System

Abstract

To provide a system.SOLUTION: A system includes: means for analyzing the feeling of a user on the basis of the evaluation comment of the user; means for directly and concretely converting the evaluation comment of the user using generation AI on the basis of the analyzed feeling of the user; means for creating concrete improvement advice using the generation AI on the basis of the evaluation comment and the feeling of the user; and means for adding the created improvement advice to the evaluation comment.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] Conventional evaluation comments often contain abstract and general expressions, and lack specific areas for improvement or advice. In addition, the style of evaluation comments is not consistent, leading to variations depending on the evaluator, which can undermine the fairness and transparency of evaluations. [Means for solving the problem]

[0005] To solve this problem, we provide a system that uses artificial intelligence to convert evaluation comments into concise, accurate, and specific comments, and adds comments with advice for improvement from a third-party perspective in accordance with the messaging app's standard style. Furthermore, this system maintains the consistency and fairness of evaluation comments by providing a format for the evaluation comment field and an interface for accepting user input. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In one embodiment of the present invention, an artificial intelligence module is provided for converting evaluation comments into concise, accurate, and specific ones. This module uses natural language processing technology to analyze input evaluation comments and convert them into more specific and clear forms. For example, an abstract evaluation comment such as "You did a good job" is converted into a concrete evaluation comment such as "You delivered a high-quality deliverable within the project deadline."

[0029] "Example 2"

[0030] There is also a module that adds comments with advice for improvement from a third-party perspective, in line with the messaging app's default style. This module generates specific advice for improvement based on the evaluation comments and adds it to the evaluation comments. For example, in response to the evaluation comment "You delivered high-quality deliverables within the project deadline," the module adds the advice "For the next project, why not consider creating a more efficient workflow?"

[0031] "Example 3"

[0032] Furthermore, a module for providing a format for the evaluation comment field is also provided. This module provides an interface for users to write evaluation comments, and the aforementioned artificial intelligence module and improvement advice addition module operate on this interface. This allows users to write evaluation comments in a consistent format, maintaining the fairness and transparency of evaluations.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The user enters their evaluation comments into the system.

[0036] Step 2: The entered evaluation comments are sent to the artificial intelligence module.

[0037] Step 3: The AI ​​module uses natural language processing technology to analyze the evaluation comments and convert them into more specific and clearer forms, such as converting an abstract evaluation comment like "You did a good job" into a concrete evaluation comment like "You delivered high-quality deliverables within the project deadline."

[0038] Step 4: The converted rating comments are displayed to the user.

[0039] "Example 2"

[0040] Step 1: The user enters their evaluation comments into the system.

[0041] Step 2: The entered evaluation comments are sent to the improvement advice addition module.

[0042] Step 3: The improvement advice addition module generates specific improvement advice based on the evaluation comments and adds it to the evaluation comments. For example, in response to the evaluation comment "You delivered high-quality deliverables within the project deadline," the improvement advice added is "In the next project, why not consider a more efficient work flow?"

[0043] Step 4: The evaluation comment with the added improvement advice is displayed to the user.

[0044] "Example 3"

[0045] Step 1: The user launches a module that provides a format for the evaluation comment field.

[0046] Step 2: The module provides an interface for users to write evaluation comments.

[0047] Step 3: The user enters the evaluation comments into the interface.

[0048] Step 4: The aforementioned AI module and improvement advice addition module are activated to ensure consistency and fairness in the evaluation comments.

[0049] Example 1

[0050] Next, a description will be given of Example 1 of Form 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."

[0051] Conventional evaluation comments are abstract, making it difficult to provide specific feedback. It is also difficult to provide evaluation comments as improvement advice from a third-party perspective. This makes it difficult for the person being evaluated to understand specific areas for improvement, potentially resulting in missed growth opportunities.

[0052] 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.

[0053] In this invention, the server includes means for a user to input an evaluation comment, means for a terminal to transmit the input evaluation comment to the server, means for the server to receive the evaluation comment and analyze it using natural language processing technology, means for the server to generate a prompt sentence to input the analysis result to the generative AI model, means for the server to input the prompt sentence to the generative AI model and generate a specific evaluation comment, means for the server to transmit the generated specific evaluation comment to the terminal, means for the terminal to display the specific evaluation comment to the user, and means for providing a format for an evaluation comment entry field that implements these functions. This makes it possible to convert evaluation comments into specific and clear information and provide useful feedback to users.

[0054] A "user" is an individual or group that uses the system to input evaluation comments.

[0055] A "terminal" is a device through which a user inputs evaluation comments and communicates with a server.

[0056] The "server" is a computer system that receives and analyzes evaluation comments and generates specific evaluation comments using a generative AI model.

[0057] An "evaluation comment" is a feedback or evaluation text entered by a user.

[0058] "Natural language processing technology" is a technology for analyzing evaluation comments and extracting grammatical structures and keywords.

[0059] A "generative AI model" is an artificial intelligence model that generates specific evaluation comments based on analyzed evaluation comments.

[0060] A "prompt sentence" is an instruction sentence to be input into a generative AI model.

[0061] The "format of the evaluation comment entry field" is a format that provides an interface for the user to input evaluation comments.

[0062] This invention is a system for converting evaluation comments specifically and clearly. The program processing of this system will be specifically explained below.

[0063] First, the user inputs an evaluation comment using a terminal. The terminal then sends the evaluation comment to the server. The server then analyzes the received evaluation comment using natural language processing technology. This analysis uses natural language processing libraries such as "spaCy" and "NLTK."

[0064] Next, the server generates a prompt sentence to be input into the generative AI model based on the analysis results. For example, "GPT-4 (registered trademark)" is used as the generative AI model. An example of a prompt sentence is "Please convert the following abstract evaluation comment into a concrete evaluation comment: 'Good job'."

[0065] The server inputs the generated prompt into the generative AI model to generate a specific evaluation comment. Based on the prompt, the generative AI model outputs a specific evaluation comment such as "A high-quality deliverable was delivered within the project deadline."

[0066] The server then transmits the generated specific evaluation comment to the terminal, and the terminal displays the received specific evaluation comment to the user. For example, a comment such as "You provided a high-quality deliverable within the project deadline" is displayed on the user's screen.

[0067] As a concrete example, consider the case where a user inputs an evaluation comment such as "Good job." This comment is sent by the device to the server, which analyzes it using natural language processing technology. Based on the analysis results, the server generates a prompt saying, "Please convert the following abstract evaluation comment into a concrete evaluation comment: 'Good job'." The prompt is then input into a generative AI model, which generates a concrete evaluation comment: "You delivered a high-quality deliverable within the project deadline." The server then sends this concrete evaluation comment to the device, which displays it to the user.

[0068] In this way, it is possible to convert evaluation comments into specific and clear comments and provide useful feedback to users.

[0069] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0070] Step 1:

[0071] The user inputs an evaluation comment.

[0072] The user inputs an evaluation comment through the device interface, for example, by inputting "good job" in the text box. The input evaluation comment is temporarily stored in the device memory.

[0073] Step 2:

[0074] The terminal transmits the input evaluation comment to the server.

[0075] The terminal sends the evaluation comment entered by the user to the server as an HTTP request. At this time, the evaluation comment is packaged in JSON format. The input is the evaluation comment "Good job" and the output is an HTTP request to the server.

[0076] Step 3:

[0077] The server receives the evaluation comments and analyzes them using natural language processing technology.

[0078] The server analyzes the received evaluation comments using a natural language processing library (e.g., spaCy or NLTK). The analysis includes extracting the grammatical structure and keywords of the evaluation comments. The input is the evaluation comment "Good job," and the output is the analysis results (grammatical structure and keywords).

[0079] Step 4:

[0080] The server generates a prompt sentence to input the analysis results into the AI ​​model.

[0081] The server generates a prompt sentence to be input to the generative AI model based on the analysis results. For example, it generates a prompt sentence such as "Please convert the following abstract evaluation comment into a concrete evaluation comment: 'Good job'." The input is the analysis result, and the output is the prompt sentence.

[0082] Step 5:

[0083] The server inputs a prompt sentence into the generative AI model and generates a specific evaluation comment.

[0084] The server inputs the generated prompt into a generative AI model (e.g., GPT-4) to generate a specific evaluation comment. Based on the prompt, the generative AI model outputs a specific evaluation comment such as "You provided a high-quality deliverable within the project deadline." The input is the prompt, and the output is a specific evaluation comment.

[0085] Step 6:

[0086] The server transmits the generated specific evaluation comments to the terminal.

[0087] The server sends the generated specific evaluation comments to the terminal as an HTTP response. At this time, the evaluation comments are packaged again in JSON format. The input is the specific evaluation comments, and the output is the HTTP response to the terminal.

[0088] Step 7:

[0089] The terminal displays specific evaluation comments to the user.

[0090] The terminal displays the received specific evaluation comments to the user. For example, a comment such as "You provided a high-quality deliverable within the project deadline" is displayed on the user's screen. The input is the specific evaluation comment, and the output is the display to the user.

[0091] (Application example 1)

[0092] Next, a description will be given of Application Example 1 of Embodiment 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."

[0093] Previous evaluation comments were abstract, making it difficult to convey specific details. Furthermore, when evaluating work within factories, managers' evaluations of robots lacked specificity, meaning the evaluation content was not accurately conveyed. This led to problems such as a decrease in the transparency and reliability of the evaluations, making it difficult to identify areas for improvement.

[0094] 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.

[0095] In this invention, the server includes means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, means for adding comments of improvement advice from a third-party perspective in accordance with the default style of the messenger app, means for using a generative AI model for converting evaluation comments into a specific form, and means for providing an interface for converting in-factory work evaluation comments into a specific form. As a result, evaluation comments are converted into a specific and clear form, and in-factory work evaluations can be accurately communicated.

[0096] "Artificial intelligence" is the technology that enables computer systems to learn, reason, and self-correct by imitating human intelligence.

[0097] An "evaluation comment" is written feedback given in response to a specific action or achievement.

[0098] "Converting succinctly, accurately, and specifically" means converting abstract evaluation comments into concise, accurate, and detailed content.

[0099] A "messenger app" is a software application for sending and receiving text and multimedia messages.

[0100] "Adding comments offering advice on improvement from a third-party perspective" means adding comments to the evaluation comments that point out areas for improvement from an objective point of view.

[0101] A "generative AI model" is a machine learning model that is trained by an artificial intelligence to perform a specific task.

[0102] An "interface" is the means or method by which a user interacts with a system.

[0103] The "format of the evaluation comment entry field" refers to a standard format or layout for inputting and displaying evaluation comments.

[0104] To put the present invention into practice, it is necessary to build a system for converting evaluation comments into concrete terms. This system includes a program that utilizes artificial intelligence to convert evaluation comments succinctly, accurately, and concretely.

[0105] The server first receives the evaluation comment entered by the user. This evaluation comment is often abstract, such as "You did a good job." The server then analyzes the evaluation comment using natural language processing technology and converts it into concrete content. At this time, it uses a generative AI model to generate prompt sentences that convert the evaluation comment into a concrete form.

[0106] Specifically, the server generates a prompt like this:

[0107] Please translate the following evaluation comments into specific, clear statements: Good job

[0108] This prompt is then input into the generative AI model to obtain a specific evaluation comment, such as "The parts were assembled within the specified time and met the quality standards."

[0109] The server then formats these specific evaluation comments to match the messaging app's default style and adds third-party advice for improvement, such as "Next time, please consider revising your work procedures to improve efficiency."

[0110] The specific evaluation comments and improvement advice generated in this way are sent to the user's device and displayed in the evaluation comment section. Through this interface, users can check the specific and clear evaluation comments and identify areas for improvement as needed.

[0111] By implementing this system, evaluation comments can be converted into specific and clear forms, enabling work evaluations to be accurately communicated within the factory. This improves the transparency and reliability of evaluations and makes it easier to identify areas for improvement.

[0112] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0113] Step 1:

[0114] The user inputs an evaluation comment.

[0115] Input: The user inputs an evaluation comment through the terminal.

[0116] Output: The entered evaluation comments are sent to the server.

[0117] Specific operation: The user uses the terminal interface to input an evaluation comment, such as "Good job." The input comment is sent to the server.

[0118] Step 2:

[0119] The server receives the evaluation comments and analyzes them using natural language processing technology.

[0120] Input: Rating comment submitted by user.

[0121] Output: Structured data of parsed rating comments.

[0122] Specific operation: The server analyzes the received evaluation comments using natural language processing techniques (e.g., morphological analysis and grammatical analysis) and generates structured data to understand the meaning and context of the evaluation comments.

[0123] Step 3:

[0124] The server uses a generative AI model to generate prompts that convert the evaluation comments into concrete forms.

[0125] Input: Parsed structured data of rating comments.

[0126] Output: The generated prompt statement.

[0127] Specific action: Based on the parsed evaluation comments, the server generates a prompt sentence such as the following: "Please convert the following evaluation comments into a specific and clear form: Good job."

[0128] Step 4:

[0129] The server inputs a prompt sentence into the generative AI model and obtains specific evaluation comments.

[0130] Input: The generated prompt statement.

[0131] Output: Specific evaluation comments.

[0132] Specific operation: The server inputs the prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) to generate a specific evaluation comment. For example, a specific evaluation comment such as "The assembly of the parts was completed within the specified time and met the quality standards" can be obtained.

[0133] Step 5:

[0134] The server formats specific evaluation comments according to the messenger app's standard style and adds comments offering advice on improvement from a third-party perspective.

[0135] Input: Specific evaluation comments.

[0136] Output: Formatted evaluation comments and improvement advice.

[0137] Specific actions: The server formats the specific evaluation comment to match the messaging app's default style and adds improvement advice, such as "Next time, please consider revising your work procedures to be more efficient."

[0138] Step 6:

[0139] The server sends the formatted evaluation comments and improvement advice to the user's terminal.

[0140] Input: Formatted evaluation comments and improvement suggestions.

[0141] Output: Evaluation comments and improvement advice displayed on the user's device.

[0142] Specific operation: The server sends the formatted evaluation comments and improvement advice to the user's device, and the user can check them through the device interface.

[0143] Example 2

[0144] Next, a description will be given of Example 2 of Form 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."

[0145] In conventional evaluation comment systems, evaluation comments are often abstract and lack specificity, making it difficult for the recipient to clearly understand how to improve. Furthermore, there is a lack of a way to add specific improvement advice to evaluation comments, which leads to a problem of reduced feedback quality. Furthermore, the evaluation comment format is not standardized, which can lead to a lack of consistency in the comments.

[0146] 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.

[0147] In this invention, the server includes: a means for a user to input an evaluation comment; a means for a terminal to send the evaluation comment to the server; a means for the server to receive the evaluation comment and perform text analysis; a means for the server to input the analysis results into a generative AI model and generate improvement advice; a means for the server to add the generated improvement advice to the original evaluation comment; a means for the server to return the final comment to the terminal; a means for the terminal to display the final comment to the user; and a means for providing a format for an evaluation comment entry field that implements these functions. This makes it possible to add specific improvement advice to evaluation comments, thereby improving the quality of feedback. Furthermore, by standardizing the evaluation comment format, consistent comments can be provided.

[0148] A "user" is an individual or group that uses the system to input evaluation comments.

[0149] A "terminal" is a device through which a user inputs evaluation comments and communicates with a server.

[0150] The "server" is a computer system that receives and analyzes evaluation comments, generates improvement advice using a generative AI model, and returns the final comments to the terminal.

[0151] An "evaluation comment" refers to the content of feedback entered by a user, and is text that includes an evaluation of a project or work.

[0152] "Text analysis" is an analytical process using natural language processing technology that the server performs to understand the content of the evaluation comments.

[0153] A "generative AI model" is an artificial intelligence model that generates specific improvement advice based on evaluation comments.

[0154] "Improvement advice" refers to specific improvements or suggestions that are added to the evaluation comments.

[0155] The "evaluation comment entry field format" is a unified interface for users to input evaluation comments and for the server to return the final comments.

[0156] This invention is a system that allows users to input evaluation comments and adds specific improvement advice to them. This system is composed of three main elements: the user, the terminal, and the server.

[0157] First, the user inputs an evaluation comment. The terminal used by the user provides an interface for inputting the evaluation comment. This interface has a standardized format for the evaluation comment entry field, making it easy for the user to input the evaluation comment.

[0158] The terminal then transmits the evaluation comments entered by the user to the server, which uses natural language processing technology to analyze the received evaluation comments. Through this analysis, the content of the evaluation comments is understood.

[0159] The server inputs the analysis results into a generative AI model. For example, OpenAI's GPT-4 is used for this generative AI model. The generative AI model generates specific improvement advice based on the input evaluation comments. The generated improvement advice is added to the evaluation comments.

[0160] As a concrete example, suppose a user enters the following rating comment:

[0161] "We delivered high-quality deliverables within the project deadline."

[0162] The server parses this comment and inputs the following prompt into the generative AI model:

[0163] "Evaluation comment: High-quality deliverables were delivered within the project deadline. Please add any suggestions for improvement."

[0164] The generative AI model generates improvement advice such as:

[0165] "Why not consider a more efficient workflow for your next project?"

[0166] The server adds this improvement advice to the original rating comment to generate the final comment:

[0167] "We delivered high-quality deliverables within the project deadline. Why not consider a more efficient workflow for the next project?"

[0168] The final comments are sent back from the server to the terminal, which then displays them to the user, who can then check the evaluation comments with the added advice for improvement.

[0169] This system allows users to add specific advice for improvement to evaluation comments, improving the quality of feedback. Also, by standardizing the format of evaluation comments, users can provide consistent comments.

[0170] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0171] Step 1:

[0172] The user inputs an evaluation comment.

[0173] The user enters a review comment in the review comment input field of the messenger app. For example, the user might enter "They provided high-quality deliverables within the project deadline." The review comment is then sent to the device.

[0174] Step 2:

[0175] The terminal transmits the evaluation comment to the server.

