people who use the system, such as factory employees and engineers, who input proposals and receive evaluations.

[0938] The "scores of similarity, originality, and feasibility of new proposals" are indicators calculated by the model for new proposals, and are numerical values ​​that indicate the evaluation results of each.

[0939] "Specific improvements" are advice and suggestions based on the evaluation results of new proposals to make the ideas more feasible and effective.

[0940] A "visual graph" is a diagram that intuitively shows the evaluation results and is provided to the user as part of the feedback.

[0941] "Detailed text" is a detailed explanation of the evaluation results that is provided to the user as part of the feedback.

[0942] This invention relates to a system that analyzes data from past idea contests and predicts the evaluation of newly submitted ideas. This system aims to improve factory efficiency and optimize designs, and allows users to input new ideas via smart devices, and provides evaluation results and suggestions for improvement.

[0943] System configuration

[0944] The system consists of the following elements:

[0945] 1. Server: Data collection, preprocessing, model training, analysis, and feedback generation.

[0946] 2. Terminal: Used by users to input ideas and receive feedback. This can be a smart device such as a smartphone or tablet.

[0947] 3. Model: Based on a generative AI model (e.g., GPT-4V), we evaluate similarity, originality, and feasibility.

[0948] Processing flow

[0949] 1. Data Collection

[0950] The server collects past idea contest data, including text data (titles and descriptions of ideas) and image data (visual descriptions of ideas).

[0951] 2. Data Preprocessing

[0952] The server performs preprocessing on the collected text data, such as tokenizing, removing stop words, and normalizing characters. Image data is resized and features are extracted.

[0953] 3. Model training

[0954] The server extracts features from the preprocessed data and trains a generative AI model that evaluates the similarity, originality, and feasibility of new ideas.

[0955] 4. Enter a new idea

[0956] Users use their smart devices to input new ideas into the system, including text entry and (optionally) image uploads, which are then sent to the server, where preprocessing is performed.

[0957] 5. Idea Analysis

[0958] The server uses the pre-processed new idea data to perform analysis with the trained model, including comparing it with past idea data to calculate a similarity score and generating an originality score and a feasibility score.

[0959] 6. Feedback Generation

[0960] The server generates feedback based on the analysis, including a list of similar past ideas, an analysis of originality, a feasibility assessment, and specific improvements. This feedback includes visual graphs and detailed text.

[0961] 7. Feedback Display

[0962] The device displays the feedback received from the server to the user, allowing them to evaluate their ideas and get specific directions for improvement.

[0963] Specific examples

[0964] For example, a user might propose "Optimizing the transport robots in a factory." The user enters the proposal in text and uploads related images (if available). The data is entered using prompts like this:

[0965] Prompt: "Evaluate new ideas for optimizing transport robots in factories."

[0966] The server preprocesses this input data and analyzes it using a pre-trained model. The analysis results include similarity scores, originality scores, and feasibility scores, and specific improvements are suggested. Feedback includes visual graphs and detailed text, allowing users to intuitively understand the evaluation results and identify areas for improvement.

[0967] In this way, the present invention can effectively support the evaluation and improvement of new ideas in factories and manufacturing industries, contributing to business efficiency and technological advances.

[0968] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0969] Step 1:

[0970] The server collects past idea contest data. This data includes text data (e.g., idea titles and descriptions) and image data (e.g., visual descriptions of ideas). The input of the data collection is data from a database or external API, and the output is the collected raw proposal data.

[0971] Specifically, the server accesses the database and calls an API to retrieve past suggestion data, which returns a dataset containing suggestion titles, detailed descriptions, and associated images.

[0972] Step 2:

[0973] The server preprocesses the collected text and image data. For text data, tokenization, stop word removal, and character normalization are performed. For image data, resizing and feature extraction are performed. The input is the collected raw proposal data, and the output is the preprocessed data.

[0974] Specifically, the server uses a natural language processing library (e.g., NLTK, spaCy) to tokenize the text data and remove stop words, and an image processing library (e.g., OpenCV) to resize images and extract features.

[0975] Step 3:

[0976] The server extracts features from the preprocessed data and trains a generative AI model (e.g., GPT-4V) to evaluate the similarity, originality, and feasibility of new ideas. The input is the preprocessed data, and the output is the trained model.

[0977] Specifically, the server converts the preprocessed text and image data into feature vectors, which are then fed to an AI model to train it. Model training involves splitting the dataset into a training set and a test set and evaluating the model's performance.

[0978] Step 4:

[0979] Users use their smart devices to input new ideas into the system, which involves text input and (optionally) image upload. The input is the user's proposed idea, and the output is the data sent from the device.

[0980] Specifically, a user opens the application on their smart device, enters the title and detailed description of a new idea in text, and uploads related images if necessary. The device then calls an API that sends this data to the server.

[0981] Step 5:

[0982] The server preprocesses the submitted new idea data, which, similar to step 2, includes tokenizing text data, removing stop words, normalizing characters, and resizing and feature extraction of images. The input is the raw proposal data submitted by the user, and the output is the preprocessed new idea data.

[0983] Specifically, the server applies pre-processing algorithms to the new idea data to convert it into a format acceptable to the model.

[0984] Step 6:

[0985] The server uses the preprocessed new idea data to perform analysis with the trained model. This analysis includes calculating a similarity score with past idea data, generating an originality score, and generating a feasibility score. The input is the preprocessed new idea data, and the output is a score of the analysis result.

[0986] Specifically, the server inputs the features of the new idea into the model and calculates similarity scores, originality scores, and feasibility scores. These scores are evaluation results based on past data.

[0987] Step 7:

[0988] The server generates feedback based on the analysis results. This feedback includes a list of similar past ideas, originality analysis results, feasibility assessment, and specific improvement points. The input is the score of the analysis results, and the output is the generated feedback.

[0989] Specifically, the server organizes the evaluation results and creates detailed text and visual graphs containing useful improvements for the user.

[0990] Step 8:

[0991] The terminal displays the feedback received from the server to the user. The input is the generated feedback and the output is the information displayed to the user in visual and detailed text format.

[0992] Specifically, the device receives the feedback data and displays it in an intuitive format within the application, allowing users to evaluate their ideas and make any necessary improvements based on the displayed feedback.

[0993] 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.

[0994] This invention relates to a system that collects and analyzes data from past idea contests to predict how much a new idea submitted by a user will be evaluated. Furthermore, by combining this with an emotion engine that recognizes the user's emotions, the system provides the user with more appropriate feedback.

[0995] System configuration and operation

[0996] Data collection and preprocessing

[0997] The server collects proposal data from a database of past idea contests, including text data (titles and detailed descriptions of ideas) and image data (visual descriptions of ideas).

[0998] The server preprocesses the text data. Specifically, it tokenizes the text, removes stop words, and normalizes characters. Image data is resized to a uniform size and key features (edges, color, shape, etc.) are extracted.

[0999] Training the model

[1000] The server trains the model using the preprocessed data. It uses deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of the proposal. It uses 80% of the training data for training and 20% for validation.

[1001] Emotion engine integration

[1002] The emotion engine is used to recognize emotions from user input data. The server integrates a module that analyzes emotions from text data and a module that analyzes emotions from image and video data.

[1003] Entering and analyzing new ideas

[1004] A user inputs a new idea into the system, entering the title and detailed description of the idea in the text boxes, and uploading image data if necessary.

[1005] The device sends the input data to the server, which then preprocesses the text data of the new idea and analyzes the user's emotions using an emotion engine.

[1006] Analyzing ideas and generating feedback

[1007] The server inputs the preprocessed new idea data into the existing model and calculates similarity scores, originality scores, and feasibility scores, taking into account the user's emotional information analyzed by the emotion engine.

[1008] The server generates feedback based on these analysis results, including a list of similar past ideas, an analysis of originality, and an assessment of feasibility, and provides specific recommendations and suggestions for improvements based on the user's feelings.

[1009] View Feedback

[1010] The device receives feedback from the server and displays it to the user. The feedback is provided as visual graphs and text, and is presented in a format that the user can intuitively understand. In addition, the analysis results from the emotion engine are also displayed, allowing the user to receive appropriate feedback that reflects their emotional state.

[1011] Specific examples

[1012] For example, if a user proposes an idea for an "innovative recycling system," the user enters a detailed description of the idea in text and uploads related images. The device then sends this data to the server, which then performs preprocessing and user sentiment analysis.

[1013] Based on the analysis results, the similarity score is 75%, the originality score is 85 / 100, and the feasibility score is 70 / 100. Furthermore, if the emotion engine detects a positive emotion from the user's input data, the feedback will include specific improvements such as "This idea is very original. To further develop it, please focus on the following points."

[1014] In this way, the present invention is a system that can improve the quality of ideas by predicting how well a user's idea will be evaluated in a contest and providing feedback that takes into account the user's emotional state.

[1015] The processing flow will be explained below.

[1016] Step 1:

[1017] The server collects proposal data from past idea contests from a database, including text data such as idea titles and detailed descriptions, and image data that visually represent the ideas.