[0176] The terminal transmits the evaluation comments entered by the user to the server in an appropriate format. The input is the evaluation comments, and the output is the data to be sent to the server.

[0177] Step 3:

[0178] The server receives the evaluation comments and performs text analysis.

[0179] The server receives the evaluation comments sent from the terminal. After receiving the evaluation comments, the server performs text analysis using natural language processing technology to understand the content of the evaluation comments. The input is the evaluation comments, and the output is the analysis results.

[0180] Step 4:

[0181] The server inputs the analysis results into a generative AI model to generate improvement advice.

[0182] The server inputs the analysis results into a generative AI model (e.g., GPT-4). The generative AI model generates specific improvement advice based on the input evaluation comments. The input is the analysis results, and the output is improvement advice.

[0183] Step 5:

[0184] The server adds the generated improvement advice to the original evaluation comment.

[0185] The server adds the improvement advice obtained from the generative AI model to the original evaluation comment. This results in an evaluation comment that reads, "You delivered a high-quality deliverable within the project deadline. For the next project, we suggest you consider a more efficient workflow." The input is the improvement advice and the original evaluation comment, and the output is the final comment.

[0186] Step 6:

[0187] The server sends the final comment back to the terminal.

[0188] The server returns the final comment to the terminal, sending it in the appropriate format. The input is the final comment, and the output is the data sent to the terminal.

[0189] Step 7:

[0190] The terminal displays the final comment to the user.

[0191] The terminal displays the final comments received from the server to the user. The user can check the evaluation comments to which improvement advice has been added. The input is the final comments, and the output is the display data for the user.

[0192] (Application example 2)

[0193] Next, a description will be given of Application Example 2 of Form 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."

[0194] In order to improve work efficiency in factories, it is important to provide specific improvement advice based on the evaluation comments of workers and robots. However, the current system does not efficiently collect evaluation comments, generate appropriate improvement advice, and notify it to workers and managers. This poses the issue of not achieving sufficient improvements in work efficiency.

[0195] 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.

[0196] In this invention, the server includes means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, means for adding improvement advice comments from a third-party perspective in accordance with the default style of the messenger app, means for collecting evaluation comments from workers and robots in the factory, means for generating specific improvement advice using a generative AI model based on the collected evaluation comments, means for notifying workers and managers of the generated improvement advice, and means for providing a format for an evaluation comment entry field that implements these functions. This makes it possible to efficiently carry out the process from collecting evaluation comments to generating and notifying improvement advice, thereby improving work efficiency in the factory.

[0197] "Artificial intelligence" is the technology that enables computer systems to learn, reason, and self-correct by imitating human intelligence.

[0198] An "evaluation comment" is a sentence that describes an evaluation of the work of a worker or robot.

[0199] A "messenger app" is application software for sending and receiving text messages and multimedia messages.

[0200] A "third-party perspective" refers to an objective viewpoint other than that of the evaluator or the person being evaluated.

[0201] "Improvement advice" is a specific proposal for improving the efficiency and quality of work based on the evaluation comments.

[0202] "In-plant" means the interior of a facility where manufacturing operations take place.

[0203] "Workers" refers to personnel who perform manufacturing work within a factory.

[0204] A "robot" is a mechanical device that performs tasks automatically according to programmed instructions.

[0205] A "generative AI model" is a model that uses artificial intelligence technology to generate text and data.

[0206] "Notification" is the act of conveying information to a specific recipient.

[0207] The "evaluation comment entry field" is an interface for inputting and displaying evaluation comments.

[0208] A "format" is a framework for organizing and arranging data or information in a particular way.

[0209] A system for implementing this invention is configured as follows: First, the server uses artificial intelligence to convert evaluation comments into concise, accurate, and specific ones. Next, it adds improvement advice comments from a third-party perspective in accordance with the default style of the messenger app. Furthermore, it collects evaluation comments from workers and robots in the factory and generates specific improvement advice using a generative AI model based on the collected evaluation comments. Finally, it notifies the generated improvement advice to workers and managers.

[0210] Hardware and software used

[0211] Hardware: Servers, smartphones, tablets, factory computers

[0212] Software: Python (registered trademark) 3.x, OpenAI API, messenger app

[0213] Data processing and calculation

[0214] The server first collects evaluation comments from workers and robots in the factory. These evaluation comments are sent to the server in text format. The server then analyzes the collected evaluation comments using natural language processing technology and generates specific improvement advice using a generative AI model (OpenAI's GPT-3). This generated improvement advice is added to the evaluation comments and ultimately notified to workers and managers.

[0215] Specific examples

[0216] For example, if evaluation comments are collected that Robot A quickly assembled parts in a factory, the server inputs the following prompt sentence into the generative AI model:

[0217] Prompt Sentence Examples

[0218] Evaluation comments: Robot A assembled the parts quickly.

[0219] Improvement advice:

[0220] The generative AI model generates specific improvement advice based on this prompt. For example, it might generate advice such as, "Next time, consider optimizing the placement of parts to further increase efficiency." This advice is added to the evaluation comments and notified to the worker or manager via smartphone or tablet.

[0221] In this way, the process from collecting evaluation comments to generating and notifying improvement advice can be carried out efficiently, making it possible to improve work efficiency within the factory.

[0222] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0223] Step 1:

[0224] The server collects evaluation comments from workers and robots in the factory.

[0225] Input: Evaluation comments from workers and robots (text format)

[0226] Output: Collected evaluation comments

[0227] Specific operation: A worker or a robot inputs an evaluation comment, which is sent to the server, which stores it in a database.

[0228] Step 2:

[0229] The server analyzes the collected evaluation comments using natural language processing technology.

[0230] Input: Collected evaluation comments

[0231] Output: Parsed rating comments

[0232] Specific operation: The server passes the evaluation comments to a text analysis engine to analyze grammar and semantics. The analysis results are used as part of the prompt sentence to input to the generative AI model.

[0233] Step 3:

[0234] The server generates specific improvement advice using a generative AI model based on the analyzed evaluation comments.

[0235] Input: Parsed rating comments

[0236] Output: Generated improvement advice

[0237] Specific operation: The server inputs the analyzed evaluation comments as prompt sentences into the generative AI model, which then generates specific improvement advice based on the prompt sentences.

[0238] Step 4:

[0239] The server adds the generated improvement advice to the evaluation comment.

[0240] Input: Generated improvement advice, evaluation comments

[0241] Output: Evaluation comment with improvement advice added

[0242] Specific behavior: The server appends the generated improvement advice to the original rating comment and formats it as a complete rating comment.

[0243] Step 5:

[0244] The server notifies the worker or manager of the evaluation comment with the added improvement advice.

[0245] Input: Evaluation comment with improvement advice added

[0246] Output: Notification to workers and managers

[0247] Specific operation: The server sends the evaluation comments with additional improvement advice to the worker or manager via a messenger app or notification system. The notification is displayed on the worker's smartphone or tablet.

[0248] Example 3

[0249] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0250] In conventional evaluation and comment systems, the evaluation comments written by users were often inconsistent, and specific improvement advice was often not provided. Furthermore, the analysis of evaluation comments and the generation of improvement advice were done manually, which was time-consuming and labor-intensive. This resulted in issues such as a lack of fairness and transparency in evaluations and a decline in user satisfaction.

[0251] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0252] In this invention, the server includes means for providing an interface for users to write evaluation comments, means for analyzing the evaluation comments using artificial intelligence on the interface and generating improvement advice, and means for presenting the generated improvement advice to the user, thereby improving the consistency and specificity of the evaluation comments and maintaining the fairness and transparency of the evaluations.

[0253] "User" means an individual or organization that uses the system to post evaluation comments and receive advice on improvements.

[0254] An "interface" is the screen or application operating part that allows users to input and submit evaluation comments.

[0255] "Artificial intelligence" refers to the machine learning models and algorithms used to analyze evaluation comments and generate improvement advice.

[0256] "Evaluation comments" are feedback and opinions written by users about products and services.

[0257] "Improvement advice" is specific suggestions and feedback generated by artificial intelligence by analyzing evaluation comments.

[0258] The "server" is a computer system that receives evaluation comments from users, analyzes them using artificial intelligence, and generates improvement advice.

[0259] "Format" refers to the consistent format and layout of the evaluation comment field, and is a structure that makes it easy for users to write evaluation comments.

[0260] "Natural language processing technology" is a technology used by artificial intelligence to analyze evaluation comments, and is a method for understanding text data and extracting meaning.

[0261] The present invention is a system that allows users to write evaluation comments, analyzes the comments using artificial intelligence, and generates specific advice for improvement. Specific embodiments of this system are described below.

[0262] Hardware and software used

[0263] Hardware: Servers, devices (PCs, smartphones, tablets, etc.)

[0264] Software: Generative AI model, evaluation comment writing module, improvement advice addition module

[0265] System configuration

[0266] 1. User Interface

[0267] The user accesses a web page or application provided by the evaluation comment writing module using a terminal. This interface includes UI elements such as a text box for inputting evaluation comments and a submit button.

[0268] 2. Enter and submit your evaluation comments

[0269] The user enters their review comments in a text box on the interface, for example, "This product is easy to use, but the battery life is poor." Once they are done, they click the "Submit" button.

[0270] 3. Receipt of rating comments by the server

[0271] The evaluation comments sent from the device are sent to the server, which receives the comments and stores them in a database.

[0272] 4. Analysis using generative AI models

[0273] The server passes the saved evaluation comments to a generative AI model for analysis, which uses natural language processing technology to understand the content of the comments.

[0274] 5. Generating Improvement Advice

[0275] Based on the analysis results of the generative AI model, the server calls the improvement advice addition module and generates specific improvement advice, such as "To extend battery life, consider improving the following: 1. Increase battery capacity. 2. Optimize software to reduce power consumption. 3. Add a power-saving mode."

[0276] 6. Providing advice to users

[0277] The server sends the generated improvement advice back to the user and displays it on the terminal interface, where the user can review it and modify the evaluation comments as necessary.

[0278] Specific examples

[0279] Example of a review comment: "This product is easy to use, but the battery life is poor."

[0280] Example prompt for a generative AI model: "If a user complains about the battery life of a product, what improvement advice should you provide?"

[0281] This system allows users to write evaluation comments in a consistent format, and the operation of the generative AI model and the improvement advice addition module ensures fairness and transparency of the evaluation. The flow of the identification process in Example 3 will be explained using Figure 15.

[0282] Step 1:

[0283] The user accesses the rating and comment writing interface.

[0284] Input: A user uses a device (PC, smartphone, tablet, etc.) to access the web page or application provided by the evaluation comment writing module.

[0285] Specific operation: The user opens a browser and enters the specified URL to access the site. The interface displays a text box for entering evaluation comments and a submit button.

[0286] Output: The user can now enter a rating comment.

[0287] Step 2:

[0288] The user enters and submits an evaluation comment.

[0289] Input: The user enters a rating comment in a text box on the interface.

[0290] Specific action: For example, enter "This product is easy to use, but the battery life is poor." After completing the entry, the user clicks the "Submit" button.

[0291] Output: The rating comment is sent from the device to the server.

[0292] Step 3:

[0293] The server receives the rating comments.

[0294] Input: Rating comment sent from the device.

[0295] Specific operation: The server receives the HTTP request, analyzes the rating comments, and stores them in a database.

[0296] Output: The rating comments are saved in the database.

[0297] Step 4:

[0298] The server analyzes the evaluation comments using a generative AI model.

[0299] Input: Rating comments stored in the database.

[0300] Specific operation: The server inputs the evaluation comments in text format into the generative AI model and obtains the analysis results. The generative AI model uses natural language processing technology to understand the content of the comments.

[0301] Output: Analysis results are generated.

[0302] Step 5:

[0303] The server generates advice using the improvement advice addition module.

[0304] Input: Analysis results of the generative AI model.

[0305] Specific operation: Based on the analysis results, the server calls the improvement advice addition module and generates specific improvement advice. For example, the advice generated might be, "To extend battery life, consider improving the following: 1. Increase battery capacity. 2. Optimize software to reduce power consumption. 3. Add a power-saving mode."

[0306] Output: Improvement advice is generated.

[0307] Step 6:

[0308] The server sends the generated advice back to the user

[0309] Input: The generated improvement advice.

[0310] Specific operation: The server generates an HTTP response and sends data including improvement advice to the terminal.

[0311] Output: Improvement advice is displayed on the terminal interface.

[0312] Step 7:

[0313] The user checks the improvement advice and modifies the evaluation comments as necessary.

[0314] Input: Improvement advice displayed on the terminal interface.

[0315] Specific behavior: The user reads the displayed advice, re-edits the rating comment, and resubmits it.

[0316] Output: The corrected rating comment is sent to the server again.

[0317] (Application example 3)

[0318] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0319] In conventional evaluation and comment systems, users often leave inconsistent comments that lack specificity and accuracy. Furthermore, there is a lack of specific advice on how to improve the quality of reviews, making it difficult for users to provide useful information for other users. Furthermore, writing reviews is cumbersome, making it difficult for users to easily write high-quality reviews.

[0320] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes: means for utilizing artificial intelligence to convert evaluation comments succinctly, accurately, and specifically; means for adding improvement advice comments from a third-party perspective in accordance with the default style of the messenger app; means for providing a format for the evaluation comment entry field that implements these functions; means for providing an interface for users to write product reviews; means for an artificial intelligence module to operate on the interface and analyze the content of the user's review; means for an improvement advice addition module to provide advice for improving the quality of the review in real time; and means for presenting guidelines for writing reviews in a consistent format. This enables users to easily write high-quality reviews and makes it easier for them to provide information that is useful to other users.

[0321] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[0322] An "evaluation comment" is a description of a user's opinion or impression about a particular product or service.

[0323] A "messenger app" is a software application for sending and receiving text and multimedia messages over the Internet.

[0324] A "third-party perspective" is an objective viewpoint from the standpoint of a third party who is not a party involved when making an evaluation or giving an opinion.

[0325] A "format" is a framework for arranging data or information in a specific form or structure.

[0326] An "interface" is the means or method by which a user interacts with a system or application.

[0327] An "artificial intelligence module" is an artificial intelligence component designed to perform a specific task.

[0328] "Analysis" is the process of examining data or information in detail to understand its structure and meaning.

[0329] The "improvement advice addition module" is a component for providing specific advice for improving quality based on user input.

[0330] "Guidelines" are guidelines or standards for performing specific actions or tasks.

[0331] A system for carrying out this invention comprises a server and a user terminal. The server includes means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, means for adding comments of improvement advice from a third-party perspective in accordance with the specified style of the messenger app, means for providing a format for the evaluation comment entry field that implements these functions, means for providing an interface for users to write product reviews, means for an artificial intelligence module to operate on the interface and analyze the content of the user's review, means for an improvement advice adding module to provide advice for improving the quality of the review in real time, and means for presenting guidelines so that reviews can be written in a consistent format.

[0332] Hardware and software used

[0333] Server: A server for hosting the Flask application.

[0334] User device: Smartphone

[0335] Software: Flask (a Python web framework), OpenAI API (an API for using generative AI models)

[0336] Data processing and calculation

[0337] 1. User device: The user enters the review on the smartphone app.

[0338] 2. Server: The entered review is sent to the Flask server.

[0339] 3. Server: The Flask server calls the OpenAI API and parses the reviews.

[0340] 4. Server: The generative AI model analyzes the reviews and generates improvement advice.

[0341] 5. Server: The Flask server returns the generated advice to the user.

[0342] Specific examples

[0343] If a user writes a review saying, "This product was very good. It was easy to use and convenient," the generative AI model will provide advice such as, "Your review will be even better if you add specific usage scenarios and information that would be useful to other users."

[0344] Prompt Sentence Examples

[0345] Please analyze the following reviews and provide your suggestions for improvement:

[0346] This product was very good. It was easy to use and convenient.

[0347] In this way, users can easily write high-quality reviews, making it easier for them to provide useful information to other users.

[0348] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0349] Step 1:

[0350] A user starts the smartphone app and enters a product review. The entered review is sent from the user's device to the server. The input data is the text review written by the user.

[0351] Step 2:

[0352] The server processes the received reviews using a Flask application, which prepares to call the OpenAI API to parse the reviews. The input data is the text review written by the user, and the output data is a prompt to send to the OpenAI API.

[0353] Step 3:

[0354] The server calls the OpenAI API and sends a prompt. The prompt contains instructions for analyzing the review written by the user and generating improvement advice. The input data is the prompt, and the output data is the improvement advice generated by the generative AI model.

[0355] Step 4:

[0356] The server receives the improvement advice returned from the OpenAI API. The received advice is sent back to the user device along with the user's review. The input data is the improvement advice generated by the generative AI model, and the output data is the review and advice sent back to the user device.

[0357] Step 5:

[0358] The user terminal displays the reviews and improvement advice received from the server. The user can modify or add to the review based on the displayed advice. The input data are the reviews and advice returned from the server, and the output data are the reviews modified or added by the user.

[0359] Step 6:

[0360] When the user finalizes the review and presses the submit button, the review is sent to the server again and saved as the final review. The input data is the final review with any corrections or additions made by the user, and the output data is the final review saved on the server.

[0361] 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.

[0362] "Example 1"

[0363] One embodiment of the present invention combines a system that includes a means for converting evaluation comments succinctly, accurately, and specifically, a means for adding improvement advice comments from a third-party perspective in accordance with the default style of a messaging app, and a means for providing a format for the evaluation comment entry field that implements these functions, with an emotion engine that recognizes user emotions. This emotion engine identifies emotional elements contained in the evaluation comments and converts the evaluation comments and generates improvement advice based on those elements. Specifically, from an evaluation comment such as "This project was very enjoyable," the emotion "fun" is extracted, and based on that, improvement advice is generated such as "We recommend that you work with the same team members on the next project so that you can have a similar enjoyment."

[0364] "Example 2"

[0365] In another embodiment, the emotion engine analyzes the user's emotions based on the evaluation comments and uses the results to convert the evaluation comments and generate improvement advice. In this case, the emotion engine extracts the emotion "difficult" from the evaluation comment "This project was very difficult," and based on that, generates improvement advice such as "We recommend assigning easier tasks to the next project."

[0366] "Example 3"

[0367] In another embodiment, the evaluation comment entry field format provides an interface for accepting user input, and the emotion engine operates on that interface. In this case, the user directly enters the evaluation comment into the interface, and the emotion engine analyzes the input in real time. Then, based on the analysis results, the evaluation comment is converted and improvement advice is generated, and this is fed back to the user.

[0368] The processing flow of each embodiment will be described below.

[0369] "Example 1"

[0370] Step 1: The user enters their evaluation comments into the system.

[0371] Step 2: The emotion engine extracts emotional elements from the evaluation comments.

[0372] Step 3: Based on the extracted sentiment, the evaluation comments are converted and improvement advice is generated.

[0373] Step 4: Provide the generated improvement advice to the user as feedback.

[0374] "Example 2"

[0375] Step 1: The user enters their evaluation comments into the system.

[0376] Step 2: The sentiment engine analyzes the rating comments and extracts the user's sentiment.

[0377] Step 3: Based on the extracted sentiment, the evaluation comments are converted and improvement advice is generated.

[0378] Step 4: Provide the generated improvement advice to the user as feedback.

[0379] "Example 3"

[0380] Step 1: The user enters the evaluation comment directly into the system interface.

[0381] Step 2: The emotion engine analyzes the user's input in real time.

[0382] Step 3: Based on the analysis results, the evaluation comments are converted and improvement advice is generated. Step 4: The generated improvement advice is fed back to the user in real time.

[0383] Example 1

[0384] Next, a description will be given of Example 1 of Form 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."

[0385] Conventional evaluation and comment systems have difficulty converting abstract evaluation comments into concrete, clear forms, and are unable to provide improvement advice that takes into account the user's feelings. As a result, evaluation comments are vague, and it is difficult to obtain specific feedback or areas for improvement. Furthermore, it is difficult to provide comments that fit the default style of the messaging app.

[0386] 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.

[0387] In this invention, the server includes means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, means for adding improvement advice comments from a third-party perspective in accordance with the default style of the messenger app, means for providing a format for the evaluation comment entry field that implements these functions, and means for identifying emotional elements included in the evaluation comments using an emotion engine that recognizes user emotions and converting the evaluation comments and generating improvement advice based on the identified emotional elements. This makes it possible to convert evaluation comments into a specific and clear format and provide improvement advice that takes the user's emotions into consideration.

[0388] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[0389] An "evaluation comment" is a piece of text that describes feedback or opinions about a specific action or outcome.

[0390] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0391] A "messenger app" is a software application for sending and receiving text and multimedia messages.

[0392] An "emotion engine" is a technology for extracting and analyzing emotional elements from data such as text and voice.

[0393] A "format" is a framework for arranging data or information in a specific form or structure.

[0394] An "interface" is a part that provides the means and methods for a user to interact with a system.

[0395] "Improvement advice" is specific suggestions or advice for improving a particular behavior or outcome.

[0396] MODE FOR CARRYING OUT THE INVENTION

[0397] This invention is a system that converts evaluation comments succinctly, accurately, and specifically, and provides emotion-based improvement advice. This system is realized by combining artificial intelligence, natural language processing technology, and an emotion engine.

[0398] 1. Generate the system program

[0399] The user uses an interface for inputting evaluation comments. This interface is provided as a text box on a web browser, etc. When the user inputs an evaluation comment, the comment is sent to the server.

[0400] 2. Explain the program's processing in natural language

[0401] The server uses Python's natural language processing libraries, NLTK and spaCy, to analyze the grammatical structure of the evaluation comments received from users and extract elements such as subjects, predicates, and objects.

[0402] Next, the server converts the evaluation comments into concrete, clear comments based on the analysis results. For example, a comment such as "This project was a lot of fun" can be converted into "I recommend that you work with the same team members on the next project so that you can have the same fun experience."

[0403] Furthermore, the server uses IBM Watson® sentiment analysis API to identify emotional elements contained in the evaluation comments. Based on the identified emotions, the server generates improvement advice. For example, based on the emotion "fun," the server generates advice such as "recommend having the same team members participate in the next project so that you can feel the same enjoyment."

[0404] 3. Add examples to your description

[0405] As a specific example, the processing when the following evaluation comment is input will be shown.

[0406] Entered evaluation comment:

[0407] "This project was a lot of fun."

[0408] Evaluation comments after conversion:

[0409] "We encourage you to join the same team members so that you can have the same fun on your next project."

[0410] Example prompts to input to a generative AI model:

[0411] "Transform the following evaluation comment into a specific, clear form and add emotion-based suggestions for improvement. Evaluation comment: 'I had a lot of fun on this project.'"

[0412] In this way, users can utilize a system that converts evaluation comments into concrete and clear forms and provides emotion-based improvement advice. This system can improve the quality of evaluation comments and increase user satisfaction by providing specific feedback and suggestions for improvement.

[0413] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0414] Step 1:

[0415] The user inputs an evaluation comment.

[0416] The user enters an evaluation comment in a text box on the web browser. For example, the user enters "I really enjoyed this project." The entered comment is sent to the server.

[0417] Step 2:

[0418] The server receives the rating comments.

[0419] The server receives the evaluation comments sent by the users and temporarily stores them in a database. The received comments become input data for the next analysis step.

[0420] Step 3:

[0421] The server analyzes the evaluation comments using natural language processing technology.

[0422] The server uses Python's natural language processing libraries NLTK and spaCy to analyze the grammatical structure of the evaluation comments. Specifically, it extracts elements such as the subject, predicate, and object of the comment. For example, from the comment "This project was very fun," it extracts the elements "project" and "fun." The analysis results become the input data for the next conversion step.

[0423] Step 4:

[0424] Based on the analysis results, the server converts the evaluation comments into a concrete and clear form.

[0425] The server converts the evaluation comments into concrete, clear forms based on the analysis results. For example, a comment such as "This project was very enjoyable" can be converted into "I recommend that you work with the same team members on the next project so that you can have the same enjoyment." The converted comments become input data for the next sentiment analysis step.

[0426] Step 5:

[0427] The server uses an emotion engine to identify emotional elements contained in the evaluation comments.

[0428] The server uses IBM Watson's sentiment analysis API to identify the emotional elements contained in the evaluation comments. For example, it extracts the emotion "fun." The results of the sentiment analysis become input data for the next step, which is generating improvement advice.

[0429] Step 6:

[0430] The server generates improvement advice based on the emotion.

[0431] The server generates improvement advice based on the identified emotion. For example, based on the emotion "fun," it generates advice such as "recommend participating in the next project with the same team members so that you can feel the same enjoyment." The generated improvement advice becomes the final output data.

[0432] Step 7:

[0433] The server returns the converted evaluation comments and improvement advice to the user.

[0434] The server then returns the converted evaluation comments and advice for improvement to the user. The user can view this information through the system interface. For example, in a web browser, the user might see a comment and advice such as, "We recommend that you work with the same team members on your next project so that you can have the same fun."

[0435] (Application example 1)

[0436] Next, a description will be given of Application Example 1 of Embodiment 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."

[0437] Conventional evaluation and comment systems have the problem that many of the evaluation comments are abstract, making it difficult to obtain specific feedback. Furthermore, there is a lack of improvement advice that takes emotional factors into consideration, which can lead to a decline in the quality of the evaluation comments. Furthermore, while specific and clear feedback is required for work evaluations within factories, there is a lack of means to achieve this.

[0438] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes: means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence; means for adding improvement advice comments from a third-party perspective in accordance with the default style of the messenger app; means for providing a format for the evaluation comment entry field that implements these functions; means for identifying emotional elements contained in the evaluation comments using an emotion engine and converting the evaluation comments and generating improvement advice based on the identified emotional elements; and means for providing a work evaluation feedback system to be installed in a factory robot. This makes it possible to generate specific and clear evaluation comments and provide improvement advice that takes emotional elements into consideration.

[0439] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[0440] An "evaluation comment" is a piece of writing that expresses opinions or feedback about a specific action or result.

[0441] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language.

[0442] An "emotion engine" is a technology that extracts emotional elements from text data and generates appropriate responses and actions based on them.

[0443] A "messenger app" is a software application for sending and receiving text messages.

[0444] "Third-party perspective" refers to making evaluations and opinions from a neutral and objective point of view.

[0445] "Improvement advice" is specific suggestions or advice for improving a particular behavior or outcome.

[0446] The "evaluation comment entry field" is an interface for inputting, displaying, and editing evaluation comments.

[0447] A "factory robot" is a mechanical device used to automate work in a factory.

[0448] The "work evaluation feedback system" is a system for collecting and analyzing work evaluation comments and providing feedback.

[0449] As an embodiment of the present invention, a work evaluation feedback system installed in a factory robot is provided. A specific embodiment of this system will be described below.

[0450] System configuration

[0451] The system consists of the following main components:

[0452] 1. Artificial intelligence module: Converts evaluation comments into concise, accurate, and specific comments.

[0453] 2. Emotion engine: Identifies the emotional elements contained in the evaluation comments and converts the evaluation comments and generates improvement advice based on that.

[0454] 3. Evaluation comment entry field: Provides an interface for users to enter, view, and edit evaluation comments.

[0455] 4. Factory robots: Install a work evaluation feedback system and perform work evaluation within the factory.

[0456] Program processing

[0457] The server processes the data in the following steps:

[0458] 1. Entering evaluation comments: The user enters evaluation comments in the evaluation comment field.

[0459] 2. Natural Language Processing: The artificial intelligence module uses natural language processing technology to analyze the input evaluation comments and convert them into a concrete and clear form.

[0460] 3. Sentiment Analysis: The sentiment engine identifies the emotional components contained in the rating comments.

[0461] 4. Generation of improvement advice: Based on the results of the emotion engine, appropriate improvement advice is generated.

[0462] 5. Providing feedback: Providing converted evaluation comments and improvement advice to users.

[0463] Hardware and software used

[0464] Hardware: Factory robots, servers, user terminals

[0465] Software: OpenAI's GPT-3 model, TextBlob library

[0466] Specific examples

[0467] For example, if a user enters an evaluation comment such as "Good job," the system processes it as follows:

[0468] 1. Input comment: "Good job"

[0469] 2. Specific evaluation comment: "Delivered high-quality deliverables within the project deadline."

[0470] 3. Improvement advice: "I hope to see similar results on your next project."

[0471] Example prompts to input to a generative AI model:

[0472] Please translate the following evaluation comments into specific, clear statements: Good job

[0473] In this way, a work evaluation feedback system installed in a factory robot is realized, which makes it possible to generate specific and clear evaluation comments and provide improvement advice that takes emotional factors into account.

[0474] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0475] Step 1:

[0476] The user inputs an evaluation comment in the evaluation comment field. The input evaluation comment is sent to the server. For example, the comment "You did a good job" is input.

[0477] Step 2:

[0478] The server sends the received evaluation comments to an AI module, which uses natural language processing technology to analyze the evaluation comments and convert them into specific, clear comments. For example, a comment such as "You did a good job" can be converted into "You delivered a high-quality product within the project deadline."

[0479] Step 3:

[0480] The server sends the converted evaluation comments to the emotion engine, which identifies emotional elements contained in the evaluation comments. For example, it extracts positive emotions from the comment "You delivered high-quality deliverables within the project deadline."

[0481] Step 4:

[0482] The server generates improvement advice based on the results of the emotion engine. If the emotion engine identifies a positive emotion, the server generates improvement advice such as, "We expect similar results in your next project."

[0483] Step 5:

[0484] The server sends the converted evaluation comment and the generated improvement advice to the user terminal. The user terminal displays this information in the evaluation comment entry field. For example, an evaluation comment such as "You provided a high-quality deliverable within the project deadline" and improvement advice such as "We expect similar results in the next project" are displayed.

[0485] Step 6:

[0486] The user checks the displayed evaluation comments and improvement advice, and makes additional comments or corrections as necessary. The final evaluation comments and improvement advice are saved in the system.

[0487] Example 2

[0488] Next, a description will be given of Example 2 of Form 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."

[0489] Conventional evaluation comment systems have difficulty accurately analyzing user evaluation comments and providing specific improvement advice. Furthermore, they do not generate advice that takes user emotions into account, making it difficult to improve user satisfaction. Furthermore, converting evaluation comments and adding improvement advice is often done manually, making efficient operation difficult.

[0490] 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.

[0491] In this invention, the server includes: means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence; means for adding improvement advice comments from a third-party perspective in accordance with the specified style of the messaging application; means for analyzing user emotions based on the evaluation comments and using the results to convert the evaluation comments and generate improvement advice; means for providing a format for an evaluation comment entry field that implements these functions; means for analyzing the evaluation comments and generating specific improvement advice using a generation AI model; and means for adding the generated improvement advice to the evaluation comments. This automates the analysis of evaluation comments and the generation of improvement advice, making it possible to provide specific advice that takes user emotions into consideration.

[0492] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[0493] An "evaluation comment" is text that describes the feedback or opinion a user gives about a project or task.

[0494] A "messaging application" is software that enables users to send and receive text messages.

[0495] "Third-party perspective" refers to opinions and advice from a perspective other than that of the user who made the evaluation comment.

[0496] "Improvement advice" is a specific suggestion for improving the progress of a project or task, based on evaluation comments.

[0497] "Sentiment analysis" is the process of extracting and analyzing user emotions from text using natural language processing techniques.

[0498] A "generative AI model" is a model that uses artificial intelligence technology to generate new text and data.

[0499] The "evaluation comment entry field" is an interface for users to input evaluation comments.

[0500] "Natural language processing technology" is a technology that enables computers to understand, generate, and manipulate human language.

[0501] A "format" is a way of arranging data or information in a particular way or structure.

[0502] This invention is a system that analyzes evaluation comments entered by users and generates specific improvement advice. The system utilizes artificial intelligence, natural language processing technology, and generative AI models to accurately convert evaluation comments and provide advice that takes the user's emotions into consideration.

[0503] The server receives evaluation comments sent by users. The received comments are first sent to the evaluation comment analysis module. This module uses natural language processing technology (e.g., Python libraries such as spaCy and NLTK) to analyze the content of the evaluation comments. For example, it analyzes the comment "You delivered high-quality deliverables within the project deadline."

[0504] Next, the server uses an emotion engine to analyze the user's emotions from the evaluation comments. The emotion engine uses natural language processing technology to extract emotions from the comments. For example, it extracts the emotion "difficult" from the comment "This project was very difficult."

[0505] The server then uses a generative AI model (e.g., OpenAI's GPT-3) to generate improvement advice based on the evaluation comments and extracted sentiment, such as "We recommend assigning easier tasks to the next project."

[0506] The generated improvement advice is added to the evaluation comments, for example, "This project was very difficult. I recommend assigning easier tasks to the next project."

[0507] The server transmits the evaluation comment with the added improvement advice to the terminal. The terminal displays the result received from the server to the user. The user can check the evaluation comment with the added improvement advice.

[0508] As a concrete example, consider the case where a user enters an evaluation comment such as "This project was very difficult." The device sends this comment to the server. The server receives the comment and uses the evaluation comment analysis module to extract the keywords "project" and "difficult." The emotion engine then analyzes the emotion "difficult." The generative AI model generates improvement advice such as "We recommend assigning easier tasks to the user in the next project." The server adds this advice to the original comment and sends it to the device. The device then displays the result to the user: "This project was very difficult. We recommend assigning easier tasks to the user in the next project."

[0509] An example of a prompt to input to a generative AI model is as follows:

[0510] User review: "This project was very difficult."

[0511] Prompt for the generative AI model: "Based on the user's evaluation comments, generate specific improvement advice for the next project. Evaluation comment: 'This project was very difficult.'"

[0512] In this way, the system analyzes users' evaluation comments and provides specific advice for improvement.

[0513] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0514] Step 1:

[0515] The user inputs an evaluation comment.

[0516] A user uses a messaging application to enter a review of a project or task, for example, "This project was very difficult." The review becomes the starting point for the system.

[0517] Step 2:

[0518] The terminal transmits the evaluation comment to the server.

[0519] The device (user's smartphone or PC) sends the entered evaluation comments to the server. The HTTPS protocol is used for transmission to ensure data security. The input is the user's evaluation comments, and the output is the data sent to the server.

[0520] Step 3:

[0521] The server receives the rating comments.

[0522] The server receives the evaluation comments sent from the terminal. The received data is passed to the evaluation comment analysis module. The input is the evaluation comment sent from the terminal, and the output is the data transfer to the analysis module.

[0523] Step 4:

[0524] The server performs the analysis using the evaluation comment analysis module.

[0525] The server uses a rating comment analysis module to analyze the content of rating comments. This module uses natural language processing technology (e.g., Python libraries spaCy and NLTK) to understand the gist of the comment. For example, it analyzes the comment "You delivered high-quality deliverables within the project deadline." The input is the rating comment, and the output is the analysis result.

[0526] Step 5:

[0527] The server analyzes emotions using an emotion engine.

[0528] The server uses an emotion engine to analyze user emotions from the evaluation comments. The emotion engine uses natural language processing technology to extract emotions from comments. For example, it extracts the emotion "difficult" from the comment "This project was very difficult." The input is the evaluation comment, and the output is the extracted emotion data.

[0529] Step 6:

[0530] The server generates improvement advice using a generative AI model.

[0531] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate improvement advice based on the evaluation comments and extracted emotions. For example, it generates advice such as "It is recommended to assign easier tasks in the next project." The input is the evaluation comments and emotion data, and the output is the generated improvement advice.

[0532] Step 7:

[0533] Add the server-generated improvement advice to the evaluation comment.