[1018] Step 2:

[1019] The server pre-processes the text data, which includes tokenization to split sentences into words and phrases, stopword removal to remove meaningless common words, and character normalization to lowercase all letters and remove special characters.

[1020] Step 3:

[1021] The server preprocesses the image data: resizes the images to a uniform size and extracts key features (edges, color, shape, etc.).

[1022] Step 4:

[1023] The server trains the model using the preprocessed data. It uses deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of ideas. For training, 80% of the data is used to train the model, and the remaining 20% ​​is used for validation.

[1024] Step 5:

[1025] A user inputs a new idea into the system by entering the title and detailed description of the idea in the text boxes, and uploading related image data if necessary.

[1026] Step 6:

[1027] The terminal transmits the data input by the user to the server.

[1028] Step 7:

[1029] The server preprocesses the text data of new ideas, tokenizing, removing stop words, and normalizing characters, similar to the processing in step 2.

[1030] Step 8:

[1031] The server preprocesses the image data of the new idea. As in step 3, it resizes and extracts features.

[1032] Step 9:

[1033] The server analyzes the user's emotions using an emotion engine, which analyzes the user's emotional state from the content of the text data and (optionally) from the uploaded image data.

[1034] Step 10:

[1035] The server inputs the preprocessed new idea data and user sentiment data into the evaluation model and performs analysis, calculating the idea similarity score, originality score, and feasibility score.

[1036] Step 11:

[1037] The server generates feedback based on the analysis results, including a list of similar past ideas, an analysis of originality, and an evaluation of feasibility. It also provides specific improvements and recommendations based on the results of the emotion engine's analysis of the user's emotions.

[1038] Step 12:

[1039] The device receives feedback from the server and displays it to the user. The feedback is presented in a format that is intuitively understandable to the user, such as visual graphs and detailed text. The analysis results from the emotion engine are also displayed, allowing the user to receive appropriate feedback that reflects their own emotional state.

[1040] In this way, the present invention is a system that can improve the quality of ideas by predicting how well a user's idea will be evaluated in a contest and providing feedback that takes into account the user's emotional state.

[1041] Example 2

[1042] 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."

[1043] Systems that predict the evaluation of newly submitted ideas based on evaluation data from past idea contests take time to process and analyze existing proposal data and can lack accuracy. Furthermore, they do not provide feedback that takes into account the user's emotional state, making it difficult to motivate users to improve. Therefore, there is a need for a system that can quickly and accurately predict the evaluation of ideas and provide appropriate feedback that reflects the user's emotional state.

[1044] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1045] In this invention, the server includes a means for collecting past proposal data, a means for preprocessing the proposal data, and a means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility, thereby enabling rapid and accurate analysis of newly proposed ideas.

[1046] The system also includes a means for inputting a newly proposed idea, a means for preprocessing the newly input idea and analyzing emotions using an emotion analysis module, a means for analyzing the idea using the emotion analysis result and a model, a means for generating feedback based on the analysis result, and a means for displaying the feedback to the user, thereby making it possible to provide appropriate feedback that reflects the emotional state of the user.

[1047] "Past proposal data" refers to information about ideas collected through previous idea contests, proposal activities, etc.

[1048] "Preprocessing" refers to a series of processes performed to make data easier to analyze, and specifically includes tokenizing text, removing stop words, resizing images, and extracting features.

[1049] "Features" refer to useful attributes and patterns extracted from data, and are used for algorithmic analysis and classification.

[1050] "Similarity" refers to an evaluation metric that indicates how similar two or more ideas or data are.

[1051] "Originality" refers to the degree to which an idea is novel and different from other ideas or existing ideas.

[1052] "Feasibility" refers to an evaluation metric that indicates whether an idea can be realistically implemented.

[1053] "Model" refers to a computer program using mathematical or machine learning algorithms built on collected data.

[1054] "Sentiment Analysis Module" refers to a system component for automatically analyzing emotions from user-entered data.

[1055] "Feedback" refers to advice and evaluation results provided to the user based on the analysis results.

[1056] "Input Form" refers to an interface for users to input new ideas, including text boxes and image upload functionality.

[1057] "Deep learning" refers to a machine learning technique that uses large amounts of data and multi-layered neural networks to make highly accurate predictions and classifications.

[1058] MODE FOR CARRYING OUT THE INVENTION

[1059] This invention relates to a system that collects and analyzes data from past idea contests and predicts the evaluation of new ideas submitted by users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides more appropriate feedback to the user.

[1060] Data collection and preprocessing

[1061] The server collects proposal data from a database of past idea contests. This data includes text data (titles and detailed descriptions of ideas) and image data (visual descriptions of ideas). It communicates with the database using SQL queries and API requests to retrieve the required data.

[1062] The server preprocesses the text data. Specifically, it uses natural language processing software to tokenize the text, remove stop words, and normalize characters. Furthermore, it uses image processing software to resize the image data to a uniform size and extract key features (edges, color, shape, etc.).

[1063] Training the model

[1064] The server trains a model using the preprocessed data. It uses a deep learning algorithm (e.g., BERT model or ResNet) to build a model that evaluates the similarity, originality, and feasibility of proposals. 80% of the training data is used for training, and the remaining 20% ​​is used for validation.

[1065] Emotion engine integration

[1066] Integrate an emotion engine into the server, including a Natural Language Processing (NLP) module for analyzing emotions from text data and a computer vision module (e.g., OpenCV or DeepFace) for analyzing emotions from image and video data.

[1067] Entering and analyzing new ideas

[1068] The user enters a new idea into the system. They enter the idea title and detailed description in the text boxes, and upload image data if necessary. The device then sends the entered data to the server. The data is sent securely using the HTTPS protocol.

[1069] The server preprocesses the text data of the new ideas and performs user sentiment analysis using an emotion engine. For example, the emotion analysis module extracts emotional information from the user's input.

[1070] Analyzing ideas and generating feedback

[1071] The server inputs the preprocessed new idea data into the existing evaluation model and calculates the idea's similarity score, originality score, and feasibility score. The server also takes into account the user's emotional information analyzed by the emotion engine. This allows the server to generate appropriate feedback that reflects the user's emotions.

[1072] View Feedback

[1073] The device receives feedback from the server and displays it to the user. The feedback is presented as visual graphs and text in a format that is intuitively understandable to the user. The generated feedback also includes specific improvements and recommendations based on similar past ideas, originality evaluation results, feasibility evaluation, and sentiment.

[1074] Specific examples

[1075] For example, if a user proposes an idea for an "innovative recycling system," the user enters a detailed description of the idea in text and uploads related images. The device then sends this data to the server, which then performs data preprocessing and user sentiment analysis. Based on the analysis results, the similarity score is 75%, the originality score is 85 / 100, and the feasibility score is 70 / 100. Furthermore, if the sentiment engine detects positive sentiment from the user's input data, the feedback includes specific suggestions for improvement, such as "This idea is very original. Please focus on the following points." An example of a prompt sentence to input to the generative AI model is, "Please generate a score and feedback for the idea 'innovative recycling system' proposed by the user."

[1076] In this way, the present invention can predict how well a user's idea will perform in a contest and provide feedback that takes into account the user's emotional state, thereby improving the quality of the idea.

[1077] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1078] System program processing flow

[1079] Step 1: Data collection

[1080] The server collects past proposal data by making SQL queries or API requests to the database to retrieve text data (idea titles, detailed descriptions) and image data (visual descriptions of ideas).

[1081] Input: Database query

[1082] Output: A set of text and image data

[1083] Step 2: Preprocessing the text data

[1084] The server preprocesses the collected text data: first, it uses natural language processing software to tokenize the text, then it removes stop words, and finally it normalizes the characters.

[1085] Input: Raw text data

[1086] Output: Preprocessed text data

[1087] Step 3: Preprocessing the image data

[1088] The server preprocesses the image data. It uses image processing software to resize all images to a uniform size. It then extracts key features from the images (edges, color, shape, etc.).

[1089] Input: Raw image data

[1090] Output: Preprocessed image data

[1091] Step 4: Prepare training data for the model

[1092] The server splits the preprocessed text and image data into a training dataset and a validation dataset, allowing the performance of the model to be evaluated.

[1093] Input: Preprocessed text and image data

[1094] Output: training dataset, validation dataset

[1095] Step 5: Train the model

[1096] The server trains a model using a deep learning algorithm (e.g., BERT model or ResNet). Using the training dataset, it builds a model to evaluate the similarity, originality, and feasibility of proposals.

[1097] Input: training dataset

[1098] Output: A trained model

[1099] Step 6: Prepare the Emotion Engine

[1100] The server implements an emotion engine, which includes an NLP module and an image recognition module (e.g., OpenCV or DeepFace), to analyze emotion information from user input data.

[1101] Input: Emotion Engine Software

[1102] Output: Sentiment analysis module

[1103] Step 7: User Ideas

[1104] To enter a new idea, users use the system's input form, enter a title and description in the text boxes, and upload an image if necessary.