[0534] The server adds the generated improvement advice to the original evaluation comment. For example, it might say, "This project was very difficult. I recommend assigning an easier task to the next project." The input is the generated improvement advice and the original evaluation comment, and the output is the evaluation comment with the added improvement advice.

[0535] Step 8:

[0536] The server sends the results to the terminal.

[0537] The server sends the evaluation comment with the added improvement advice to the terminal. The transmission is again via HTTPS. The input is the evaluation comment with the added improvement advice, and the output is the data sent to the terminal.

[0538] Step 9:

[0539] The terminal displays the results to the user.

[0540] The terminal displays the results received from the server to the user. The user can check the evaluation comments with added improvement advice. The input is the data received from the server, and the output is what is displayed to the user.

[0541] (Application example 2)

[0542] Next, a description will be given of Application Example 2 of Form 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."

[0543] Conventional evaluation comment systems have difficulty converting evaluation comments into concise, accurate, and specific comments, and are unable to provide improvement advice from a third-party perspective. It is also difficult to analyze user sentiment and generate improvement advice based on the results. This has led to problems such as a decline in the quality of evaluation comments and a lack of concrete guidelines for improvement.

[0544] 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.

[0545] In this invention, the server includes means for converting evaluation comments succinctly, accurately, and specifically by utilizing artificial intelligence, means for adding comments of improvement advice from a third-party perspective in accordance with the default style of the messenger app, and means for analyzing emotions based on the evaluation comments and generating improvement advice based on the results, thereby making it possible to improve the quality of evaluation comments and provide specific improvement advice.

[0546] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[0547] An "evaluation comment" is a piece of text that provides feedback or evaluation of a particular task or project.

[0548] "Converting in a concise, accurate, and specific manner" means converting evaluation comments into concise, accurate, and specific content.

[0549] A "messenger app" is application software for sending and receiving text messages and multimedia messages.

[0550] A "defined style" is a format or style that is established as a standard in a particular application or system.

[0551] A "third-party perspective" is an objective viewpoint from a position that is not directly involved when making an evaluation or giving advice.

[0552] "Improvement advice" is specific suggestions or advice for improving a particular task or project.

[0553] "Emotion analysis" means identifying a user's emotions from data such as text or voice, and evaluating the type and intensity of those emotions.

[0554] The "evaluation comment entry field" is an interface or form for inputting evaluation comments.

[0555] A "format" is a framework for organizing data or information according to a specific form or structure.

[0556] To implement this invention, it is necessary to build a system that converts evaluation comments succinctly, accurately, and specifically, and adds improvement advice from a third-party perspective. This system is realized using artificial intelligence, natural language processing technology, and a sentiment analysis engine.

[0557] System Configuration

[0558] The system consists of the following main components:

[0559] 1. Server: Converts evaluation comments, analyzes sentiment, and generates improvement advice.

[0560] 2. Terminal: Provides an interface for users to enter evaluation comments and receive improvement advice.

[0561] 3. Artificial intelligence: Convert evaluation comments into concise, accurate, and specific information.

[0562] 4. Natural language processing technology: Analyzes and converts evaluation comments.

[0563] 5. Sentiment analysis engine: Analyzes user sentiment from rating comments.

[0564] 6. Generative AI model: Generates improvement advice based on the prompt sentence.

[0565] Program processing

[0566] The server receives the evaluation comments entered by the user and performs the following processes:

[0567] 1. Sentiment analysis: Analyze the sentiment of the rating comments using a natural language processing library such as TextBlob.

[0568] 2. Prompt generation: Generate appropriate prompts based on the results of sentiment analysis.

[0569] 3. Improvement advice generation: Using the OpenAI API, specific improvement advice is generated from the generated prompt sentences.

[0570] Hardware and software used

[0571] Hardware: Smartphones, servers

[0572] Software: Python, OpenAI API, TextBlob

[0573] Specific examples

[0574] For example, if a user enters an evaluation comment such as "Delivered high-quality work within the project deadline," the system will process it as follows:

[0575] 1. Sentiment Analysis: Analyze the sentiment of the rating comments using TextBlob to detect positive sentiment.

[0576] 2. Prompt generation: Generate the following prompt: "Evaluation comments: You delivered a high-quality deliverable within the project deadline. This contains positive emotions. Please provide some advice on how to improve the next project."

[0577] 3. Generation of improvement advice: Using the OpenAI API, improvement advice such as "Why not consider a more efficient work flow for your next project?" is generated from the generated prompt text.

[0578] Prompt Sentence Examples

[0579] Evaluation comment: High quality deliverables delivered within the project deadline

[0580] It contains positive emotions and offers advice to make your next project even better.

[0581] In this way, it becomes possible to improve the quality of the evaluation comments and provide specific advice for improvement.

[0582] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0583] Step 1:

[0584] The user inputs an evaluation comment using a terminal, and the input evaluation comment is sent to the server.

[0585] Input: User-entered evaluation comments (e.g., "Delivered high-quality deliverables within the project deadline")

[0586] Output: Rating comments sent to the server

[0587] Step 2:

[0588] The server performs sentiment analysis on the received evaluation comments using TextBlob, which analyzes the sentiment of the evaluation comments and determines the type of sentiment (positive, negative, neutral).

[0589] Input: Evaluation comments (e.g., "Delivered high-quality deliverables within the project deadline")

[0590] Data Processing: Sentiment Analysis using TextBlob

[0591] Output: Sentiment analysis result (e.g., positive)

[0592] Step 3:

[0593] The server generates prompt sentences based on the results of emotion analysis, creating appropriate prompt sentences depending on the type of emotion.

[0594] Input: Sentiment analysis results (e.g., positive), evaluation comments

[0595] Data processing: Generate prompt sentences based on the sentiment analysis results and evaluation comments

[0596] Output: Generated prompt (e.g., "Evaluation comments: You delivered a high-quality deliverable within the project deadline. This contains positive emotions. Please provide some advice on how to improve on your next project.")

[0597] Step 4:

[0598] The server sends the generated prompt sentence to the OpenAI API, which generates specific improvement advice. The OpenAI API generates appropriate advice based on the prompt sentence.

[0599] Input: Generated prompt text

[0600] Data Calculation: Generate improvement advice from prompts using OpenAI API

[0601] Output: Generated improvement advice (e.g., "For your next project, why not consider a more efficient workflow?")

[0602] Step 5:

[0603] The server sends the generated improvement advice to the user's terminal, where the user can check the improvement advice.

[0604] Input: Generated improvement advice

[0605] Output: Improvement advice sent to the user's device

[0606] In this way, it becomes possible to improve the quality of the evaluation comments and provide specific advice for improvement.

[0607] Example 3

[0608] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0609] With conventional evaluation and comment systems, it is difficult to ensure the consistency, fairness, and transparency of comments written by users. Furthermore, there is a lack of a means to provide appropriate feedback on comments written by users, which can lead to a decline in the quality of comments. Furthermore, there is no system that analyzes user comments in real time and provides advice on improvement, which places a heavy burden on users.

[0610] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0611] In this invention, the server includes a means for providing an interface for users to write evaluation comments, a means for an artificial intelligence module to run on the interface and analyze the evaluation comments, and a means for generating improvement advice based on the analysis results and providing feedback to the user. This allows users to write evaluation comments in a consistent format, ensuring fairness and transparency of evaluations. Furthermore, real-time analysis and feedback reduces the burden on users and enables the quality of comments to be improved.

[0612] An "interface" is a means for providing a screen or input form for users to write evaluation comments.

[0613] The "artificial intelligence module" is a program that analyzes evaluation comments and generates improvement advice.

[0614] "Analysis" is the process of analyzing the content of evaluation comments written by users and understanding their emotions and intentions.

[0615] "Improvement advice" is a suggestion generated based on the analysis results to make the evaluation comments more specific and accurate.

[0616] "Feedback" is the process of returning analysis results and improvement advice to the user.

[0617] "Saving" means recording the final evaluation comments corrected by the user in a storage device such as a database.

[0618] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0619] The present invention provides a system that provides an interface for users to write evaluation comments and an artificial intelligence module operates on the interface. A specific embodiment of this system will be described below.

[0620] Hardware and software used

[0621] Hardware: Servers (e.g., cloud computing services)

[0622] software:

[0623] Artificial intelligence modules (e.g., generative AI models using natural language processing technology)

[0624] Additional modules for improvement advice (e.g. custom scripts)

[0625] Emotion engines (e.g., emotion analysis tools)

[0626] Specific operation of the system

[0627] Subject: Server

[0628] The server provides an interface for users to write evaluation comments. This interface can be accessed through a web browser or a dedicated application. When a user accesses the interface, the server displays a text box for inputting evaluation comments.

[0629] Subject: User

[0630] The user uses the provided interface to enter a review comment, for example, "This product is very easy to use and has a great design. However, if only the battery life was a little longer, it would be perfect."

[0631] Subject: Server

[0632] The server receives user-entered evaluation comments, temporarily stores them in a database, and then analyzes the comments in real time using an emotion engine. The analysis results include the emotional tone of the comments and their positive and negative aspects.

[0633] The server then uses the generative AI model to generate improvement advice based on the analysis results, such as "It would be a good idea to emphasize the positive aspects and add specific suggestions for improving battery life."

[0634] The generated improvement advice is fed back to the user. The user then modifies their evaluation comment based on the feedback from the server. For example, they might modify their comment to say, "This product is very easy to use and has a great design. It would be even better if the battery life was a little longer."

[0635] Finally, the server stores the user-modified rating comments in a database for future reference and analysis.

[0636] Specific examples

[0637] Example prompts to input to the generative AI model

[0638] Please write an evaluation comment about your experience using this product. Please include specific usage scenarios and your impressions.

[0639] This system allows users to write evaluation comments in a consistent format, ensuring fairness and transparency of evaluations. Real-time analysis and feedback also reduces the burden on users and improves the quality of comments. The flow of the identification process in Example 3 will be described with reference to FIG. 21.

[0640] Step 1:

[0641] The user accesses the evaluation comment writing interface.

[0642] Input: URL or application launch to access the interface through a web browser or dedicated application.

[0643] Output: A text box will appear for you to enter your rating comments.

[0644] Specific operation: The user opens a web browser and accesses the specified URL or launches a dedicated application. The server then displays the evaluation comment entry interface on the user's device.

[0645] Step 2:

[0646] The user inputs an evaluation comment.

[0647] Input: Enter your evaluation comment in the text box.

[0648] Output: The entered evaluation comments are displayed on the interface.

[0649] What it does: The user enters their review in a text box on the interface. For example, they might write, "This product is very easy to use and has a great design. However, if only the battery life was a little longer, it would be perfect."

[0650] Step 3:

[0651] The server receives the entered comment.

[0652] Input: The rating comment entered by the user.

[0653] Output: Received comments are temporarily stored in a database.

[0654] Specific operation: The server receives the evaluation comments entered by the user and temporarily stores them in a database.

[0655] Step 4:

[0656] The server analyzes the comments using an emotion engine.

[0657] Input: The received rating comment.

[0658] Output: Analysis results including the emotional tone of the comments and whether they are positive or negative.

[0659] Specific operation: The server calls the emotion engine to analyze the received evaluation comments. The analysis results include the emotional tone of the comments and their positive and negative elements.

[0660] Step 5:

[0661] The server generates improvement advice based on the analysis results.

[0662] Input: Analysis results from the emotion engine.

[0663] Output: Improvement advice.

[0664] Specific operation: The server uses the generative AI model to generate improvement advice based on the analysis results. For example, it generates advice such as, "It would be a good idea to emphasize the positive aspects and add specific improvement suggestions for battery life."

[0665] Step 6:

[0666] The server generates improvement advice and feeds it back to the user.

[0667] Input: Improvement advice.

[0668] Output: Feedback displayed to the user in the interface.

[0669] Specific operation: The server generates improvement advice and provides it to the user as feedback. The feedback is displayed on the interface.

[0670] Step 7:

[0671] The user edits the comment based on the feedback.

[0672] Input: Feedback from the server.

[0673] Output: The revised rating comment.

[0674] Specific behavior: The user modifies the evaluation comment based on the feedback from the server. For example, the user might modify the comment to say, "This product is very easy to use and has a great design. It would be even better if the battery life was a little longer."

[0675] Step 8:

[0676] The server stores the final evaluation comments.

[0677] Input: The revised rating comment.

[0678] Output: The final evaluation comments stored in the database.

[0679] What happens: The server saves the final user-modified evaluation comments in a database for future reference and analysis.

[0680] (Application example 3)

[0681] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0682] In conventional evaluation and comment systems, the comments written by users are often subjective and lack specificity and fairness. Furthermore, there is a lack of advice on how to improve the comments written by users from a third-party perspective, resulting in low transparency of the evaluations. Furthermore, when users enter product reviews, they do not receive real-time feedback, which can lead to a decline in the quality of the reviews. A system that can solve these issues is needed.

[0683] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0684] In this invention, the server includes a means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, a means for analyzing user input in real time using a sentiment analysis engine, and a means for generating advice for improving the evaluation comments using a generative AI model. This makes it possible to improve the quality of evaluation comments written by users and maintain fairness and transparency. In addition, when users enter product reviews, they can receive feedback in real time, further improving the quality of the reviews.

[0685] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[0686] An "emotion analysis engine" is a technology that analyzes emotions and the intensity of emotions from text data and determines the emotional state, such as positive, negative, or neutral.

[0687] A "generative AI model" is a type of artificial intelligence that generates new text or information based on given input data, and is a technique used particularly in natural language processing.

[0688] The "evaluation comment entry field format" is an interface for users to input evaluation comments, and has a structure that allows artificial intelligence and sentiment analysis engines to operate.

[0689] An "interface" is a means by which a user interacts with a system, and includes a screen and operating method for input and output.

[0690] "Natural language processing technology" is a technology that enables computers to understand, generate, and manipulate human language, and includes functions such as text analysis, generation, and translation.

[0691] The system for implementing this invention mainly comprises a server, a user terminal, and an interface. Each component and its operation will be described in detail below.

[0692] server

[0693] The server is the main component for running the artificial intelligence, sentiment analysis engine, and generative AI models. The server has the following functions:

[0694] 1. Artificial Intelligence: Convert user-entered evaluation comments concisely, accurately, and specifically. Using natural language processing technology, the input text is analyzed and converted into an appropriate format.

[0695] 2. Sentiment Analysis Engine: Analyzes user input in real time to determine the emotional state, such as positive, negative, or neutral, to understand the user's emotions and provide appropriate feedback.

[0696] 3. Generative AI model: Generates improvement advice for evaluation comments based on user input. The generative AI model is implemented using OpenAI's API.

[0697] User terminal

[0698] The user device is a device such as a smartphone or tablet that provides an interface for users to enter evaluation comments. The user device has the following functions:

[0699] 1. Interface: Provides a screen for users to enter their evaluation comments. This interface sends the text entered by the user to the server, allowing users to receive feedback in real time.

[0700] Interface

[0701] The interface is a means for users to enter rating comments and receive feedback from the server. The interface has the following features:

[0702] 1. Input field: Provides a text box for users to enter their evaluation comments.

[0703] 2. Real-time feedback: As users provide input, the sentiment analysis engine and generative AI model work together to provide real-time feedback.

[0704] Specific examples

[0705] For example, if a user enters an evaluation comment such as "This product is very easy to use, but the battery life is poor," the sentiment analysis engine analyzes this comment and calculates its positivity and subjectivity.The generative AI model then generates advice to improve this comment.

[0706] Prompt Sentence Examples

[0707] Please offer suggestions to improve the following review: This product is very easy to use, but the battery life is poor.

[0708] In this way, a system is realized that can improve the quality of evaluation comments written by users and maintain fairness and transparency.

[0709] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0710] Step 1:

[0711] The user inputs an evaluation comment through the terminal interface.

[0712] Input: User-entered evaluation comments (e.g., "This product is very easy to use, but the battery life is poor.")

[0713] Output: The entered evaluation comments are sent from the terminal to the server.

[0714] Step 2:

[0715] The server passes the received evaluation comments to the sentiment analysis engine, which performs sentiment analysis in real time.

[0716] Input: Rating comment sent from the device

[0717] Data processing: The sentiment analysis engine analyzes the text and calculates positivity and subjectivity.

[0718] Output: Sentiment analysis result (e.g., positivity 0.5, subjectivity 0.6)

[0719] Step 3:

[0720] Based on the results of the emotion analysis, the server generates prompt sentences for the generative AI model and generates advice for improving the evaluation comments.

[0721] Input: Sentiment analysis results and evaluation comments

[0722] Data processing: The generative AI model generates prompt sentences and generates improvement advice using the OpenAI API.

[0723] Output: Generated improvement advice (e.g., "Regarding the poor battery life, please provide specific usage time and circumstances, which will be helpful for other users.")

[0724] Step 4:

[0725] The server transmits the generated improvement advice to the terminal and provides feedback to the user.

[0726] Input: Generated improvement advice

[0727] Output: Improvement advice displayed on the terminal

[0728] Step 5:

[0729] The user modifies the evaluation comment by referring to the improvement advice through the terminal interface.

[0730] Input: Evaluation comments from users who received improvement advice

[0731] Output: The modified rating comment is resubmitted from the device to the server.

[0732] Step 6:

[0733] The server finally stores the modified evaluation comments and makes them available for other users to view.

[0734] Input: Revised rating comment

[0735] Output: The saved evaluation comments are stored in a database and can be viewed by other users.

[0736] 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.

[0737] 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> ) 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.

[0738] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0739] 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.

[0740] [Second embodiment]

[0741] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0742] 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.

[0743] 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).

[0744] 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.

[0745] 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.

[0746] 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).

[0747] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0753] "Example 1"

[0754] In one embodiment of the present invention, an artificial intelligence module is provided for converting evaluation comments into concise, accurate, and specific ones. This module uses natural language processing technology to analyze input evaluation comments and convert them into more specific and clear forms. For example, an abstract evaluation comment such as "You did a good job" is converted into a concrete evaluation comment such as "You delivered a high-quality deliverable within the project deadline."

[0755] "Example 2"

[0756] There is also a module that adds comments with advice for improvement from a third-party perspective, in line with the messaging app's default style. This module generates specific advice for improvement based on the evaluation comments and adds it to the evaluation comments. For example, in response to the evaluation comment "You delivered high-quality deliverables within the project deadline," the module adds the advice "For the next project, why not consider creating a more efficient workflow?"

[0757] "Example 3"

[0758] Furthermore, a module for providing a format for the evaluation comment field is also provided. This module provides an interface for users to write evaluation comments, and the aforementioned artificial intelligence module and improvement advice addition module operate on this interface. This allows users to write evaluation comments in a consistent format, maintaining the fairness and transparency of evaluations.

[0759] The processing flow of each embodiment will be described below.

[0760] "Example 1"

[0761] Step 1: The user enters their evaluation comments into the system.

[0762] Step 2: The entered evaluation comments are sent to the artificial intelligence module.

[0763] Step 3: The AI ​​module uses natural language processing technology to analyze the evaluation comments and convert them into more specific and clearer forms, such as converting an abstract evaluation comment like "You did a good job" into a concrete evaluation comment like "You delivered high-quality deliverables within the project deadline."

[0764] Step 4: The converted rating comments are displayed to the user.

[0765] "Example 2"

[0766] Step 1: The user enters their evaluation comments into the system.

[0767] Step 2: The entered evaluation comments are sent to the improvement advice addition module.

[0768] Step 3: The improvement advice addition module generates specific improvement advice based on the evaluation comments and adds it to the evaluation comments. For example, in response to the evaluation comment "You delivered high-quality deliverables within the project deadline," the improvement advice added is "In the next project, why not consider a more efficient work flow?"

[0769] Step 4: The evaluation comment with the added improvement advice is displayed to the user.

[0770] "Example 3"

[0771] Step 1: The user launches a module that provides a format for the evaluation comment field.

[0772] Step 2: The module provides an interface for users to write evaluation comments.

[0773] Step 3: The user enters the evaluation comments into the interface.

[0774] Step 4: The aforementioned AI module and improvement advice addition module are activated to ensure consistency and fairness in the evaluation comments.

[0775] Example 1

[0776] Next, a description will be given of Example 1 of Form 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."

[0777] Conventional evaluation comments are abstract, making it difficult to provide specific feedback. It is also difficult to provide evaluation comments as improvement advice from a third-party perspective. This makes it difficult for the person being evaluated to understand specific areas for improvement, potentially resulting in missed growth opportunities.

[0778] 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.

[0779] In this invention, the server includes means for a user to input an evaluation comment, means for a terminal to transmit the input evaluation comment to the server, means for the server to receive the evaluation comment and analyze it using natural language processing technology, means for the server to generate a prompt sentence to input the analysis result to the generative AI model, means for the server to input the prompt sentence to the generative AI model and generate a specific evaluation comment, means for the server to transmit the generated specific evaluation comment to the terminal, means for the terminal to display the specific evaluation comment to the user, and means for providing a format for an evaluation comment entry field that implements these functions. This makes it possible to convert evaluation comments into specific and clear information and provide useful feedback to users.

[0780] A "user" is an individual or group that uses the system to input evaluation comments.

[0781] A "terminal" is a device through which a user inputs evaluation comments and communicates with a server.

[0782] The "server" is a computer system that receives and analyzes evaluation comments and generates specific evaluation comments using a generative AI model.

[0783] An "evaluation comment" is a feedback or evaluation text entered by a user.

[0784] "Natural language processing technology" is a technology for analyzing evaluation comments and extracting grammatical structures and keywords.

[0785] A "generative AI model" is an artificial intelligence model that generates specific evaluation comments based on analyzed evaluation comments.

[0786] A "prompt sentence" is an instruction sentence to be input into a generative AI model.

[0787] The "format of the evaluation comment entry field" is a format that provides an interface for the user to input evaluation comments.

[0788] This invention is a system for converting evaluation comments specifically and clearly. The program processing of this system will be specifically explained below.

[0789] First, the user inputs an evaluation comment using a terminal. The terminal then sends the evaluation comment to the server. The server then analyzes the received evaluation comment using natural language processing technology. This analysis uses natural language processing libraries such as "spaCy" and "NLTK."

[0790] Next, the server generates a prompt sentence to be input into the generative AI model based on the analysis results. For example, "GPT-4" is used as the generative AI model. An example of a prompt sentence is "Please convert the following abstract evaluation comment into a concrete evaluation comment: 'Good job'."

[0791] The server inputs the generated prompt into the generative AI model to generate a specific evaluation comment. Based on the prompt, the generative AI model outputs a specific evaluation comment such as "A high-quality deliverable was delivered within the project deadline."

[0792] The server then transmits the generated specific evaluation comment to the terminal, and the terminal displays the received specific evaluation comment to the user. For example, a comment such as "You provided a high-quality deliverable within the project deadline" is displayed on the user's screen.

[0793] As a concrete example, consider the case where a user inputs an evaluation comment such as "Good job." This comment is sent by the device to the server, which analyzes it using natural language processing technology. Based on the analysis results, the server generates a prompt saying, "Please convert the following abstract evaluation comment into a concrete evaluation comment: 'Good job'." The prompt is then input into a generative AI model, which generates a concrete evaluation comment: "You delivered a high-quality deliverable within the project deadline." The server then sends this concrete evaluation comment to the device, which displays it to the user.

[0794] In this way, it is possible to convert evaluation comments into specific and clear comments and provide useful feedback to users.

[0795] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0796] Step 1:

[0797] The user inputs an evaluation comment.

[0798] The user inputs an evaluation comment through the device interface, for example, by inputting "good job" in the text box. The input evaluation comment is temporarily stored in the device memory.

[0799] Step 2:

[0800] The terminal transmits the input evaluation comment to the server.

[0801] The terminal sends the evaluation comment entered by the user to the server as an HTTP request. At this time, the evaluation comment is packaged in JSON format. The input is the evaluation comment "Good job" and the output is an HTTP request to the server.

[0802] Step 3:

[0803] The server receives the evaluation comments and analyzes them using natural language processing technology.

[0804] The server analyzes the received evaluation comments using a natural language processing library (e.g., spaCy or NLTK). The analysis includes extracting the grammatical structure and keywords of the evaluation comments. The input is the evaluation comment "Good job," and the output is the analysis results (grammatical structure and keywords).

[0805] Step 4:

[0806] The server generates a prompt sentence to input the analysis results into the AI ​​model.

[0807] The server generates a prompt sentence to be input to the generative AI model based on the analysis results. For example, it generates a prompt sentence such as "Please convert the following abstract evaluation comment into a concrete evaluation comment: 'Good job'." The input is the analysis result, and the output is the prompt sentence.

[0808] Step 5:

[0809] The server inputs a prompt sentence into the generative AI model and generates a specific evaluation comment.

[0810] The server inputs the generated prompt into a generative AI model (e.g., GPT-4) to generate a specific evaluation comment. Based on the prompt, the generative AI model outputs a specific evaluation comment such as "You provided a high-quality deliverable within the project deadline." The input is the prompt, and the output is a specific evaluation comment.

[0811] Step 6:

[0812] The server transmits the generated specific evaluation comments to the terminal.

[0813] The server sends the generated specific evaluation comments to the terminal as an HTTP response. At this time, the evaluation comments are packaged again in JSON format. The input is the specific evaluation comments, and the output is the HTTP response to the terminal.

[0814] Step 7:

[0815] The terminal displays specific evaluation comments to the user.

[0816] The terminal displays the received specific evaluation comments to the user. For example, a comment such as "You provided a high-quality deliverable within the project deadline" is displayed on the user's screen. The input is the specific evaluation comment, and the output is the display to the user.

[0817] (Application example 1)

[0818] Next, a description will be given of Application Example 1 of Form 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."

[0819] Previous evaluation comments were abstract, making it difficult to convey specific details. Furthermore, in factory work evaluations, managers' evaluations of robots lacked specificity, making it difficult to accurately convey the evaluation details. This led to problems such as a decrease in the transparency and reliability of the evaluations, making it difficult to identify areas for improvement.

[0820] 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.

[0821] In this invention, the server includes means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, means for adding comments of improvement advice from a third-party perspective in accordance with the default style of the messenger app, means for using a generative AI model for converting evaluation comments into a specific form, and means for providing an interface for converting in-factory work evaluation comments into a specific form. As a result, evaluation comments are converted into a specific and clear form, and in-factory work evaluations can be accurately communicated.

[0822] "Artificial intelligence" is the technology that enables computer systems to learn, reason, and self-correct by imitating human intelligence.

[0823] An "evaluation comment" is written feedback given in response to a specific action or achievement.

[0824] "Converting succinctly, accurately, and specifically" means converting abstract evaluation comments into concise, accurate, and detailed content.

[0825] A "messenger app" is a software application for sending and receiving text and multimedia messages.

[0826] "Adding comments offering advice on improvement from a third-party perspective" means adding comments to the evaluation comments that point out areas for improvement from an objective point of view.

[0827] A "generative AI model" is a machine learning model that is trained by an artificial intelligence to perform a specific task.

[0828] An "interface" is the means or method by which a user interacts with a system.

[0829] The "format of the evaluation comment entry field" refers to a standard format or layout for inputting and displaying evaluation comments.

[0830] To put the present invention into practice, it is necessary to build a system for converting evaluation comments into concrete terms. This system includes a program that utilizes artificial intelligence to convert evaluation comments succinctly, accurately, and concretely.

[0831] The server first receives the evaluation comment entered by the user. This evaluation comment is often abstract, such as "You did a good job." The server then analyzes the evaluation comment using natural language processing technology and converts it into concrete content. At this time, it uses a generative AI model to generate prompt sentences that convert the evaluation comment into a concrete form.

[0832] Specifically, the server generates a prompt like this:

[0833] Please translate the following evaluation comments into specific, clear statements: Good job

[0834] This prompt is then input into the generative AI model to obtain a specific evaluation comment, such as "The parts were assembled within the specified time and met the quality standards."

[0835] The server then formats these specific evaluation comments to match the messaging app's default style and adds third-party advice for improvement, such as "Next time, please consider revising your work procedures to improve efficiency."

[0836] The specific evaluation comments and improvement advice generated in this way are sent to the user's device and displayed in the evaluation comment section. Through this interface, users can check the specific and clear evaluation comments and identify areas for improvement as needed.

[0837] By implementing this system, evaluation comments can be converted into specific and clear forms, enabling work evaluations to be accurately communicated within the factory. This improves the transparency and reliability of evaluations and makes it easier to identify areas for improvement.

[0838] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0839] Step 1:

[0840] The user inputs an evaluation comment.

[0841] Input: The user inputs an evaluation comment through the terminal.

[0842] Output: The entered evaluation comments are sent to the server.

[0843] Specific operation: The user uses the terminal interface to input an evaluation comment, such as "Good job." The input comment is sent to the server.

[0844] Step 2:

[0845] The server receives the evaluation comments and analyzes them using natural language processing technology.

[0846] Input: Rating comment submitted by user.

[0847] Output: Structured data of parsed rating comments.

[0848] Specific operation: The server analyzes the received evaluation comments using natural language processing techniques (e.g., morphological analysis and grammatical analysis) and generates structured data to understand the meaning and context of the evaluation comments.

[0849] Step 3:

[0850] The server uses a generative AI model to generate prompts that convert the evaluation comments into concrete forms.

[0851] Input: Parsed structured data of rating comments.

[0852] Output: The generated prompt statement.

[0853] Specific action: Based on the parsed evaluation comments, the server generates a prompt sentence such as the following: "Please convert the following evaluation comments into a specific and clear form: Good job."

[0854] Step 4:

[0855] The server inputs a prompt sentence into the generative AI model and obtains specific evaluation comments.

[0856] Input: The generated prompt statement.

[0857] Output: Specific evaluation comments.

[0858] Specific operation: The server inputs the prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) to generate a specific evaluation comment, such as "The parts assembly was completed within the specified time and met the quality standards."

[0859] Step 5:

[0860] The server formats specific evaluation comments according to the messenger app's standard style and adds comments offering advice on improvement from a third-party perspective.

[0861] Input: Specific evaluation comments.

[0862] Output: Formatted evaluation comments and improvement advice.

[0863] Specific actions: The server formats the specific evaluation comment to match the messaging app's default style and adds improvement advice, such as "Next time, please consider revising your work procedures to be more efficient."

[0864] Step 6:

[0865] The server sends the formatted evaluation comments and improvement advice to the user's terminal.

[0866] Input: Formatted evaluation comments and improvement suggestions.

[0867] Output: Evaluation comments and improvement advice displayed on the user's device.

[0868] Specific operation: The server sends the formatted evaluation comments and improvement advice to the user's device, and the user can check them through the device interface.

[0869] Example 2

[0870] Next, a description will be given of Example 2 of Form 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."

[0871] In conventional evaluation comment systems, evaluation comments are often abstract and lack specificity, making it difficult for the recipient to clearly understand how to improve. Furthermore, there is a lack of a way to add specific improvement advice to evaluation comments, which leads to a problem of reduced feedback quality. Furthermore, the evaluation comment format is not standardized, which can lead to a lack of consistency in the comments.

[0872] 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.

[0873] In this invention, the server includes: a means for a user to input an evaluation comment; a means for a terminal to send the evaluation comment to the server; a means for the server to receive the evaluation comment and perform text analysis; a means for the server to input the analysis results into a generative AI model and generate improvement advice; a means for the server to add the generated improvement advice to the original evaluation comment; a means for the server to return the final comment to the terminal; a means for the terminal to display the final comment to the user; and a means for providing a format for an evaluation comment entry field that implements these functions. This makes it possible to add specific improvement advice to evaluation comments, thereby improving the quality of feedback. Furthermore, by standardizing the evaluation comment format, consistent comments can be provided.

[0874] A "user" is an individual or group that uses the system to input evaluation comments.

[0875] A "terminal" is a device through which a user inputs evaluation comments and communicates with a server.

[0876] The "server" is a computer system that receives and analyzes evaluation comments, generates improvement advice using a generative AI model, and returns the final comments to the terminal.

[0877] An "evaluation comment" refers to the content of feedback entered by a user, and is text that includes an evaluation of a project or work.

[0878] "Text analysis" is an analytical process using natural language processing technology that the server performs to understand the content of the evaluation comments.

[0879] A "generative AI model" is an artificial intelligence model that generates specific improvement advice based on evaluation comments.

[0880] "Improvement advice" refers to specific improvements or suggestions that are added to the evaluation comments.

[0881] The "evaluation comment entry field format" is a unified interface for users to input evaluation comments and for the server to return the final comments.

[0882] This invention is a system that allows users to input evaluation comments and adds specific improvement advice to them. This system is composed of three main elements: the user, the terminal, and the server.

[0883] First, the user inputs an evaluation comment. The terminal used by the user provides an interface for inputting the evaluation comment. This interface has a standardized format for the evaluation comment entry field, making it easy for the user to input the evaluation comment.

[0884] The terminal then transmits the evaluation comments entered by the user to the server, which uses natural language processing technology to analyze the received evaluation comments. Through this analysis, the content of the evaluation comments is understood.

[0885] The server inputs the analysis results into a generative AI model. For example, OpenAI's GPT-4 is used for this generative AI model. The generative AI model generates specific improvement advice based on the input evaluation comments. The generated improvement advice is added to the evaluation comments.

[0886] As a concrete example, suppose a user enters the following rating comment:

[0887] "We delivered high-quality deliverables within the project deadline."

[0888] The server parses this comment and inputs the following prompt into the generative AI model:

[0889] "Evaluation comment: High-quality deliverables were delivered within the project deadline. Please add any suggestions for improvement."

[0890] The generative AI model generates improvement advice such as:

[0891] "Why not consider a more efficient workflow for your next project?"

[0892] The server adds this improvement advice to the original rating comment to generate the final comment:

[0893] "We delivered high-quality deliverables within the project deadline. Why not consider a more efficient workflow for the next project?"

[0894] The final comments are sent back from the server to the terminal, which then displays them to the user, who can then check the evaluation comments with the added advice for improvement.

[0895] This system allows users to add specific advice for improvement to evaluation comments, improving the quality of feedback. Also, by standardizing the format of evaluation comments, users can provide consistent comments.

[0896] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0897] Step 1:

[0898] The user inputs an evaluation comment.

[0899] The user enters a review comment in the review comment input field of the messenger app. For example, the user might enter "They provided high-quality deliverables within the project deadline." The review comment is then sent to the device.

[0900] Step 2:

[0901] The terminal transmits the evaluation comment to the server.

[0902] The terminal transmits the evaluation comments entered by the user to the server in an appropriate format. The input is the evaluation comments, and the output is the data to be sent to the server.

[0903] Step 3:

[0904] The server receives the evaluation comments and performs text analysis.

[0905] The server receives the evaluation comments sent from the terminal. After receiving the evaluation comments, the server performs text analysis using natural language processing technology to understand the content of the evaluation comments. The input is the evaluation comments, and the output is the analysis results.

[0906] Step 4:

[0907] The server inputs the analysis results into a generative AI model to generate improvement advice.

[0908] The server inputs the analysis results into a generative AI model (e.g., GPT-4). The generative AI model generates specific improvement advice based on the input evaluation comments. The input is the analysis results, and the output is improvement advice.

[0909] Step 5:

[0910] The server adds the generated improvement advice to the original evaluation comment.

[0911] The server adds the improvement advice obtained from the generative AI model to the original evaluation comment. This results in an evaluation comment that reads, "You delivered a high-quality deliverable within the project deadline. For the next project, we suggest you consider a more efficient workflow." The input is the improvement advice and the original evaluation comment, and the output is the final comment.