[1105] Input: Text and image data of new ideas

[1106] Output: Idea input dataset

[1107] Step 8: Send data from the device to the server

[1108] The device sends the input data of the new idea to the server, which is securely transmitted using the HTTPS protocol.

[1109] Input: Idea input dataset

[1110] Output: Data sent to the server

[1111] Step 9: Preprocessing and sentiment analysis of new ideas

[1112] The server preprocesses the text data of new ideas and analyzes user sentiment using an emotion engine, which includes tokenizing the text, removing stop words, and normalizing characters. It also resizes the image data and extracts features.

[1113] Input: Text and image data of new ideas

[1114] Output: Preprocessed idea data and sentiment analysis results

[1115] Step 10: Analyze your idea

[1116] The server inputs the pre-processed new idea data into the trained model and calculates similarity scores, originality scores, and feasibility scores, while also taking into account the analysis results of the emotion engine.

[1117] Input: Preprocessed idea data and sentiment analysis results

[1118] Output: Idea rating score

[1119] Step 11: Generate feedback

[1120] The server generates feedback based on the analysis results, including a list of similar past ideas, an evaluation of originality and feasibility, and specific improvements and recommendations that take into account user sentiment.

[1121] Input: Idea rating scores and sentiment analysis results

[1122] Output: Feedback content

[1123] Step 12: Submit and view feedback

[1124] The device displays the feedback received from the server to the user, which is presented as visual graphs and text in a way that is intuitive to the user.

[1125] Input: Feedback

[1126] Output: Feedback displayed to the user

[1127] (Application example 2)

[1128] 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."

[1129] Existing systems often have inefficient processes for users to submit new ideas and receive feedback. In particular, the feedback provided may be insufficient because it does not take into account the user's emotional state, the originality of the proposal, or the feasibility of the proposal. Furthermore, when content creators submit new ideas, it is difficult to accurately predict how their ideas will be evaluated and receive feedback that takes their emotions into account.

[1130] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1131] In this invention, the server includes means for collecting past proposal data, means for preprocessing the proposal data, means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility, means for inputting newly proposed ideas, means for preprocessing the newly input ideas and analyzing them using the model, means for generating feedback based on the analysis results, means for displaying the feedback to the user, means for analyzing the user's emotions at the time of input, and means for reflecting the emotion analysis results in the feedback. This makes it possible to provide specific and useful feedback that takes into account the user's emotions, the originality, and feasibility of the idea.

[1132] "Past proposal data" refers to proposal information previously collected and recorded, including text data and image data.

[1133] "Preprocessing" refers to the process of converting raw data into a format that is easier to analyze, specifically tokenizing text, removing stop words, normalizing characters, and resizing and extracting features from images.

[1134] "Features" indicate specific attributes or aspects of data, and are important information that serves as input for model learning.

[1135] "Similarity" is an indicator of how similar a newly proposed idea is to past proposals.

[1136] "Originality" is an indicator of how unique and novel a newly proposed idea is.

[1137] "Feasibility" is an indicator of whether a newly proposed idea can be realized.

[1138] "Training a model" is the process of using historical data to tune an algorithm so that it can make predictions or classifications.

[1139] "Inputting an idea" refers to the act of a user providing information to the system, such as the title of the proposal, a detailed description, and related images and videos.

[1140] "Feedback" refers to advice and evaluations provided based on the analysis results, and is information that allows users to refine and improve their ideas.

[1141] "Analyzing emotions" is the process of identifying emotions from the user's input, facial expressions, etc., and specifying the type and intensity of those emotions.

[1142] In the system that realizes this application example, the program is implemented according to the following steps.

[1143] Data collection and preprocessing

[1144] The server collects past proposal data, including text data and image data. The server then preprocesses the collected data. Specifically, the server tokenizes the text data, removes stop words, and normalizes characters, and resizes the image data to extract key features (edges, color, shape, etc.).

[1145] Training the model

[1146] The server uses the preprocessed data to train a generative AI model, using deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of proposals, using 80% of the training data for training and 20% for validation.

[1147] Emotion engine integration

[1148] The server is integrated with emotion analysis modules, including a module for analyzing emotions from text data and a module for analyzing emotions from image and video data. This emotion engine is used to recognize emotions from user input data.

[1149] Entering and analyzing new ideas

[1150] The user inputs a new idea into the system. They enter the title and detailed description of the idea in the text boxes, and upload image data if necessary. The device then sends the input data to the server. The server then preprocesses the text data of the new idea and analyzes the user's emotions using an emotion engine.

[1151] Analyzing ideas and generating feedback

[1152] The server inputs the preprocessed new idea data into the existing model and calculates similarity, originality, and feasibility scores. The server also takes into account the user's emotional information analyzed by the emotion engine. The server generates feedback based on these analysis results. The feedback includes a list of similar past ideas, originality analysis results, and feasibility assessment. It also provides specific recommendations and suggestions for improvements appropriate to the user's emotions.

[1153] View Feedback

[1154] The device receives feedback from the server and displays it to the user. The feedback is provided as visual graphs and text, and is presented in a format that the user can intuitively understand. In addition, the analysis results from the emotion engine are also displayed, allowing the user to receive appropriate feedback that reflects their emotional state.

[1155] Specific examples

[1156] For example, if a user proposes an idea for an "innovative recycling system," they enter a detailed description of their idea in text and upload related images. The device then sends this data to the server, which then preprocesses the data and analyzes the user's sentiment. Based on the analysis results, the similarity score is 75%, the originality score is 85 / 100, and the feasibility score is 70 / 100. Furthermore, if the sentiment engine detects positive sentiment from the user's input data, the feedback will include specific improvements such as, "This idea is very original. To further develop it, please focus on the following points."

[1157] Prompt Sentence Examples

[1158] title = "Innovative recycling system ideas"

[1159] description = "My new recycling system idea is..."

[1160] image_path = "example.jpg"

[1161] In this way, the system helps content creators improve the quality of their ideas by predicting their ratings and providing emotionally sensitive feedback when they submit new ideas.

[1162] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1163] Step 1: Data collection and preprocessing

[1164] The server collects past proposal data from a database. The collected data includes text data (idea titles, detailed descriptions) and image data (visual descriptions of ideas). The input data is in text and image formats. The server tokenizes the text data, removes stop words, normalizes characters, resizes the image data to a uniform size, and extracts key features (edges, color, shape, etc.). The output is preprocessed text and image data.

[1165] Step 2: Training the model

[1166] The server uses the preprocessed data to train a generative AI model. Specifically, it uses a deep learning algorithm to build a model that evaluates the similarity, originality, and feasibility of proposals. 80% of the training data is used for training, and 20% is used for validation. The input is preprocessed text and image data, and the output is a trained evaluation model.

[1167] Step 3: Integrating the Emotion Engine

[1168] The server is integrated with an emotion analysis module, which can analyze emotions from user-supplied text and image data. The input is the text and image data provided by the user, and the output is the analyzed emotion information.

[1169] Step 4: Enter a new idea

[1170] A user uses a terminal to input a new idea into the system. Specifically, the user enters the title and detailed description of the idea in the text boxes, and uploads image data if necessary. The input is the text and image data entered by the user, and the output is the data sent from the terminal to the server.

[1171] Step 5: Data preprocessing and sentiment analysis

[1172] The server preprocesses the text data of new ideas received from the terminal and analyzes the user's emotions using an emotion engine. The input is the text and image data of the newly proposed idea, and the output is the preprocessed data and the user's emotional information.

[1173] Step 6: Analyze ideas and generate feedback

[1174] The server inputs the preprocessed new idea data into the existing evaluation model and calculates similarity scores, originality scores, and feasibility scores, taking into account the results of sentiment analysis. The input is the new idea data and the results of sentiment analysis, and the output is the idea's evaluation score and feedback based on the sentiment.

[1175] Step 7: View your feedback

[1176] The terminal receives feedback from the server and displays it to the user. The feedback is provided as visual graphs or text, and is displayed in a format that the user can intuitively understand. The input is the feedback data sent from the server, and the output is a display format that the user can view.

[1177] 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.

[1178] 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.

[1179] 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.

[1180] [Fourth embodiment]

[1181] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1182] 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.

[1183] 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).

[1184] 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.

[1185] 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.

[1186] 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).

[1187] 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. 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.

[1188] 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.

[1189] 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.

[1190] 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.

[1191] 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.

[1192] 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.

[1193] 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."

[1194] The present invention relates to a system that analyzes data from past idea contests and predicts the evaluation of newly submitted ideas. First, a means for collecting and preprocessing past proposal data is provided. Next, a means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility is provided. A means for inputting newly proposed ideas is provided, and the input ideas are preprocessed and analyzed using the model. Next, a means for generating feedback based on the analysis results is provided, and finally, a means for displaying the feedback to the user is provided.

[1195] Program processing overview

[1196] Data collection

[1197] The server collects proposal data from a database of past idea contests, including text data (titles and descriptions of ideas) and image data (visual descriptions of ideas).

[1198] Data Preprocessing

[1199] The server preprocesses the collected text data. Specifically, it tokenizes the text, removes stop words, normalizes characters, etc. For image data, it resizes the data and extracts features.

[1200] Model training

[1201] The server trains the model using the preprocessed data. It uses a deep learning algorithm (e.g., GPT-4V) to generate a model that evaluates the similarity, originality, and feasibility of ideas. 80% of the training data is used for training, and 20% is used for validation.

[1202] Input and preprocessing of new ideas

[1203] Users input new ideas into the system, including text entry and (optionally) image uploads. The device sends this data to the server, which then pre-processes it.

[1204] Idea Analysis

[1205] The server uses the pre-processed new idea data to perform analysis with the trained model, including calculating a similarity score by comparing it with past idea data and generating an originality score and a feasibility score.

[1206] Feedback Generation

[1207] The server generates feedback based on the analysis results, specifically a report containing a list of similar past ideas, an analysis of originality, a feasibility assessment, and specific improvements.

[1208] Feedback Display

[1209] The device receives feedback from the server and displays it to the user, including visual graphs and detailed text, presented in a format that is intuitively understandable to the user.

[1210] Specific examples

[1211] For example, suppose a user proposes an "innovative recycling system." The user enters a detailed description of the idea in text and uploads related images. The device sends this data to the server, which then performs preprocessing.

[1212] The server uses the preprocessed data to evaluate the similarity, originality, and feasibility of new ideas. The evaluation results in a similarity score of 75%, an originality score of 85 / 100, and a feasibility score of 70 / 100. Based on this information, specific improvements (e.g., improving cost efficiency, linking with other recycling technologies, etc.) are suggested.

[1213] Finally, the device visually displays this feedback to the user, allowing them to understand how their ideas are evaluated and providing specific directions for improvement.

[1214] In this way, the present invention is a system that helps participants objectively evaluate and effectively improve their ideas, thereby improving the quality and soundness of idea contests.

[1215] The processing flow will be explained below.

[1216] Step 1:

[1217] The server collects proposal data from past idea contests from a database, including text data (e.g., idea titles, detailed descriptions) and image designs (e.g., visual descriptions of ideas).

[1218] Step 2:

[1219] The server preprocesses the collected text data by tokenizing the text (splitting sentences into words and phrases), removing stop words (common words not needed for analysis), and normalizing characters (converting all to lowercase and removing special characters).

[1220] Step 3:

[1221] The server preprocesses the image data collected by resizing the images to a uniform size and extracting features (edges, color, shape, etc.).

[1222] Step 4:

[1223] The server trains the model using the preprocessed data. It uses deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of the proposals. 80% of the training data is used for training, and 20% is used for validation.

[1224] Step 5:

[1225] A user enters a new idea into the system by entering a title and detailed description of the idea in text boxes, and optionally uploading an associated image.

[1226] Step 6:

[1227] The terminal transmits the data input by the user to the server.

[1228] Step 7:

[1229] The server preprocesses the text data of new ideas. Similar to the preprocessing of collected data, it performs tokenization, stopword removal, and character normalization.

[1230] Step 8:

[1231] The server preprocesses the image data of the new idea. Similar to the preprocessing of collected data, it resizes and extracts features.

[1232] Step 9:

[1233] The server inputs the preprocessed new idea data into the model and performs analysis, calculating the idea similarity score, originality score, and feasibility score.

[1234] Step 10:

[1235] The server generates feedback based on the analysis, including a list of similar ideas from previous ideas, an analysis of originality, and an assessment of feasibility, as well as specific improvements and recommendations.

[1236] Step 11:

[1237] The device receives feedback from the server and displays it to the user in the form of visual graphs and detailed text, in a format that is intuitively understandable to the user.

[1238] Example 1

[1239] 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."

[1240] Conventional idea contests often lack fairness and objectivity because submitted ideas are evaluated subjectively by human judges. Furthermore, systems for efficiently analyzing proposed ideas and suggesting areas for improvement are inadequate, making it difficult to improve the quality of diverse ideas. Furthermore, while rapid and accurate evaluation of the similarity, originality, and feasibility of new ideas is required, achieving this is not easy.

[1241] 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.

[1242] In this invention, the server includes: means for collecting past proposal data; means for preprocessing the proposal data; means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility; means for inputting newly proposed ideas; means for preprocessing the newly input ideas and analyzing them using the model; means for generating feedback based on the analysis results; means for displaying the feedback to a user; data preprocessing means for tokenizing the text data, removing stop words, and normalizing characters; data preprocessing means for resizing the image data and extracting features; and means for dividing the model into a training set and a validation set for training and generating an optimal model. This makes it possible to objectively and efficiently evaluate newly proposed ideas and present specific areas for improvement.

[1243] "Past proposal data" refers to information on proposals submitted to previous idea contests, and includes text data and image data.

[1244] "Means of collection" refers to the function that allows the server to obtain and store past proposal data through a database or API.

[1245] "Preprocessing means" refers to a function that processes the data collected by the server, such as tokenizing, removing stop words, normalizing characters, resizing, and extracting features, to optimize it for subsequent analysis and training.

[1246] "Means for extracting features" is a function for deriving the information (features) required for the model from preprocessed data.

[1247] "Means for training a model" refers to the function by which the server uses deep learning algorithms to build and optimize a model based on collected and preprocessed data.

[1248] A "newly proposed idea" is an idea that a user newly submits to the system, and includes text data and image data.

[1249] "Input means" refers to an interface or function that allows users to submit new ideas to the system.

[1250] "Means for analysis" refers to the function by which the server preprocesses newly proposed ideas and evaluates them for similarity, originality, feasibility, etc. using a trained model.

[1251] The "means for generating feedback" is a function in which the server creates a report containing specific evaluations and areas for improvement for the user based on the analysis results.

[1252] The "means for displaying feedback to the user" is a function by which the terminal presents the generated feedback to the user in a format that can be visually and intuitively understood.

[1253] "Tokenization" is the process of dividing text data into smaller units (tokens) such as words or phrases.

[1254] "Stop word removal" is the process of removing words that occur frequently but are semantically insignificant (e.g., the, and).

[1255] "Character normalization" is the process of transforming characters from different writing forms to make them uniform.

[1256] "Resizing" is the process of changing and unifying the size of an image.

[1257] "Feature extraction" is the process of extracting important information (features) from image or text data for the model to analyze.

[1258] A "training set" is the portion of a dataset used to train a model, accounting for approximately 80% of the total data.

[1259] A "validation set" is a portion of the dataset used to evaluate the performance and accuracy of a model, and accounts for approximately 20% of the total data.

[1260] The "optimal model" is the model that has been adjusted to show the highest accuracy and performance as a result of evaluation using training data and validation data.

[1261] The present invention relates to a system for analyzing data from past idea contests and predicting the evaluation of newly submitted ideas. The embodiments for carrying out the present invention will be described in detail below.

[1262] The hardware configuration of this system includes a server and a terminal. The server is mainly responsible for data collection, preprocessing, model training and evaluation, and feedback generation. The terminal provides an interface for users to input new ideas and receive feedback.

[1263] 1. Data Collection

[1264] The server collects proposal data from a database of past idea contests via API. The proposal data includes text data (titles and descriptions of ideas) and image data (visual descriptions of ideas). The collected data is stored in the server's local data storage.

[1265] 2. Data Preprocessing

[1266] The server preprocesses the collected text data using a natural language processing tool (e.g., NLTK). Specifically, the process includes the following steps:

[1267] Tokenization: Breaking text into words and phrases.

[1268] Stop word removal: removes frequently occurring but semantically insignificant words.

[1269] Character normalization: unifying different writing forms.

[1270] Additionally, the image data is pre-processed using a computer vision library (e.g., OpenCV):

[1271] Resize: Resize images to a uniform size.

[1272] Feature extraction: Features are extracted from images using SIFT (Scale-Invariant Feature Transform).

[1273] 3. Model training

[1274] Based on the preprocessed data, the server trains a model using a deep learning algorithm (e.g., GPT-4V). The dataset is divided into a training set (80%) and a validation set (20%). The server uses these datasets to build and optimize a model to evaluate the similarity, originality, and feasibility of ideas.

[1275] 4. Enter a new idea

[1276] The user inputs new ideas in text format and uploads related images through the device, which then sends this data to the server using an HTTP request.

[1277] 5. Idea Analysis

[1278] The server pre-processes new ideas and feeds them into a trained model for analysis, which involves comparing them with past idea data to calculate a similarity score and generating originality and feasibility scores.

[1279] 6. Feedback Generation and Display

[1280] The server generates feedback based on the analysis results and creates a report containing specific improvements and evaluation results. The device displays this report to the user in a visually and intuitive format.

[1281] Specific examples

[1282] For example, suppose a user proposes an "innovative recycling system." The user enters a detailed description of the idea in text and uploads related images. The device sends this data to the server, which performs preprocessing. An example of a specific prompt is as follows:

[1283] "Please rate the following idea: It is titled 'Innovative Recycling System' and proposes an environmentally friendly recycling process. Please provide details below. {Detailed Description} Also, upload relevant images. Please provide your rating results with a similarity score, originality score, feasibility score, and specific suggestions for improvement."