[0912] Step 6:

[0913] The server sends the final comment back to the terminal.

[0914] The server returns the final comment to the terminal, sending it in the appropriate format. The input is the final comment, and the output is the data sent to the terminal.

[0915] Step 7:

[0916] The terminal displays the final comment to the user.

[0917] The terminal displays the final comments received from the server to the user. The user can check the evaluation comments to which improvement advice has been added. The input is the final comments, and the output is the display data for the user.

[0918] (Application example 2)

[0919] Next, a description will be given of Application Example 2 of Form 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."

[0920] In order to improve work efficiency in factories, it is important to provide specific improvement advice based on the evaluation comments of workers and robots. However, the current system does not efficiently collect evaluation comments, generate appropriate improvement advice, and notify it to workers and managers. This poses the issue of not achieving sufficient improvements in work efficiency.

[0921] 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.

[0922] In this invention, the server includes means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, means for adding improvement advice comments from a third-party perspective in accordance with the default style of the messenger app, means for collecting evaluation comments from workers and robots in the factory, means for generating specific improvement advice using a generative AI model based on the collected evaluation comments, means for notifying workers and managers of the generated improvement advice, and means for providing a format for an evaluation comment entry field that implements these functions. This makes it possible to efficiently carry out the process from collecting evaluation comments to generating and notifying improvement advice, thereby improving work efficiency in the factory.

[0923] "Artificial intelligence" is the technology that enables computer systems to learn, reason, and self-correct by imitating human intelligence.

[0924] An "evaluation comment" is a sentence that describes an evaluation of the work of a worker or robot.

[0925] A "messenger app" is application software for sending and receiving text messages and multimedia messages.

[0926] A "third-party perspective" refers to an objective viewpoint other than that of the evaluator or the person being evaluated.

[0927] "Improvement advice" is a specific proposal for improving the efficiency and quality of work based on the evaluation comments.

[0928] "In-plant" means the interior of a facility where manufacturing operations take place.

[0929] "Workers" refers to personnel who perform manufacturing work within a factory.

[0930] A "robot" is a mechanical device that performs tasks automatically according to programmed instructions.

[0931] A "generative AI model" is a model that uses artificial intelligence technology to generate text and data.

[0932] "Notification" is the act of conveying information to a specific recipient.

[0933] The "evaluation comment entry field" is an interface for inputting and displaying evaluation comments.

[0934] A "format" is a framework for organizing and arranging data or information in a particular way.

[0935] A system for implementing this invention is configured as follows: First, the server uses artificial intelligence to convert evaluation comments into concise, accurate, and specific ones. Next, it adds improvement advice comments from a third-party perspective in accordance with the default style of the messenger app. Furthermore, it collects evaluation comments from workers and robots in the factory and generates specific improvement advice using a generative AI model based on the collected evaluation comments. Finally, it notifies the generated improvement advice to workers and managers.

[0936] Hardware and software used

[0937] Hardware: Servers, smartphones, tablets, factory computers

[0938] Software: Python 3.x, OpenAI API, messenger app

[0939] Data processing and calculation

[0940] The server first collects evaluation comments from workers and robots in the factory. These evaluation comments are sent to the server in text format. The server then analyzes the collected evaluation comments using natural language processing technology and generates specific improvement advice using a generative AI model (OpenAI's GPT-3). This generated improvement advice is added to the evaluation comments and ultimately notified to workers and managers.

[0941] Specific examples

[0942] For example, if evaluation comments are collected that Robot A quickly assembled parts in a factory, the server inputs the following prompt sentence into the generative AI model:

[0943] Prompt Sentence Examples

[0944] Evaluation comments: Robot A assembled the parts quickly.

[0945] Improvement advice:

[0946] The generative AI model generates specific improvement advice based on this prompt. For example, it might generate advice such as, "Next time, consider optimizing the placement of parts to further increase efficiency." This advice is added to the evaluation comments and notified to the worker or manager via smartphone or tablet.

[0947] In this way, the process from collecting evaluation comments to generating and notifying improvement advice can be carried out efficiently, making it possible to improve work efficiency within the factory.

[0948] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0949] Step 1:

[0950] The server collects evaluation comments from workers and robots in the factory.

[0951] Input: Evaluation comments from workers and robots (text format)

[0952] Output: Collected evaluation comments

[0953] Specific operation: A worker or a robot inputs an evaluation comment, which is sent to the server, which stores it in a database.

[0954] Step 2:

[0955] The server analyzes the collected evaluation comments using natural language processing technology.

[0956] Input: Collected evaluation comments

[0957] Output: Parsed rating comments

[0958] Specific operation: The server passes the evaluation comments to a text analysis engine to analyze grammar and semantics. The analysis results are used as part of the prompt sentence to input to the generative AI model.

[0959] Step 3:

[0960] The server generates specific improvement advice using a generative AI model based on the analyzed evaluation comments.

[0961] Input: Parsed rating comments

[0962] Output: Generated improvement advice

[0963] Specific operation: The server inputs the analyzed evaluation comments as prompt sentences into the generative AI model, which then generates specific improvement advice based on the prompt sentences.

[0964] Step 4:

[0965] The server adds the generated improvement advice to the evaluation comment.

[0966] Input: Generated improvement advice, evaluation comments

[0967] Output: Evaluation comment with improvement advice added

[0968] Specific behavior: The server appends the generated improvement advice to the original rating comment and formats it as a complete rating comment.

[0969] Step 5:

[0970] The server notifies the worker or manager of the evaluation comment with the added improvement advice.

[0971] Input: Evaluation comment with improvement advice added

[0972] Output: Notification to workers and managers

[0973] Specific operation: The server sends the evaluation comments with additional improvement advice to the worker or manager via a messenger app or notification system. The notification is displayed on the worker's smartphone or tablet.

[0974] Example 3

[0975] Next, a description will be given of Example 3 of Form Example 3. 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."

[0976] In conventional evaluation and comment systems, the evaluation comments written by users were often inconsistent, and specific improvement advice was often not provided. Furthermore, the analysis of evaluation comments and the generation of improvement advice were done manually, which was time-consuming and labor-intensive. This resulted in issues such as a lack of fairness and transparency in evaluations and a decline in user satisfaction.

[0977] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0978] In this invention, the server includes means for providing an interface for users to write evaluation comments, means for analyzing the evaluation comments using artificial intelligence on the interface and generating improvement advice, and means for presenting the generated improvement advice to the user, thereby improving the consistency and specificity of the evaluation comments and maintaining the fairness and transparency of the evaluations.

[0979] "User" means an individual or organization that uses the system to post evaluation comments and receive advice on improvements.

[0980] An "interface" is the screen or application operating part that allows users to input and submit evaluation comments.

[0981] "Artificial intelligence" refers to the machine learning models and algorithms used to analyze evaluation comments and generate improvement advice.

[0982] "Evaluation comments" are feedback and opinions written by users about products and services.

[0983] "Improvement advice" is specific suggestions and feedback generated by artificial intelligence by analyzing evaluation comments.

[0984] The "server" is a computer system that receives evaluation comments from users, analyzes them using artificial intelligence, and generates improvement advice.

[0985] "Format" refers to the consistent format and layout of the evaluation comment field, and is a structure that makes it easy for users to write evaluation comments.

[0986] "Natural language processing technology" is a technology used by artificial intelligence to analyze evaluation comments, and is a method for understanding text data and extracting meaning.

[0987] The present invention is a system that allows users to write evaluation comments, analyzes the comments using artificial intelligence, and generates specific advice for improvement. Specific embodiments of this system are described below.

[0988] Hardware and software used

[0989] Hardware: Servers, devices (PCs, smartphones, tablets, etc.)

[0990] Software: Generative AI model, evaluation comment writing module, improvement advice addition module

[0991] System configuration

[0992] 1. User Interface

[0993] The user accesses a web page or application provided by the evaluation comment writing module using a terminal. This interface includes UI elements such as a text box for inputting evaluation comments and a submit button.

[0994] 2. Enter and submit your evaluation comments

[0995] The user enters their review comments in a text box on the interface, for example, "This product is easy to use, but the battery life is poor." Once they are done, they click the "Submit" button.

[0996] 3. Receipt of rating comments by the server

[0997] The evaluation comments sent from the device are sent to the server, which receives the comments and stores them in a database.

[0998] 4. Analysis using generative AI models

[0999] The server passes the saved evaluation comments to a generative AI model for analysis, which uses natural language processing technology to understand the content of the comments.

[1000] 5. Generating Improvement Advice

[1001] Based on the analysis results of the generative AI model, the server calls the improvement advice addition module and generates specific improvement advice, such as "To extend battery life, consider improving the following: 1. Increase battery capacity. 2. Optimize software to reduce power consumption. 3. Add a power-saving mode."

[1002] 6. Providing advice to users

[1003] The server sends the generated improvement advice back to the user and displays it on the terminal interface, where the user can review it and modify the evaluation comments as necessary.

[1004] Specific examples

[1005] Example of a review comment: "This product is easy to use, but the battery life is poor."

[1006] Example prompt for a generative AI model: "If a user complains about the battery life of a product, what improvement advice should you provide?"

[1007] This system allows users to write evaluation comments in a consistent format, and the operation of the generative AI model and the improvement advice addition module ensures fairness and transparency of the evaluation. The flow of the identification process in Example 3 will be explained using Figure 15.

[1008] Step 1:

[1009] The user accesses the rating and comment writing interface.

[1010] Input: A user uses a device (PC, smartphone, tablet, etc.) to access the web page or application provided by the evaluation comment writing module.

[1011] Specific operation: The user opens a browser and enters the specified URL to access the site. The interface displays a text box for entering evaluation comments and a submit button.

[1012] Output: The user can now enter a rating comment.

[1013] Step 2:

[1014] The user enters and submits an evaluation comment.

[1015] Input: The user enters a rating comment in a text box on the interface.

[1016] Specific action: For example, enter "This product is easy to use, but the battery life is poor." After completing the entry, the user clicks the "Submit" button.

[1017] Output: The rating comment is sent from the device to the server.

[1018] Step 3:

[1019] The server receives the rating comments.

[1020] Input: Rating comment sent from the device.

[1021] Specific operation: The server receives the HTTP request, analyzes the rating comments, and stores them in a database.

[1022] Output: The rating comments are saved in the database.

[1023] Step 4:

[1024] The server analyzes the evaluation comments using a generative AI model.

[1025] Input: Rating comments stored in the database.

[1026] Specific operation: The server inputs the evaluation comments in text format into the generative AI model and obtains the analysis results. The generative AI model uses natural language processing technology to understand the content of the comments.

[1027] Output: Analysis results are generated.

[1028] Step 5:

[1029] The server generates advice using the improvement advice addition module.

[1030] Input: Analysis results of the generative AI model.

[1031] Specific operation: Based on the analysis results, the server calls the improvement advice addition module and generates specific improvement advice. For example, the advice generated might be, "To extend battery life, consider improving the following: 1. Increase battery capacity. 2. Optimize software to reduce power consumption. 3. Add a power-saving mode."

[1032] Output: Improvement advice is generated.

[1033] Step 6:

[1034] The server sends the generated advice back to the user

[1035] Input: The generated improvement advice.

[1036] Specific operation: The server generates an HTTP response and sends data including improvement advice to the terminal.

[1037] Output: Improvement advice is displayed on the terminal interface.

[1038] Step 7:

[1039] The user checks the improvement advice and modifies the evaluation comments as necessary.

[1040] Input: Improvement advice displayed on the terminal interface.

[1041] Specific behavior: The user reads the displayed advice, re-edits the rating comment, and resubmits it.

[1042] Output: The corrected rating comment is sent to the server again.

[1043] (Application example 3)

[1044] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1045] In conventional evaluation and comment systems, users often leave inconsistent comments that lack specificity and accuracy. Furthermore, there is a lack of specific advice on how to improve the quality of reviews, making it difficult for users to provide useful information for other users. Furthermore, writing reviews is cumbersome, making it difficult for users to easily write high-quality reviews.

[1046] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes: means for utilizing artificial intelligence to convert evaluation comments succinctly, accurately, and specifically; means for adding improvement advice comments from a third-party perspective in accordance with the default style of the messenger app; means for providing a format for the evaluation comment entry field that implements these functions; means for providing an interface for users to write product reviews; means for an artificial intelligence module to operate on the interface and analyze the content of the user's review; means for an improvement advice addition module to provide advice for improving the quality of the review in real time; and means for presenting guidelines for writing reviews in a consistent format. This enables users to easily write high-quality reviews and makes it easier for them to provide information that is useful to other users.

[1047] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1048] An "evaluation comment" is a description of a user's opinion or impression about a particular product or service.

[1049] A "messenger app" is a software application for sending and receiving text and multimedia messages over the Internet.

[1050] A "third-party perspective" is an objective viewpoint from the standpoint of a third party who is not a party involved when making an evaluation or giving an opinion.

[1051] A "format" is a framework for arranging data or information in a specific form or structure.

[1052] An "interface" is the means or method by which a user interacts with a system or application.

[1053] An "artificial intelligence module" is an artificial intelligence component designed to perform a specific task.

[1054] "Analysis" is the process of examining data or information in detail to understand its structure and meaning.

[1055] The "improvement advice addition module" is a component for providing specific advice for improving quality based on user input.

[1056] "Guidelines" are guidelines or standards for performing specific actions or tasks.

[1057] A system for carrying out this invention comprises a server and a user terminal. The server includes means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, means for adding comments of improvement advice from a third-party perspective in accordance with the specified style of the messenger app, means for providing a format for the evaluation comment entry field that implements these functions, means for providing an interface for users to write product reviews, means for an artificial intelligence module to operate on the interface and analyze the content of the user's review, means for an improvement advice adding module to provide advice for improving the quality of the review in real time, and means for presenting guidelines so that reviews can be written in a consistent format.

[1058] Hardware and software used

[1059] Server: A server for hosting the Flask application.

[1060] User device: Smartphone

[1061] Software: Flask (a Python web framework), OpenAI API (an API for using generative AI models)

[1062] Data processing and calculation

[1063] 1. User device: The user enters the review on the smartphone app.

[1064] 2. Server: The entered review is sent to the Flask server.

[1065] 3. Server: The Flask server calls the OpenAI API and parses the reviews.

[1066] 4. Server: The generative AI model analyzes the reviews and generates improvement advice.

[1067] 5. Server: The Flask server returns the generated advice to the user.

[1068] Specific examples

[1069] If a user writes a review saying, "This product was very good. It was easy to use and convenient," the generative AI model will provide advice such as, "Your review will be even better if you add specific usage scenarios and information that would be useful to other users."

[1070] Prompt Sentence Examples

[1071] Please analyze the following reviews and provide your suggestions for improvement:

[1072] This product was very good. It was easy to use and convenient.

[1073] In this way, users can easily write high-quality reviews, making it easier for them to provide useful information to other users.

[1074] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1075] Step 1:

[1076] A user starts the smartphone app and enters a product review. The entered review is sent from the user's device to the server. The input data is the text review written by the user.

[1077] Step 2:

[1078] The server processes the received reviews using a Flask application, which prepares to call the OpenAI API to parse the reviews. The input data is the text review written by the user, and the output data is a prompt to send to the OpenAI API.

[1079] Step 3:

[1080] The server calls the OpenAI API and sends a prompt. The prompt contains instructions for analyzing the review written by the user and generating improvement advice. The input data is the prompt, and the output data is the improvement advice generated by the generative AI model.

[1081] Step 4:

[1082] The server receives the improvement advice returned from the OpenAI API. The received advice is sent back to the user device along with the user's review. The input data is the improvement advice generated by the generative AI model, and the output data is the review and advice sent back to the user device.

[1083] Step 5:

[1084] The user terminal displays the reviews and improvement advice received from the server. The user can modify or add to the review based on the displayed advice. The input data are the reviews and advice returned from the server, and the output data are the reviews modified or added by the user.

[1085] Step 6:

[1086] When the user finalizes the review and presses the submit button, the review is sent to the server again and saved as the final review. The input data is the final review with any corrections or additions made by the user, and the output data is the final review saved on the server.

[1087] 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.

[1088] "Example 1"

[1089] One embodiment of the present invention combines a system that includes a means for converting evaluation comments succinctly, accurately, and specifically, a means for adding improvement advice comments from a third-party perspective in accordance with the default style of a messaging app, and a means for providing a format for the evaluation comment entry field that implements these functions, with an emotion engine that recognizes user emotions. This emotion engine identifies emotional elements contained in the evaluation comments and converts the evaluation comments and generates improvement advice based on those elements. Specifically, from an evaluation comment such as "This project was very enjoyable," the emotion "fun" is extracted, and based on that, improvement advice is generated such as "We recommend that you work with the same team members on the next project so that you can have a similar enjoyment."

[1090] "Example 2"

[1091] In another embodiment, the emotion engine analyzes the user's emotions based on the evaluation comments and uses the results to convert the evaluation comments and generate improvement advice. In this case, the emotion engine extracts the emotion "difficult" from the evaluation comment "This project was very difficult," and based on that, generates improvement advice such as "We recommend assigning easier tasks to the next project."

[1092] "Example 3"

[1093] In another embodiment, the evaluation comment entry field format provides an interface for accepting user input, and the emotion engine operates on that interface. In this case, the user directly enters the evaluation comment into the interface, and the emotion engine analyzes the input in real time. Then, based on the analysis results, the evaluation comment is converted and improvement advice is generated, and this is fed back to the user.

[1094] The processing flow of each embodiment will be described below.

[1095] "Example 1"

[1096] Step 1: The user enters their evaluation comments into the system.

[1097] Step 2: The emotion engine extracts emotional elements from the evaluation comments.

[1098] Step 3: Based on the extracted sentiment, the evaluation comments are converted and improvement advice is generated.

[1099] Step 4: Provide the generated improvement advice to the user as feedback.

[1100] "Example 2"

[1101] Step 1: The user enters their evaluation comments into the system.

[1102] Step 2: The sentiment engine analyzes the rating comments and extracts the user's sentiment.

[1103] Step 3: Based on the extracted sentiment, the evaluation comments are converted and improvement advice is generated.

[1104] Step 4: Provide the generated improvement advice to the user as feedback.

[1105] "Example 3"

[1106] Step 1: The user enters the evaluation comment directly into the system interface.

[1107] Step 2: The emotion engine analyzes the user's input in real time.

[1108] Step 3: Based on the analysis results, the evaluation comments are converted and improvement advice is generated. Step 4: The generated improvement advice is fed back to the user in real time.

[1109] Example 1

[1110] Next, a description will be given of Example 1 of Form 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."

[1111] Conventional evaluation and comment systems have difficulty converting abstract evaluation comments into concrete, clear forms, and are unable to provide improvement advice that takes into account the user's feelings. As a result, evaluation comments are vague, and it is difficult to obtain specific feedback or areas for improvement. Furthermore, it is difficult to provide comments that fit the default style of the messaging app.

[1112] 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.

[1113] In this invention, the server includes means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, means for adding improvement advice comments from a third-party perspective in accordance with the default style of the messenger app, means for providing a format for the evaluation comment entry field that implements these functions, and means for identifying emotional elements included in the evaluation comments using an emotion engine that recognizes user emotions and converting the evaluation comments and generating improvement advice based on the identified emotional elements. This makes it possible to convert evaluation comments into a specific and clear format and provide improvement advice that takes the user's emotions into consideration.

[1114] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1115] An "evaluation comment" is a piece of text that describes feedback or opinions about a specific action or outcome.

[1116] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[1117] A "messenger app" is a software application for sending and receiving text and multimedia messages.

[1118] An "emotion engine" is a technology for extracting and analyzing emotional elements from data such as text and voice.

[1119] A "format" is a framework for arranging data or information in a specific form or structure.

[1120] An "interface" is a part that provides the means and methods for a user to interact with a system.

[1121] "Improvement advice" is specific suggestions or advice for improving a particular behavior or outcome.

[1122] MODE FOR CARRYING OUT THE INVENTION

[1123] This invention is a system that converts evaluation comments succinctly, accurately, and specifically, and provides emotion-based improvement advice. This system is realized by combining artificial intelligence, natural language processing technology, and an emotion engine.

[1124] 1. Generate the system program

[1125] The user uses an interface for inputting evaluation comments. This interface is provided as a text box on a web browser, etc. When the user inputs an evaluation comment, the comment is sent to the server.

[1126] 2. Explain the program's processing in natural language

[1127] The server uses Python's natural language processing libraries, NLTK and spaCy, to analyze the grammatical structure of the evaluation comments received from users and extract elements such as subjects, predicates, and objects.

[1128] Next, the server converts the evaluation comments into concrete, clear comments based on the analysis results. For example, a comment such as "This project was a lot of fun" can be converted into "I recommend that you work with the same team members on the next project so that you can have the same fun experience."

[1129] The server then uses IBM Watson's sentiment analysis API to identify the emotional components of the evaluation comments. Based on the identified emotions, the server generates improvement advice. For example, based on the emotion "fun," the server generates advice such as "recommend having the same team members participate in the next project so that you can have a similarly enjoyable experience."

[1130] 3. Add examples to your description

[1131] As a specific example, the processing when the following evaluation comment is input will be shown.

[1132] Entered evaluation comment:

[1133] "This project was a lot of fun."

[1134] Evaluation comments after conversion:

[1135] "We encourage you to join the same team members so that you can have the same fun on your next project."

[1136] Example prompts to input to a generative AI model:

[1137] "Transform the following evaluation comment into a specific, clear form and add emotion-based suggestions for improvement. Evaluation comment: 'I had a lot of fun on this project.'"

[1138] In this way, users can utilize a system that converts evaluation comments into concrete and clear forms and provides emotion-based improvement advice. This system can improve the quality of evaluation comments and increase user satisfaction by providing specific feedback and suggestions for improvement.

[1139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1140] Step 1:

[1141] The user inputs an evaluation comment.

[1142] The user enters an evaluation comment in a text box on the web browser. For example, the user enters "I really enjoyed this project." The entered comment is sent to the server.

[1143] Step 2:

[1144] The server receives the rating comments.

[1145] The server receives the evaluation comments sent by the users and temporarily stores them in a database. The received comments become input data for the next analysis step.

[1146] Step 3:

[1147] The server analyzes the evaluation comments using natural language processing technology.

[1148] The server uses Python's natural language processing libraries NLTK and spaCy to analyze the grammatical structure of the evaluation comments. Specifically, it extracts elements such as the subject, predicate, and object of the comment. For example, from the comment "This project was very fun," it extracts the elements "project" and "fun." The analysis results become the input data for the next conversion step.

[1149] Step 4:

[1150] Based on the analysis results, the server converts the evaluation comments into a concrete and clear form.

[1151] The server converts the evaluation comments into concrete, clear forms based on the analysis results. For example, a comment such as "This project was very enjoyable" can be converted into "I recommend that you work with the same team members on the next project so that you can have the same enjoyment." The converted comments become input data for the next sentiment analysis step.

[1152] Step 5:

[1153] The server uses an emotion engine to identify emotional elements contained in the evaluation comments.

[1154] The server uses IBM Watson's sentiment analysis API to identify the emotional elements contained in the evaluation comments. For example, it extracts the emotion "fun." The results of the sentiment analysis become input data for the next step, which is generating improvement advice.

[1155] Step 6:

[1156] The server generates improvement advice based on the emotion.

[1157] The server generates improvement advice based on the identified emotion. For example, based on the emotion "fun," it generates advice such as "recommend participating in the next project with the same team members so that you can feel the same enjoyment." The generated improvement advice becomes the final output data.

[1158] Step 7:

[1159] The server returns the converted evaluation comments and improvement advice to the user.

[1160] The server then returns the converted evaluation comments and advice for improvement to the user. The user can view this information through the system interface. For example, in a web browser, the user might see a comment and advice such as, "We recommend that you work with the same team members on your next project so that you can have the same fun."

[1161] (Application example 1)

[1162] Next, a description will be given of Application Example 1 of Form 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."

[1163] Conventional evaluation and comment systems have the problem that many of the evaluation comments are abstract, making it difficult to obtain specific feedback. Furthermore, there is a lack of improvement advice that takes emotional factors into consideration, which can lead to a decline in the quality of the evaluation comments. Furthermore, while specific and clear feedback is required for work evaluations within factories, there is a lack of means to achieve this.

[1164] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes: means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence; means for adding improvement advice comments from a third-party perspective in accordance with the default style of the messenger app; means for providing a format for the evaluation comment entry field that implements these functions; means for identifying emotional elements contained in the evaluation comments using an emotion engine and converting the evaluation comments and generating improvement advice based on the identified emotional elements; and means for providing a work evaluation feedback system to be installed in a factory robot. This makes it possible to generate specific and clear evaluation comments and provide improvement advice that takes emotional elements into consideration.

[1165] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1166] An "evaluation comment" is a piece of writing that expresses opinions or feedback about a specific action or result.

[1167] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language.

[1168] An "emotion engine" is a technology that extracts emotional elements from text data and generates appropriate responses and actions based on them.

[1169] A "messenger app" is a software application for sending and receiving text messages.

[1170] "Third-party perspective" refers to making evaluations and opinions from a neutral and objective point of view.

[1171] "Improvement advice" is specific suggestions or advice for improving a particular behavior or outcome.

[1172] The "evaluation comment entry field" is an interface for inputting, displaying, and editing evaluation comments.

[1173] A "factory robot" is a mechanical device used to automate work in a factory.

[1174] The "work evaluation feedback system" is a system for collecting and analyzing work evaluation comments and providing feedback.

[1175] As an embodiment of the present invention, a work evaluation feedback system installed in a factory robot is provided. A specific embodiment of this system will be described below.

[1176] System configuration

[1177] The system consists of the following main components:

[1178] 1. Artificial intelligence module: Converts evaluation comments into concise, accurate, and specific comments.

[1179] 2. Emotion engine: Identifies the emotional elements contained in the evaluation comments and converts the evaluation comments and generates improvement advice based on that.

[1180] 3. Evaluation comment entry field: Provides an interface for users to enter, view, and edit evaluation comments.

[1181] 4. Factory robots: Install a work evaluation feedback system and perform work evaluation within the factory.

[1182] Program processing

[1183] The server processes the data in the following steps:

[1184] 1. Entering evaluation comments: The user enters evaluation comments in the evaluation comment field.

[1185] 2. Natural Language Processing: The artificial intelligence module uses natural language processing technology to analyze the input evaluation comments and convert them into a concrete and clear form.

[1186] 3. Sentiment Analysis: The sentiment engine identifies the emotional components contained in the rating comments.

[1187] 4. Generation of improvement advice: Based on the results of the emotion engine, appropriate improvement advice is generated.

[1188] 5. Providing feedback: Providing converted evaluation comments and improvement advice to users.

[1189] Hardware and software used

[1190] Hardware: Factory robots, servers, user terminals

[1191] Software: OpenAI's GPT-3 model, TextBlob library

[1192] Specific examples

[1193] For example, if a user enters an evaluation comment such as "Good job," the system processes it as follows:

[1194] 1. Input comment: "Good job"

[1195] 2. Specific evaluation comment: "Delivered high-quality deliverables within the project deadline."

[1196] 3. Improvement advice: "I hope to see similar results on your next project."

[1197] Example prompts to input to a generative AI model:

[1198] Please translate the following evaluation comments into specific, clear statements: Good job

[1199] In this way, a work evaluation feedback system installed in a factory robot is realized, which makes it possible to generate specific and clear evaluation comments and provide improvement advice that takes emotional factors into account.

[1200] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1201] Step 1:

[1202] The user inputs an evaluation comment in the evaluation comment field. The input evaluation comment is sent to the server. For example, the comment "You did a good job" is input.

[1203] Step 2:

[1204] The server sends the received evaluation comments to an AI module, which uses natural language processing technology to analyze the evaluation comments and convert them into specific, clear comments. For example, a comment such as "You did a good job" can be converted into "You delivered a high-quality product within the project deadline."

[1205] Step 3:

[1206] The server sends the converted evaluation comments to the emotion engine, which identifies emotional elements contained in the evaluation comments. For example, it extracts positive emotions from the comment "You delivered high-quality deliverables within the project deadline."

[1207] Step 4:

[1208] The server generates improvement advice based on the results of the emotion engine. If the emotion engine identifies a positive emotion, the server generates improvement advice such as, "We expect similar results in your next project."

[1209] Step 5:

[1210] The server sends the converted evaluation comment and the generated improvement advice to the user terminal. The user terminal displays this information in the evaluation comment entry field. For example, an evaluation comment such as "You provided a high-quality deliverable within the project deadline" and improvement advice such as "We expect similar results in the next project" are displayed.

[1211] Step 6:

[1212] The user checks the displayed evaluation comments and improvement advice, and makes additional comments or corrections as necessary. The final evaluation comments and improvement advice are saved in the system.

[1213] Example 2

[1214] Next, a description will be given of Example 2 of Form 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."

[1215] Conventional evaluation comment systems have difficulty accurately analyzing user evaluation comments and providing specific improvement advice. Furthermore, they do not generate advice that takes user emotions into account, making it difficult to improve user satisfaction. Furthermore, converting evaluation comments and adding improvement advice is often done manually, making efficient operation difficult.

[1216] 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.

[1217] In this invention, the server includes: means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence; means for adding improvement advice comments from a third-party perspective in accordance with the specified style of the messaging application; means for analyzing user emotions based on the evaluation comments and using the results to convert the evaluation comments and generate improvement advice; means for providing a format for an evaluation comment entry field that implements these functions; means for analyzing the evaluation comments and generating specific improvement advice using a generation AI model; and means for adding the generated improvement advice to the evaluation comments. This automates the analysis of evaluation comments and the generation of improvement advice, making it possible to provide specific advice that takes user emotions into consideration.

[1218] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1219] An "evaluation comment" is text that describes the feedback or opinion a user gives about a project or task.

[1220] A "messaging application" is software that enables users to send and receive text messages.

[1221] "Third-party perspective" refers to opinions and advice from a perspective other than that of the user who made the evaluation comment.

[1222] "Improvement advice" is a specific suggestion for improving the progress of a project or task, based on evaluation comments.

[1223] "Sentiment analysis" is the process of extracting and analyzing user emotions from text using natural language processing techniques.

[1224] A "generative AI model" is a model that uses artificial intelligence technology to generate new text and data.

[1225] The "evaluation comment entry field" is an interface for users to input evaluation comments.

[1226] "Natural language processing technology" is a technology that enables computers to understand, generate, and manipulate human language.

[1227] A "format" is a way of arranging data or information in a particular way or structure.

[1228] This invention is a system that analyzes evaluation comments entered by users and generates specific improvement advice. The system utilizes artificial intelligence, natural language processing technology, and generative AI models to accurately convert evaluation comments and provide advice that takes the user's emotions into consideration.

[1229] The server receives evaluation comments sent by users. The received comments are first sent to the evaluation comment analysis module. This module uses natural language processing technology (e.g., Python libraries such as spaCy and NLTK) to analyze the content of the evaluation comments. For example, it analyzes the comment "You delivered high-quality deliverables within the project deadline."

[1230] Next, the server uses an emotion engine to analyze the user's emotions from the evaluation comments. The emotion engine uses natural language processing technology to extract emotions from the comments. For example, it extracts the emotion "difficult" from the comment "This project was very difficult."

[1231] The server then uses a generative AI model (e.g., OpenAI's GPT-3) to generate improvement advice based on the evaluation comments and extracted sentiment, such as "We recommend assigning easier tasks to the next project."

[1232] The generated improvement advice is added to the evaluation comments, for example, "This project was very difficult. I recommend assigning easier tasks to the next project."

[1233] The server transmits the evaluation comment with the added improvement advice to the terminal. The terminal displays the result received from the server to the user. The user can check the evaluation comment with the added improvement advice.

[1234] As a concrete example, consider the case where a user enters an evaluation comment such as "This project was very difficult." The device sends this comment to the server. The server receives the comment and uses the evaluation comment analysis module to extract the keywords "project" and "difficult." The emotion engine then analyzes the emotion "difficult." The generative AI model generates improvement advice such as "We recommend assigning easier tasks to the user in the next project." The server adds this advice to the original comment and sends it to the device. The device then displays the result to the user: "This project was very difficult. We recommend assigning easier tasks to the user in the next project."

[1235] An example of a prompt to input to a generative AI model is as follows:

[1236] User review: "This project was very difficult."

[1237] Prompt for the generative AI model: "Based on the user's evaluation comments, generate specific improvement advice for the next project. Evaluation comment: 'This project was very difficult.'"

[1238] In this way, the system analyzes users' evaluation comments and provides specific advice for improvement.

[1239] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1240] Step 1:

[1241] The user inputs an evaluation comment.

[1242] A user uses a messaging application to enter a review of a project or task, for example, "This project was very difficult." The review becomes the starting point for the system.

[1243] Step 2:

[1244] The terminal transmits the evaluation comment to the server.

[1245] The device (user's smartphone or PC) sends the entered evaluation comments to the server. The HTTPS protocol is used for transmission to ensure data security. The input is the user's evaluation comments, and the output is the data sent to the server.

[1246] Step 3:

[1247] The server receives the rating comments.

[1248] The server receives the evaluation comments sent from the terminal. The received data is passed to the evaluation comment analysis module. The input is the evaluation comment sent from the terminal, and the output is the data transfer to the analysis module.

[1249] Step 4:

[1250] The server performs the analysis using the evaluation comment analysis module.

[1251] The server uses a rating comment analysis module to analyze the content of rating comments. This module uses natural language processing technology (e.g., Python libraries spaCy and NLTK) to understand the gist of the comment. For example, it analyzes the comment "You delivered high-quality deliverables within the project deadline." The input is the rating comment, and the output is the analysis result.

[1252] Step 5:

[1253] The server analyzes emotions using an emotion engine.

[1254] The server uses an emotion engine to analyze user emotions from the evaluation comments. The emotion engine uses natural language processing technology to extract emotions from comments. For example, it extracts the emotion "difficult" from the comment "This project was very difficult." The input is the evaluation comment, and the output is the extracted emotion data.

[1255] Step 6:

[1256] The server generates improvement advice using a generative AI model.

[1257] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate improvement advice based on the evaluation comments and extracted emotions. For example, it generates advice such as "It is recommended to assign easier tasks in the next project." The input is the evaluation comments and emotion data, and the output is the generated improvement advice.

[1258] Step 7:

[1259] Add the server-generated improvement advice to the evaluation comment.

[1260] The server adds the generated improvement advice to the original evaluation comment. For example, it might say, "This project was very difficult. I recommend assigning an easier task to the next project." The input is the generated improvement advice and the original evaluation comment, and the output is the evaluation comment with the added improvement advice.

[1261] Step 8:

[1262] The server sends the results to the terminal.

[1263] The server sends the evaluation comment with the added improvement advice to the terminal. The transmission is again via HTTPS. The input is the evaluation comment with the added improvement advice, and the output is the data sent to the terminal.

[1264] Step 9:

[1265] The terminal displays the results to the user.

[1266] The terminal displays the results received from the server to the user. The user can check the evaluation comments with added improvement advice. The input is the data received from the server, and the output is what is displayed to the user.

[1267] (Application example 2)

[1268] Next, a description will be given of Application Example 2 of Form 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."

[1269] Conventional evaluation comment systems have difficulty converting evaluation comments into concise, accurate, and specific comments, and are unable to provide improvement advice from a third-party perspective. It is also difficult to analyze user sentiment and generate improvement advice based on the results. This has led to problems such as a decline in the quality of evaluation comments and a lack of concrete guidelines for improvement.