[1284] The server tokenizes the text data using NLTK, removes stop words, and performs Unicode normalization. It also resizes images using OpenCV and extracts features using SIFT. It then uses a pre-trained GPT-4V model to evaluate the similarity, originality, and feasibility scores of new ideas. For example, a similarity score of 75%, an originality score of 85 / 100, and a feasibility score of 70 / 100 are calculated.

[1285] Finally, the terminal visually displays this feedback to the user, allowing the user to understand the evaluation of their idea and specific areas for improvement. Through this process, the present invention enables the improvement of the quality and soundness of ideas.

[1286] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1287] Step 1:

[1288] The server connects to a database of past idea contests. The input includes database access information and collection criteria. Specifically, the server calls an API and retrieves proposal data (text data and image data). The retrieved proposal data is saved in the server's local storage as an output.

[1289] Step 2:

[1290] The server preprocesses the collected text data. The input contains the acquired text data. Specifically, the server uses a natural language processing tool (e.g., NLTK) to tokenize the data, remove stop words, and normalize characters. The output is the preprocessed text data.

[1291] Step 3:

[1292] The server preprocesses the collected image data. The input contains the acquired image data. Specifically, the server resizes the image using a computer vision library (e.g., OpenCV) and extracts features using SIFT (Scale-Invariant Feature Transform). The output is the preprocessed image data.

[1293] Step 4:

[1294] The server uses the preprocessed data to train a model. The inputs include preprocessed text and image data and a deep learning algorithm (e.g., GPT-4V). Specifically, the server splits the data into a training set (80%) and a validation set (20%) and trains the deep learning model. The output is an optimized model.

[1295] Step 5:

[1296] A user uses a terminal to input a new idea in text format. The input includes a detailed description of the new idea and related images. Specific operations involve the user entering text and uploading images through the system interface. The output is the input data stored in the terminal.

[1297] Step 6:

[1298] The device sends input data for a new idea to the server. The input includes a detailed description and image of the idea stored on the device. In concrete terms, the device sends the data to the server using an HTTP request. The output is the data arriving at the server.

[1299] Step 7:

[1300] The server preprocesses the text data of new ideas. The input includes the submitted text data. Specific operations include tokenization, removal of stop words, and character normalization. The output is the preprocessed text data.

[1301] Step 8:

[1302] The server preprocesses the image data of the new idea. The input includes the transmitted image data. Specifically, the server resizes the image and extracts features. The output is the preprocessed image data.

[1303] Step 9:

[1304] The server analyzes the new idea using the trained model. The input includes preprocessed text data and image data of the new idea and the trained model. Specifically, the server inputs the data into the model and calculates a similarity score, originality score, and feasibility score. The output is the analysis result.

[1305] Step 10:

[1306] The server generates feedback based on the analysis results. The analysis results are included as input. In concrete terms, the server creates a feedback report, including improvements and evaluation results. The feedback report is obtained as output.

[1307] Step 11:

[1308] The terminal displays the feedback received from the server to the user. The input includes a feedback report. As a specific operation, the terminal visually displays the feedback through a user interface and presents it to the user. As an output, the user can confirm the feedback.

[1309] (Application example 1)

[1310] 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."

[1311] In recent years, factories and manufacturing industries have been required to improve efficiency and optimize designs, but evaluating new ideas and proposals requires a great deal of time and effort. It is also difficult to objectively evaluate ideas' similarity, originality, and feasibility, leaving employees with a lack of means to identify effective improvements. This makes it difficult to adopt and realize innovative ideas.

[1312] 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.

[1313] In this invention, the server includes means for collecting past proposal data, means for preprocessing the proposal data, means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility, means for inputting newly proposed ideas, means for preprocessing the newly input ideas and analyzing them using the model, means for generating feedback based on the analysis results, means for displaying the feedback to a user, and means for presenting specific improvements based on scores of similarity, originality, and feasibility of the new proposal. This allows a user to input a new idea via a smart device and quickly receive its evaluation results and improvements.

[1314] "Proposal data" is information about past proposals, and includes text data and image data.

[1315] "Preprocessing" is the process of converting collected proposal data into an analyzable format, including text tokenization, stopword removal, image resizing, and feature extraction.

[1316] "Features" are salient indicators or attributes extracted from data, and are information used for model training and analysis.

[1317] "Similarity" is an index that evaluates how similar a new proposal is to past proposals.

[1318] "Originality" is an index used to evaluate how novel a new proposal is.

[1319] "Feasibility" is an indicator used to evaluate whether a new proposal is technically feasible.

[1320] A "model" is an algorithm that learns from past data and evaluates the similarity, originality, and feasibility of new proposals. Specifically, it refers to a language processing model based on deep learning.

[1321] "Newly input ideas" are new ideas for factory efficiency or design proposed by the user.

[1322] "Feedback" is information that includes an evaluation and specific improvements provided to the user based on the analysis results.

[1323] "Users" are people who use the system, such as factory employees and engineers, who input proposals and receive evaluations.

[1324] The "scores of similarity, originality, and feasibility of new proposals" are indicators calculated by the model for new proposals, and are numerical values ​​that indicate the evaluation results of each.

[1325] "Specific improvements" are advice and suggestions based on the evaluation results of new proposals to make the ideas more feasible and effective.

[1326] A "visual graph" is a diagram that intuitively shows the evaluation results and is provided to the user as part of the feedback.

[1327] "Detailed text" is a detailed explanation of the evaluation results that is provided to the user as part of the feedback.

[1328] This invention relates to a system that analyzes data from past idea contests and predicts the evaluation of newly submitted ideas. This system aims to improve factory efficiency and optimize designs, and allows users to input new ideas via smart devices, and provides evaluation results and suggestions for improvement.

[1329] System configuration

[1330] The system consists of the following elements:

[1331] 1. Server: Data collection, preprocessing, model training, analysis, and feedback generation.

[1332] 2. Terminal: Used by users to input ideas and receive feedback. This can be a smart device such as a smartphone or tablet.

[1333] 3. Model: Based on a generative AI model (e.g., GPT-4V), we evaluate similarity, originality, and feasibility.

[1334] Processing flow

[1335] 1. Data Collection

[1336] The server collects past idea contest data, including text data (titles and descriptions of ideas) and image data (visual descriptions of ideas).

[1337] 2. Data Preprocessing

[1338] The server performs preprocessing on the collected text data, such as tokenizing, removing stop words, and normalizing characters. Image data is resized and features are extracted.

[1339] 3. Model training

[1340] The server extracts features from the preprocessed data and trains a generative AI model that evaluates the similarity, originality, and feasibility of new ideas.

[1341] 4. Enter a new idea

[1342] Users use their smart devices to input new ideas into the system, including text entry and (optionally) image uploads, which are then sent to the server, where preprocessing is performed.

[1343] 5. Idea Analysis

[1344] The server uses the pre-processed new idea data to perform analysis with the trained model, including comparing it with past idea data to calculate a similarity score and generating an originality score and a feasibility score.

[1345] 6. Feedback Generation

[1346] The server generates feedback based on the analysis, including a list of similar past ideas, an analysis of originality, a feasibility assessment, and specific improvements. This feedback includes visual graphs and detailed text.

[1347] 7. Feedback Display

[1348] The device displays the feedback received from the server to the user, allowing them to evaluate their ideas and get specific directions for improvement.

[1349] Specific examples

[1350] For example, a user might propose "Optimizing the transport robots in a factory." The user enters the proposal in text and uploads related images (if available). The data is entered using prompts like this:

[1351] Prompt: "Evaluate new ideas for optimizing transport robots in factories."

[1352] The server preprocesses this input data and analyzes it using a pre-trained model. The analysis results include similarity scores, originality scores, and feasibility scores, and specific improvements are suggested. Feedback includes visual graphs and detailed text, allowing users to intuitively understand the evaluation results and identify areas for improvement.

[1353] In this way, the present invention can effectively support the evaluation and improvement of new ideas in factories and manufacturing industries, contributing to business efficiency and technological advances.

[1354] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1355] Step 1:

[1356] The server collects past idea contest data. This data includes text data (e.g., idea titles and descriptions) and image data (e.g., visual descriptions of ideas). The input of the data collection is data from a database or external API, and the output is the collected raw proposal data.

[1357] Specifically, the server accesses the database and calls an API to retrieve past suggestion data, which returns a dataset containing suggestion titles, detailed descriptions, and associated images.

[1358] Step 2:

[1359] The server preprocesses the collected text and image data. For text data, tokenization, stop word removal, and character normalization are performed. For image data, resizing and feature extraction are performed. The input is the collected raw proposal data, and the output is the preprocessed data.

[1360] Specifically, the server uses a natural language processing library (e.g., NLTK, spaCy) to tokenize the text data and remove stop words, and an image processing library (e.g., OpenCV) to resize images and extract features.

[1361] Step 3:

[1362] The server extracts features from the preprocessed data and trains a generative AI model (e.g., GPT-4V) to evaluate the similarity, originality, and feasibility of new ideas. The input is the preprocessed data, and the output is the trained model.

[1363] Specifically, the server converts the preprocessed text and image data into feature vectors, which are then fed to an AI model to train it. Model training involves splitting the dataset into a training set and a test set and evaluating the model's performance.

[1364] Step 4:

[1365] Users use their smart devices to input new ideas into the system, which involves text input and (optionally) image upload. The input is the user's proposed idea, and the output is the data sent from the device.

[1366] Specifically, a user opens the application on their smart device, enters the title and detailed description of a new idea in text, and uploads related images if necessary. The device then calls an API that sends this data to the server.

[1367] Step 5:

[1368] The server preprocesses the submitted new idea data, which, similar to step 2, includes tokenizing text data, removing stop words, normalizing characters, and resizing and feature extraction of images. The input is the raw proposal data submitted by the user, and the output is the preprocessed new idea data.

[1369] Specifically, the server applies pre-processing algorithms to the new idea data to convert it into a format acceptable to the model.

[1370] Step 6:

[1371] The server uses the preprocessed new idea data to perform analysis with the trained model. This analysis includes calculating a similarity score with past idea data, generating an originality score, and generating a feasibility score. The input is the preprocessed new idea data, and the output is a score of the analysis result.

[1372] Specifically, the server inputs the features of the new idea into the model and calculates similarity scores, originality scores, and feasibility scores. These scores are evaluation results based on past data.

[1373] Step 7:

[1374] The server generates feedback based on the analysis results. This feedback includes a list of similar past ideas, originality analysis results, feasibility assessment, and specific improvement points. The input is the score of the analysis results, and the output is the generated feedback.

[1375] Specifically, the server organizes the evaluation results and creates detailed text and visual graphs containing useful improvements for the user.

[1376] Step 8:

[1377] The terminal displays the feedback received from the server to the user. The input is the generated feedback and the output is the information displayed to the user in visual and detailed text format.

[1378] Specifically, the device receives the feedback data and displays it in an intuitive format within the application, allowing users to evaluate their ideas and make any necessary improvements based on the displayed feedback.

[1379] 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.

[1380] This invention relates to a system that collects and analyzes data from past idea contests to predict how much a new idea submitted by a user will be evaluated. Furthermore, by combining this with an emotion engine that recognizes the user's emotions, the system provides the user with more appropriate feedback.

[1381] System configuration and operation

[1382] Data collection and preprocessing

[1383] The server collects proposal data from a database of past idea contests, including text data (titles and detailed descriptions of ideas) and image data (visual descriptions of ideas).

[1384] The server preprocesses the text data. Specifically, it tokenizes the text, removes stop words, and normalizes characters. Image data is resized to a uniform size and key features (edges, color, shape, etc.) are extracted.

[1385] Training the model

[1386] The server trains the model using the preprocessed data. It uses deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of the proposal. It uses 80% of the training data for training and 20% for validation.

[1387] Emotion engine integration

[1388] The emotion engine is used to recognize emotions from user input data. The server integrates a module that analyzes emotions from text data and a module that analyzes emotions from image and video data.

[1389] Entering and analyzing new ideas

[1390] A user inputs a new idea into the system, entering the title and detailed description of the idea in the text boxes, and uploading image data if necessary.

[1391] The device sends the input data to the server, which then preprocesses the text data of the new idea and analyzes the user's emotions using an emotion engine.

[1392] Analyzing ideas and generating feedback

[1393] The server inputs the preprocessed new idea data into the existing model and calculates similarity scores, originality scores, and feasibility scores, taking into account the user's emotional information analyzed by the emotion engine.

[1394] The server generates feedback based on these analysis results, including a list of similar past ideas, an analysis of originality, and an assessment of feasibility, and provides specific recommendations and suggestions for improvements based on the user's feelings.

[1395] View Feedback

[1396] The device receives feedback from the server and displays it to the user. The feedback is provided as visual graphs and text, and is presented in a format that the user can intuitively understand. In addition, the analysis results from the emotion engine are also displayed, allowing the user to receive appropriate feedback that reflects their emotional state.

[1397] Specific examples

[1398] For example, if a user proposes an idea for an "innovative recycling system," the user enters a detailed description of the idea in text and uploads related images. The device then sends this data to the server, which then performs preprocessing and user sentiment analysis.

[1399] Based on the analysis results, the similarity score is 75%, the originality score is 85 / 100, and the feasibility score is 70 / 100. Furthermore, if the emotion engine detects a positive emotion from the user's input data, the feedback will include specific improvements such as "This idea is very original. To further develop it, please focus on the following points."

[1400] In this way, the present invention is a system that can improve the quality of ideas by predicting how well a user's idea will be evaluated in a contest and providing feedback that takes into account the user's emotional state.

[1401] The processing flow will be explained below.

[1402] Step 1:

[1403] The server collects proposal data from past idea contests from a database, including text data such as idea titles and detailed descriptions, and image data that visually represent the ideas.

[1404] Step 2:

[1405] The server pre-processes the text data, which includes tokenization to split sentences into words and phrases, stopword removal to remove meaningless common words, and character normalization to lowercase all letters and remove special characters.

[1406] Step 3:

[1407] The server preprocesses the image data: resizes the images to a uniform size and extracts key features (edges, color, shape, etc.).

[1408] Step 4:

[1409] The server trains the model using the preprocessed data. It uses deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of ideas. For training, 80% of the data is used to train the model, and the remaining 20% ​​is used for validation.

[1410] Step 5:

[1411] A user inputs a new idea into the system by entering the title and detailed description of the idea in the text boxes, and uploading related image data if necessary.

[1412] Step 6:

[1413] The terminal transmits the data input by the user to the server.

[1414] Step 7:

[1415] The server preprocesses the text data of new ideas, tokenizing, removing stop words, and normalizing characters, similar to the processing in step 2.

[1416] Step 8:

[1417] The server preprocesses the image data of the new idea. As in step 3, it resizes and extracts features.

[1418] Step 9:

[1419] The server analyzes the user's emotions using an emotion engine, which analyzes the user's emotional state from the content of the text data and (optionally) from the uploaded image data.

[1420] Step 10:

[1421] The server inputs the preprocessed new idea data and user sentiment data into the evaluation model and performs analysis, calculating the idea similarity score, originality score, and feasibility score.

[1422] Step 11:

[1423] The server generates feedback based on the analysis results, including a list of similar past ideas, an analysis of originality, and an evaluation of feasibility. It also provides specific improvements and recommendations based on the results of the emotion engine's analysis of the user's emotions.

[1424] Step 12:

[1425] The device receives feedback from the server and displays it to the user. The feedback is presented in a format that is intuitively understandable to the user, such as visual graphs and detailed text. The analysis results from the emotion engine are also displayed, allowing the user to receive appropriate feedback that reflects their own emotional state.

[1426] In this way, the present invention is a system that can improve the quality of ideas by predicting how well a user's idea will be evaluated in a contest and providing feedback that takes into account the user's emotional state.

[1427] Example 2

[1428] 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."

[1429] Systems that predict the evaluation of newly submitted ideas based on evaluation data from past idea contests take time to process and analyze existing proposal data and can lack accuracy. Furthermore, they do not provide feedback that takes into account the user's emotional state, making it difficult to motivate users to improve. Therefore, there is a need for a system that can quickly and accurately predict the evaluation of ideas and provide appropriate feedback that reflects the user's emotional state.

[1430] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1431] In this invention, the server includes a means for collecting past proposal data, a means for preprocessing the proposal data, and a means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility, thereby enabling rapid and accurate analysis of newly proposed ideas.

[1432] The system also includes a means for inputting a newly proposed idea, a means for preprocessing the newly input idea and analyzing emotions using an emotion analysis module, a means for analyzing the idea using the emotion analysis result and a model, a means for generating feedback based on the analysis result, and a means for displaying the feedback to the user, thereby making it possible to provide appropriate feedback that reflects the emotional state of the user.

[1433] "Past proposal data" refers to information about ideas collected through previous idea contests, proposal activities, etc.

[1434] "Preprocessing" refers to a series of processes performed to make data easier to analyze, and specifically includes tokenizing text, removing stop words, resizing images, and extracting features.

[1435] "Features" refer to useful attributes and patterns extracted from data, and are used for algorithmic analysis and classification.

[1436] "Similarity" refers to an evaluation metric that indicates how similar two or more ideas or data are.

[1437] "Originality" refers to the degree to which an idea is novel and different from other ideas or existing ideas.

[1438] "Feasibility" refers to an evaluation metric that indicates whether an idea can be realistically implemented.

[1439] "Model" refers to a computer program using mathematical or machine learning algorithms built on collected data.

[1440] "Sentiment Analysis Module" refers to a system component for automatically analyzing emotions from user-entered data.

[1441] "Feedback" refers to advice and evaluation results provided to the user based on the analysis results.

[1442] "Input Form" refers to an interface for users to input new ideas, including text boxes and image upload functionality.

[1443] "Deep learning" refers to a machine learning technique that uses large amounts of data and multi-layered neural networks to make highly accurate predictions and classifications.

[1444] MODE FOR CARRYING OUT THE INVENTION

[1445] This invention relates to a system that collects and analyzes data from past idea contests and predicts the evaluation of new ideas submitted by users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides more appropriate feedback to the user.

[1446] Data collection and preprocessing

[1447] The server collects proposal data from a database of past idea contests. This data includes text data (titles and detailed descriptions of ideas) and image data (visual descriptions of ideas). It communicates with the database using SQL queries and API requests to retrieve the required data.

[1448] The server preprocesses the text data. Specifically, it uses natural language processing software to tokenize the text, remove stop words, and normalize characters. Furthermore, it uses image processing software to resize the image data to a uniform size and extract key features (edges, color, shape, etc.).

[1449] Training the model

[1450] The server trains a model using the preprocessed data. It uses a deep learning algorithm (e.g., BERT model or ResNet) to build a model that evaluates the similarity, originality, and feasibility of proposals. 80% of the training data is used for training, and the remaining 20% ​​is used for validation.

[1451] Emotion engine integration

[1452] Integrate an emotion engine into the server, including a Natural Language Processing (NLP) module for analyzing emotions from text data and a computer vision module (e.g., OpenCV or DeepFace) for analyzing emotions from image and video data.

[1453] Entering and analyzing new ideas

[1454] The user enters a new idea into the system. They enter the idea title and detailed description in the text boxes, and upload image data if necessary. The device then sends the entered data to the server. The data is sent securely using the HTTPS protocol.

[1455] The server preprocesses the text data of the new ideas and performs user sentiment analysis using an emotion engine. For example, the emotion analysis module extracts emotional information from the user's input.

[1456] Analyzing ideas and generating feedback

[1457] The server inputs the preprocessed new idea data into the existing evaluation model and calculates the idea's similarity score, originality score, and feasibility score. The server also takes into account the user's emotional information analyzed by the emotion engine. This allows the server to generate appropriate feedback that reflects the user's emotions.

[1458] View Feedback

[1459] The device receives feedback from the server and displays it to the user. The feedback is presented as visual graphs and text in a format that is intuitively understandable to the user. The generated feedback also includes specific improvements and recommendations based on similar past ideas, originality evaluation results, feasibility evaluation, and sentiment.

[1460] Specific examples

[1461] For example, if a user proposes an idea for an "innovative recycling system," the user enters a detailed description of the idea in text and uploads related images. The device then sends this data to the server, which then performs data preprocessing and user sentiment analysis. Based on the analysis results, the similarity score is 75%, the originality score is 85 / 100, and the feasibility score is 70 / 100. Furthermore, if the sentiment engine detects positive sentiment from the user's input data, the feedback includes specific suggestions for improvement, such as "This idea is very original. Please focus on the following points." An example of a prompt sentence to input to the generative AI model is, "Please generate a score and feedback for the idea 'innovative recycling system' proposed by the user."

[1462] In this way, the present invention can predict how well a user's idea will perform in a contest and provide feedback that takes into account the user's emotional state, thereby improving the quality of the idea.

[1463] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1464] System program processing flow

[1465] Step 1: Data collection

[1466] The server collects past proposal data by making SQL queries or API requests to the database to retrieve text data (idea titles, detailed descriptions) and image data (visual descriptions of ideas).

[1467] Input: Database query

[1468] Output: A set of text and image data

[1469] Step 2: Preprocessing the text data

[1470] The server preprocesses the collected text data: first, it uses natural language processing software to tokenize the text, then it removes stop words, and finally it normalizes the characters.

[1471] Input: Raw text data

[1472] Output: Preprocessed text data

[1473] Step 3: Preprocessing the image data

[1474] The server preprocesses the image data. It uses image processing software to resize all images to a uniform size. It then extracts key features from the images (edges, color, shape, etc.).

[1475] Input: Raw image data

[1476] Output: Preprocessed image data

[1477] Step 4: Prepare training data for the model

[1478] The server splits the preprocessed text and image data into a training dataset and a validation dataset, allowing the performance of the model to be evaluated.

[1479] Input: Preprocessed text and image data

[1480] Output: training dataset, validation dataset

[1481] Step 5: Train the model

[1482] The server trains a model using a deep learning algorithm (e.g., BERT model or ResNet). Using the training dataset, it builds a model to evaluate the similarity, originality, and feasibility of proposals.

[1483] Input: training dataset

[1484] Output: A trained model

[1485] Step 6: Prepare the Emotion Engine

[1486] The server implements an emotion engine, which includes an NLP module and an image recognition module (e.g., OpenCV or DeepFace), to analyze emotion information from user input data.

[1487] Input: Emotion Engine Software

[1488] Output: Sentiment analysis module

[1489] Step 7: User Ideas

[1490] To enter a new idea, users use the system's input form, enter a title and description in the text boxes, and upload an image if necessary.

[1491] Input: Text and image data of new ideas

[1492] Output: Idea input dataset

[1493] Step 8: Send data from the device to the server

[1494] The device sends the input data of the new idea to the server, which is securely transmitted using the HTTPS protocol.

[1495] Input: Idea input dataset

[1496] Output: Data sent to the server

[1497] Step 9: Preprocessing and sentiment analysis of new ideas

[1498] The server preprocesses the text data of new ideas and analyzes user sentiment using an emotion engine, which includes tokenizing the text, removing stop words, and normalizing characters. It also resizes the image data and extracts features.

[1499] Input: Text and image data of new ideas

[1500] Output: Preprocessed idea data and sentiment analysis results

[1501] Step 10: Analyze your idea

[1502] The server inputs the pre-processed new idea data into the trained model and calculates similarity scores, originality scores, and feasibility scores, while also taking into account the analysis results of the emotion engine.

[1503] Input: Preprocessed idea data and sentiment analysis results

[1504] Output: Idea rating score

[1505] Step 11: Generate feedback

[1506] The server generates feedback based on the analysis results, including a list of similar past ideas, an evaluation of originality and feasibility, and specific improvements and recommendations that take into account user sentiment.

[1507] Input: Idea rating scores and sentiment analysis results

[1508] Output: Feedback content

[1509] Step 12: Submit and view feedback

[1510] The device displays the feedback received from the server to the user, which is presented as visual graphs and text in a way that is intuitive to the user.

[1511] Input: Feedback

[1512] Output: Feedback displayed to the user

[1513] (Application example 2)

[1514] 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."

[1515] Existing systems often have inefficient processes for users to submit new ideas and receive feedback. In particular, the feedback provided may be insufficient because it does not take into account the user's emotional state, the originality of the proposal, or the feasibility of the proposal. Furthermore, when content creators submit new ideas, it is difficult to accurately predict how their ideas will be evaluated and receive feedback that takes their emotions into account.

[1516] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1517] In this invention, the server includes means for collecting past proposal data, means for preprocessing the proposal data, means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility, means for inputting newly proposed ideas, means for preprocessing the newly input ideas and analyzing them using the model, means for generating feedback based on the analysis results, means for displaying the feedback to the user, means for analyzing the user's emotions at the time of input, and means for reflecting the emotion analysis results in the feedback. This makes it possible to provide specific and useful feedback that takes into account the user's emotions, the originality, and feasibility of the idea.

[1518] "Past proposal data" refers to proposal information previously collected and recorded, including text data and image data.

[1519] "Preprocessing" refers to the process of converting raw data into a format that is easier to analyze, specifically tokenizing text, removing stop words, normalizing characters, and resizing and extracting features from images.

[1520] "Features" indicate specific attributes or aspects of data, and are important information that serves as input for model learning.

[1521] "Similarity" is an indicator of how similar a newly proposed idea is to past proposals.

[1522] "Originality" is an indicator of how unique and novel a newly proposed idea is.

[1523] "Feasibility" is an indicator of whether a newly proposed idea can be realized.

[1524] "Training a model" is the process of using historical data to tune an algorithm so that it can make predictions or classifications.

[1525] "Inputting an idea" refers to the act of a user providing information to the system, such as the title of the proposal, a detailed description, and related images and videos.

[1526] "Feedback" refers to advice and evaluations provided based on the analysis results, and is information that allows users to refine and improve their ideas.

[1527] "Analyzing emotions" is the process of identifying emotions from the user's input, facial expressions, etc., and specifying the type and intensity of those emotions.

[1528] In the system that realizes this application example, the program is implemented according to the following steps.

[1529] Data collection and preprocessing

[1530] The server collects past proposal data, including text data and image data. The server then preprocesses the collected data. Specifically, the server tokenizes the text data, removes stop words, and normalizes characters, and resizes the image data to extract key features (edges, color, shape, etc.).

[1531] Training the model

[1532] The server uses the preprocessed data to train a generative AI model, using deep learning algorithms to build a model that evaluates the similarity, originality, and feasibility of proposals, using 80% of the training data for training and 20% for validation.

[1533] Emotion engine integration

[1534] The server is integrated with emotion analysis modules, including a module for analyzing emotions from text data and a module for analyzing emotions from image and video data. This emotion engine is used to recognize emotions from user input data.

[1535] Entering and analyzing new ideas

[1536] The user inputs a new idea into the system. They enter the title and detailed description of the idea in the text boxes, and upload image data if necessary. The device then sends the input data to the server. The server then preprocesses the text data of the new idea and analyzes the user's emotions using an emotion engine.

[1537] Analyzing ideas and generating feedback

[1538] The server inputs the preprocessed new idea data into the existing model and calculates similarity, originality, and feasibility scores. The server also takes into account the user's emotional information analyzed by the emotion engine. The server generates feedback based on these analysis results. The feedback includes a list of similar past ideas, originality analysis results, and feasibility assessment. It also provides specific recommendations and suggestions for improvements appropriate to the user's emotions.

[1539] View Feedback

[1540] The device receives feedback from the server and displays it to the user. The feedback is provided as visual graphs and text, and is presented in a format that the user can intuitively understand. In addition, the analysis results from the emotion engine are also displayed, allowing the user to receive appropriate feedback that reflects their emotional state.

[1541] Specific examples

[1542] For example, if a user proposes an idea for an "innovative recycling system," they enter a detailed description of their idea in text and upload related images. The device then sends this data to the server, which then preprocesses the data and analyzes the user's sentiment. Based on the analysis results, the similarity score is 75%, the originality score is 85 / 100, and the feasibility score is 70 / 100. Furthermore, if the sentiment engine detects positive sentiment from the user's input data, the feedback will include specific improvements such as, "This idea is very original. To further develop it, please focus on the following points."

[1543] Prompt Sentence Examples

[1544] title = "Innovative recycling system ideas"

[1545] description = "My new recycling system idea is..."

[1546] image_path = "example.jpg"

[1547] In this way, the system helps content creators improve the quality of their ideas by predicting their ratings and providing emotionally sensitive feedback when they submit new ideas.

[1548] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1549] Step 1: Data collection and preprocessing

[1550] The server collects past proposal data from a database. The collected data includes text data (idea titles, detailed descriptions) and image data (visual descriptions of ideas). The input data is in text and image formats. The server tokenizes the text data, removes stop words, normalizes characters, resizes the image data to a uniform size, and extracts key features (edges, color, shape, etc.). The output is preprocessed text and image data.

[1551] Step 2: Training the model

[1552] The server uses the preprocessed data to train a generative AI model. Specifically, it uses a deep learning algorithm to build a model that evaluates the similarity, originality, and feasibility of proposals. 80% of the training data is used for training, and 20% is used for validation. The input is preprocessed text and image data, and the output is a trained evaluation model.

[1553] Step 3: Integrating the Emotion Engine

[1554] The server is integrated with an emotion analysis module, which can analyze emotions from user-supplied text and image data. The input is the text and image data provided by the user, and the output is the analyzed emotion information.

[1555] Step 4: Enter a new idea

[1556] A user uses a terminal to input a new idea into the system. Specifically, the user enters the title and detailed description of the idea in the text boxes, and uploads image data if necessary. The input is the text and image data entered by the user, and the output is the data sent from the terminal to the server.

[1557] Step 5: Data preprocessing and sentiment analysis

[1558] The server preprocesses the text data of new ideas received from the terminal and analyzes the user's emotions using an emotion engine. The input is the text and image data of the newly proposed idea, and the output is the preprocessed data and the user's emotional information.

[1559] Step 6: Analyze ideas and generate feedback

[1560] The server inputs the preprocessed new idea data into the existing evaluation model and calculates similarity scores, originality scores, and feasibility scores, taking into account the results of sentiment analysis. The input is the new idea data and the results of sentiment analysis, and the output is the idea's evaluation score and feedback based on the sentiment.

[1561] Step 7: View your feedback

[1562] The terminal receives feedback from the server and displays it to the user. The feedback is provided as visual graphs or text, and is displayed in a format that the user can intuitively understand. The input is the feedback data sent from the server, and the output is a display format that the user can view.

[1563] 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.

[1564] 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.

[1565] 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.

[1566] 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.

[1567] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1568] 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.

[1569] 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).

[1570] 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.

[1571] 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."

[1572] 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.

[1573] 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).

[1574] 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.

[1575] 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.

[1576] 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.

[1577] 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.

[1578] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1579] 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.

[1580] 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.

[1581] 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.

[1582] 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.

[1583] 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.

[1584] The following is further disclosed regarding the above embodiment.

[1585] (Claim 1)

[1586] a means of collecting historical proposal data;

[1587] means for preprocessing the proposal data;

[1588] means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility;

[1589] a means for inputting newly proposed ideas;

[1590] means for preprocessing the newly input ideas and analyzing them using the model;

[1591] means for generating feedback based on the analysis results;

[1592] means for displaying said feedback to a user;

[1593] A system including:

[1594] (Claim 2)

[1595] 2. The system of claim 1, wherein the suggestion data includes text data and image data.

[1596] (Claim 3)

[1597] The system of claim 1 , wherein the model is a language processing model based on deep learning.

[1598] "Example 1"

[1599] (Claim 1)

[1600] a means of collecting historical proposal data;

[1601] means for preprocessing the proposal data;

[1602] means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility;

[1603] a means for inputting newly proposed ideas;

[1604] means for preprocessing the newly input ideas and analyzing them using the model;

[1605] means for generating feedback based on the analysis results;

[1606] means for displaying said feedback to a user;

[1607] data preprocessing means including tokenizing the text data, removing stop words and normalizing characters;

[1608] a data preprocessing means for resizing the image data and extracting features;

[1609] A means for dividing the model into a training set and a validation set and training the model to generate an optimal model;

[1610] A system including:

[1611] (Claim 2)

[1612] 2. The system of claim 1, wherein the suggestion data includes text data and image data.

[1613] (Claim 3)

[1614] The system of claim 1 , wherein the model is a language processing model based on deep learning.

[1615] "Application Example 1"

[1616] (Claim 1)

[1617] a means of collecting historical proposal data;

[1618] means for preprocessing the proposal data;

[1619] means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility;

[1620] a means for inputting newly proposed ideas;

[1621] means for preprocessing the newly input ideas and analyzing them using the model;

[1622] means for generating feedback based on the analysis results;

[1623] means for displaying said feedback to a user;

[1624] A method to suggest specific improvements based on scores of similarity, originality, and feasibility of new proposals;

[1625] A system including:

[1626] (Claim 2)

[1627] 10. The system of claim 1, wherein the suggestion data includes textual data and image data, and the feedback includes visual graphs and detailed text.

[1628] (Claim 3)

[1629] The system of claim 1, wherein the model is a language processing model based on deep learning, and the system allows users to input new ideas via a smart device and display the evaluation results and areas for improvement.

[1630] "Example 2: Combining Emotion Engines"

[1631] (Claim 1)

[1632] a means of collecting historical proposal data;

[1633] means for preprocessing the proposal data;

[1634] means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility;

[1635] a means for inputting newly proposed ideas;

[1636] means for pre-processing the newly input ideas and analyzing their sentiment using a sentiment analysis module;

[1637] means for analyzing ideas using the sentiment analysis results and models;

[1638] means for generating feedback based on the analysis results;

[1639] means for displaying said feedback to a user;

[1640] A system including:

[1641] (Claim 2)

[1642] 2. The system of claim 1, wherein the suggestion data includes text data and image data.

[1643] (Claim 3)

[1644] The system of claim 1 , wherein the model is a language processing model based on deep learning.

[1645] (Claim 4)

[1646] The system of claim 1, wherein the feedback includes a list of similar past ideas, and evaluation results of originality and feasibility.

[1647] (Claim 5)

[1648] 10. The system of claim 1, wherein the feedback includes specific improvements and recommendations that reflect the user's emotional state.

[1649] "Application example 2 when combining emotion engines"

[1650] (Claim 1)

[1651] a means of collecting historical proposal data;

[1652] means for preprocessing the proposal data;

[1653] means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility;

[1654] a means for inputting newly proposed ideas;

[1655] means for preprocessing the newly input ideas and analyzing them using the model;

[1656] means for generating feedback based on the analysis results;

[1657] means for displaying said feedback to a user;

[1658] A means for analyzing the user's emotion when inputting;

[1659] a means for reflecting the emotion analysis result in feedback;

[1660] A system including:

[1661] (Claim 2)

[1662] 2. The system of claim 1, wherein the suggestion data includes text data and image data.

[1663] (Claim 3)

[1664] The system of claim 1 , wherein the model comprises a language processing model based on deep learning. [Explanation of symbols]

[1665] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting historical proposal data; means for preprocessing the proposal data; means for extracting features from the preprocessed data and training a model for evaluating similarity, originality, and feasibility; a means for inputting newly proposed ideas; means for preprocessing the newly input ideas and analyzing them using the model; means for generating feedback based on the analysis results; means for displaying said feedback to a user; A system including:

2. The system of claim 1 , wherein the suggestion data includes text data and image data.

3. The system of claim 1 , wherein the model is a language processing model based on deep learning.

Images