[1270] 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.

[1271] In this invention, the server includes means for converting evaluation comments succinctly, accurately, and specifically by utilizing artificial intelligence, means for adding comments of improvement advice from a third-party perspective in accordance with the default style of the messenger app, and means for analyzing emotions based on the evaluation comments and generating improvement advice based on the results, thereby making it possible to improve the quality of evaluation comments and provide specific improvement advice.

[1272] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1273] An "evaluation comment" is a piece of text that provides feedback or evaluation of a particular task or project.

[1274] "Converting in a concise, accurate, and specific manner" means converting evaluation comments into concise, accurate, and specific content.

[1275] A "messenger app" is application software for sending and receiving text messages and multimedia messages.

[1276] A "defined style" is a format or style that is established as a standard in a particular application or system.

[1277] A "third-party perspective" is an objective viewpoint from a position that is not directly involved when making an evaluation or giving advice.

[1278] "Improvement advice" is specific suggestions or advice for improving a particular task or project.

[1279] "Emotion analysis" means identifying a user's emotions from data such as text or voice, and evaluating the type and intensity of those emotions.

[1280] The "evaluation comment entry field" is an interface or form for inputting evaluation comments.

[1281] A "format" is a framework for organizing data or information according to a specific form or structure.

[1282] To implement this invention, it is necessary to build a system that converts evaluation comments succinctly, accurately, and specifically, and adds improvement advice from a third-party perspective. This system is realized using artificial intelligence, natural language processing technology, and a sentiment analysis engine.

[1283] System Configuration

[1284] The system consists of the following main components:

[1285] 1. Server: Converts evaluation comments, analyzes sentiment, and generates improvement advice.

[1286] 2. Terminal: Provides an interface for users to enter evaluation comments and receive improvement advice.

[1287] 3. Artificial intelligence: Convert evaluation comments into concise, accurate, and specific information.

[1288] 4. Natural language processing technology: Analyzes and converts evaluation comments.

[1289] 5. Sentiment analysis engine: Analyzes user sentiment from rating comments.

[1290] 6. Generative AI model: Generates improvement advice based on the prompt sentence.

[1291] Program processing

[1292] The server receives the evaluation comments entered by the user and performs the following processes:

[1293] 1. Sentiment analysis: Analyze the sentiment of the rating comments using a natural language processing library such as TextBlob.

[1294] 2. Prompt generation: Generate appropriate prompts based on the results of sentiment analysis.

[1295] 3. Improvement advice generation: Using the OpenAI API, specific improvement advice is generated from the generated prompt sentences.

[1296] Hardware and software used

[1297] Hardware: Smartphones, servers

[1298] Software: Python, OpenAI API, TextBlob

[1299] Specific examples

[1300] For example, if a user enters an evaluation comment such as "Delivered high-quality work within the project deadline," the system will process it as follows:

[1301] 1. Sentiment Analysis: Analyze the sentiment of the rating comments using TextBlob to detect positive sentiment.

[1302] 2. Prompt generation: Generate the following prompt: "Evaluation comments: You delivered a high-quality deliverable within the project deadline. This contains positive emotions. Please provide some advice on how to improve the next project."

[1303] 3. Generation of improvement advice: Using the OpenAI API, improvement advice such as "Why not consider a more efficient work flow for your next project?" is generated from the generated prompt text.

[1304] Prompt Sentence Examples

[1305] Evaluation comment: High quality deliverables delivered within the project deadline

[1306] It contains positive emotions and offers advice to make your next project even better.

[1307] In this way, it becomes possible to improve the quality of the evaluation comments and provide specific advice for improvement.

[1308] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1309] Step 1:

[1310] The user inputs an evaluation comment using a terminal, and the input evaluation comment is sent to the server.

[1311] Input: User-entered evaluation comments (e.g., "Delivered high-quality deliverables within the project deadline")

[1312] Output: Rating comments sent to the server

[1313] Step 2:

[1314] The server performs sentiment analysis on the received evaluation comments using TextBlob, which analyzes the sentiment of the evaluation comments and determines the type of sentiment (positive, negative, neutral).

[1315] Input: Evaluation comments (e.g., "Delivered high-quality deliverables within the project deadline")

[1316] Data Processing: Sentiment Analysis using TextBlob

[1317] Output: Sentiment analysis result (e.g., positive)

[1318] Step 3:

[1319] The server generates prompt sentences based on the results of emotion analysis, creating appropriate prompt sentences depending on the type of emotion.

[1320] Input: Sentiment analysis results (e.g., positive), evaluation comments

[1321] Data processing: Generate prompt sentences based on the sentiment analysis results and evaluation comments

[1322] Output: Generated prompt (e.g., "Evaluation comments: You delivered a high-quality deliverable within the project deadline. This contains positive emotions. Please provide some advice on how to improve on your next project.")

[1323] Step 4:

[1324] The server sends the generated prompt sentence to the OpenAI API, which generates specific improvement advice. The OpenAI API generates appropriate advice based on the prompt sentence.

[1325] Input: Generated prompt text

[1326] Data Calculation: Generate improvement advice from prompts using OpenAI API

[1327] Output: Generated improvement advice (e.g., "For your next project, why not consider a more efficient workflow?")

[1328] Step 5:

[1329] The server sends the generated improvement advice to the user's terminal, where the user can check the improvement advice.

[1330] Input: Generated improvement advice

[1331] Output: Improvement advice sent to the user's device

[1332] In this way, it becomes possible to improve the quality of the evaluation comments and provide specific advice for improvement.

[1333] Example 3

[1334] Next, a description will be given of Example 3 of Form Example 3. 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."

[1335] With conventional evaluation and comment systems, it is difficult to ensure the consistency, fairness, and transparency of comments written by users. Furthermore, there is a lack of a means to provide appropriate feedback on comments written by users, which can lead to a decline in the quality of comments. Furthermore, there is no system that analyzes user comments in real time and provides advice on improvement, which places a heavy burden on users.

[1336] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1337] In this invention, the server includes a means for providing an interface for users to write evaluation comments, a means for an artificial intelligence module to run on the interface and analyze the evaluation comments, and a means for generating improvement advice based on the analysis results and providing feedback to the user. This allows users to write evaluation comments in a consistent format, ensuring fairness and transparency of evaluations. Furthermore, real-time analysis and feedback reduces the burden on users and enables the quality of comments to be improved.

[1338] An "interface" is a means for providing a screen or input form for users to write evaluation comments.

[1339] The "artificial intelligence module" is a program that analyzes evaluation comments and generates improvement advice.

[1340] "Analysis" is the process of analyzing the content of evaluation comments written by users and understanding their emotions and intentions.

[1341] "Improvement advice" is a suggestion generated based on the analysis results to make the evaluation comments more specific and accurate.

[1342] "Feedback" is the process of returning analysis results and improvement advice to the user.

[1343] "Saving" means recording the final evaluation comments corrected by the user in a storage device such as a database.

[1344] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[1345] The present invention provides a system that provides an interface for users to write evaluation comments and an artificial intelligence module operates on the interface. A specific embodiment of this system will be described below.

[1346] Hardware and software used

[1347] Hardware: Servers (e.g., cloud computing services)

[1348] software:

[1349] Artificial intelligence modules (e.g., generative AI models using natural language processing technology)

[1350] Additional modules for improvement advice (e.g. custom scripts)

[1351] Emotion engines (e.g., emotion analysis tools)

[1352] Specific operation of the system

[1353] Subject: Server

[1354] The server provides an interface for users to write evaluation comments. This interface can be accessed through a web browser or a dedicated application. When a user accesses the interface, the server displays a text box for inputting evaluation comments.

[1355] Subject: User

[1356] The user uses the provided interface to enter a review comment, for example, "This product is very easy to use and has a great design. However, if only the battery life was a little longer, it would be perfect."

[1357] Subject: Server

[1358] The server receives user-entered evaluation comments, temporarily stores them in a database, and then analyzes the comments in real time using an emotion engine. The analysis results include the emotional tone of the comments and their positive and negative aspects.

[1359] The server then uses the generative AI model to generate improvement advice based on the analysis results, such as "It would be a good idea to emphasize the positive aspects and add specific suggestions for improving battery life."

[1360] The generated improvement advice is fed back to the user. The user then modifies their evaluation comment based on the feedback from the server. For example, they might modify their comment to say, "This product is very easy to use and has a great design. It would be even better if the battery life was a little longer."

[1361] Finally, the server stores the user-modified rating comments in a database for future reference and analysis.

[1362] Specific examples

[1363] Example prompts to input to the generative AI model

[1364] Please write an evaluation comment about your experience using this product. Please include specific usage scenarios and your impressions.

[1365] This system allows users to write evaluation comments in a consistent format, ensuring fairness and transparency of evaluations. Real-time analysis and feedback also reduces the burden on users and improves the quality of comments. The flow of the identification process in Example 3 will be described with reference to FIG. 21.

[1366] Step 1:

[1367] The user accesses the evaluation comment writing interface.

[1368] Input: URL or application launch to access the interface through a web browser or dedicated application.

[1369] Output: A text box will appear for you to enter your rating comments.

[1370] Specific operation: The user opens a web browser and accesses the specified URL or launches a dedicated application. The server then displays the evaluation comment entry interface on the user's device.

[1371] Step 2:

[1372] The user inputs an evaluation comment.

[1373] Input: Enter your evaluation comment in the text box.

[1374] Output: The entered evaluation comments are displayed on the interface.

[1375] What it does: The user enters their review in a text box on the interface. For example, they might write, "This product is very easy to use and has a great design. However, if only the battery life was a little longer, it would be perfect."

[1376] Step 3:

[1377] The server receives the entered comment.

[1378] Input: The rating comment entered by the user.

[1379] Output: Received comments are temporarily stored in a database.

[1380] Specific operation: The server receives the evaluation comments entered by the user and temporarily stores them in a database.

[1381] Step 4:

[1382] The server analyzes the comments using an emotion engine.

[1383] Input: The received rating comment.

[1384] Output: Analysis results including the emotional tone of the comments and whether they are positive or negative.

[1385] Specific operation: The server calls the emotion engine to analyze the received evaluation comments. The analysis results include the emotional tone of the comments and their positive and negative elements.

[1386] Step 5:

[1387] The server generates improvement advice based on the analysis results.

[1388] Input: Analysis results from the emotion engine.

[1389] Output: Improvement advice.

[1390] Specific operation: The server uses the generative AI model to generate improvement advice based on the analysis results. For example, it generates advice such as, "It would be a good idea to emphasize the positive aspects and add specific improvement suggestions for battery life."

[1391] Step 6:

[1392] The server generates improvement advice and feeds it back to the user.

[1393] Input: Improvement advice.

[1394] Output: Feedback displayed to the user in the interface.

[1395] Specific operation: The server generates improvement advice and provides it to the user as feedback. The feedback is displayed on the interface.

[1396] Step 7:

[1397] The user edits the comment based on the feedback.

[1398] Input: Feedback from the server.

[1399] Output: The revised rating comment.

[1400] Specific behavior: The user modifies the evaluation comment based on the feedback from the server. For example, the user might modify the comment to say, "This product is very easy to use and has a great design. It would be even better if the battery life was a little longer."

[1401] Step 8:

[1402] The server stores the final evaluation comments.

[1403] Input: The revised rating comment.

[1404] Output: The final evaluation comments stored in the database.

[1405] What happens: The server saves the final user-modified evaluation comments in a database for future reference and analysis.

[1406] (Application example 3)

[1407] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1408] In conventional evaluation and comment systems, the comments written by users are often subjective and lack specificity and fairness. Furthermore, there is a lack of advice on how to improve the comments written by users from a third-party perspective, resulting in low transparency of the evaluations. Furthermore, when users enter product reviews, they do not receive real-time feedback, which can lead to a decline in the quality of the reviews. A system that can solve these issues is needed.

[1409] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1410] In this invention, the server includes a means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, a means for analyzing user input in real time using a sentiment analysis engine, and a means for generating advice for improving the evaluation comments using a generative AI model. This makes it possible to improve the quality of evaluation comments written by users and maintain fairness and transparency. In addition, when users enter product reviews, they can receive feedback in real time, further improving the quality of the reviews.

[1411] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1412] An "emotion analysis engine" is a technology that analyzes emotions and the intensity of emotions from text data and determines the emotional state, such as positive, negative, or neutral.

[1413] A "generative AI model" is a type of artificial intelligence that generates new text or information based on given input data, and is a technique used particularly in natural language processing.

[1414] The "evaluation comment entry field format" is an interface for users to input evaluation comments, and has a structure that allows artificial intelligence and sentiment analysis engines to operate.

[1415] An "interface" is a means by which a user interacts with a system, and includes a screen and operating method for input and output.

[1416] "Natural language processing technology" is a technology that enables computers to understand, generate, and manipulate human language, and includes functions such as text analysis, generation, and translation.

[1417] The system for implementing this invention mainly comprises a server, a user terminal, and an interface. Each component and its operation will be described in detail below.

[1418] server

[1419] The server is the main component for running the artificial intelligence, sentiment analysis engine, and generative AI models. The server has the following functions:

[1420] 1. Artificial Intelligence: Convert user-entered evaluation comments concisely, accurately, and specifically. Using natural language processing technology, the input text is analyzed and converted into an appropriate format.

[1421] 2. Sentiment Analysis Engine: Analyzes user input in real time to determine the emotional state, such as positive, negative, or neutral, to understand the user's emotions and provide appropriate feedback.

[1422] 3. Generative AI model: Generates improvement advice for evaluation comments based on user input. The generative AI model is implemented using OpenAI's API.

[1423] User terminal

[1424] The user device is a device such as a smartphone or tablet that provides an interface for users to enter evaluation comments. The user device has the following functions:

[1425] 1. Interface: Provides a screen for users to enter their evaluation comments. This interface sends the text entered by the user to the server, allowing users to receive feedback in real time.

[1426] Interface

[1427] The interface is a means for users to enter rating comments and receive feedback from the server. The interface has the following features:

[1428] 1. Input field: Provides a text box for users to enter their evaluation comments.

[1429] 2. Real-time feedback: As users provide input, the sentiment analysis engine and generative AI model work together to provide real-time feedback.

[1430] Specific examples

[1431] For example, if a user enters an evaluation comment such as "This product is very easy to use, but the battery life is poor," the sentiment analysis engine analyzes this comment and calculates its positivity and subjectivity.The generative AI model then generates advice to improve this comment.

[1432] Prompt Sentence Examples

[1433] Please offer suggestions to improve the following review: This product is very easy to use, but the battery life is poor.

[1434] In this way, a system is realized that can improve the quality of evaluation comments written by users and maintain fairness and transparency.

[1435] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1436] Step 1:

[1437] The user inputs an evaluation comment through the terminal interface.

[1438] Input: User-entered evaluation comments (e.g., "This product is very easy to use, but the battery life is poor.")

[1439] Output: The entered evaluation comments are sent from the terminal to the server.

[1440] Step 2:

[1441] The server passes the received evaluation comments to the sentiment analysis engine, which performs sentiment analysis in real time.

[1442] Input: Rating comment sent from the device

[1443] Data processing: The sentiment analysis engine analyzes the text and calculates positivity and subjectivity.

[1444] Output: Sentiment analysis result (e.g., positivity 0.5, subjectivity 0.6)

[1445] Step 3:

[1446] Based on the results of the emotion analysis, the server generates prompt sentences for the generative AI model and generates advice for improving the evaluation comments.

[1447] Input: Sentiment analysis results and evaluation comments

[1448] Data processing: The generative AI model generates prompt sentences and generates improvement advice using the OpenAI API.

[1449] Output: Generated improvement advice (e.g., "Regarding the poor battery life, please provide specific usage time and circumstances, which will be helpful for other users.")

[1450] Step 4:

[1451] The server transmits the generated improvement advice to the terminal and provides feedback to the user.

[1452] Input: Generated improvement advice

[1453] Output: Improvement advice displayed on the terminal

[1454] Step 5:

[1455] The user modifies the evaluation comment by referring to the improvement advice through the terminal interface.

[1456] Input: Evaluation comments from users who received improvement advice

[1457] Output: The modified rating comment is resubmitted from the device to the server.

[1458] Step 6:

[1459] The server finally stores the modified evaluation comments and makes them available for other users to view.

[1460] Input: Revised rating comment

[1461] Output: The saved evaluation comments are stored in a database and can be viewed by other users.

[1462] 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.

[1463] 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> ) 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.

[1464] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1465] 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.

[1466] [Third embodiment]

[1467] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1468] 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.

[1469] 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).

[1470] 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.

[1471] 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.

[1472] 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).

[1473] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1474] 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.

[1475] 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.

[1476] 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.

[1477] 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.

[1478] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1479] "Example 1"

[1480] In one embodiment of the present invention, an artificial intelligence module is provided for converting evaluation comments into concise, accurate, and specific ones. This module uses natural language processing technology to analyze input evaluation comments and convert them into more specific and clear forms. For example, an abstract evaluation comment such as "You did a good job" is converted into a concrete evaluation comment such as "You delivered a high-quality deliverable within the project deadline."

[1481] "Example 2"

[1482] There is also a module that adds comments with advice for improvement from a third-party perspective, in line with the messaging app's default style. This module generates specific advice for improvement based on the evaluation comments and adds it to the evaluation comments. For example, in response to the evaluation comment "You delivered high-quality deliverables within the project deadline," the module adds the advice "For the next project, why not consider creating a more efficient workflow?"

[1483] "Example 3"

[1484] Furthermore, a module for providing a format for the evaluation comment field is also provided. This module provides an interface for users to write evaluation comments, and the aforementioned artificial intelligence module and improvement advice addition module operate on this interface. This allows users to write evaluation comments in a consistent format, maintaining the fairness and transparency of evaluations.

[1485] The processing flow of each embodiment will be described below.

[1486] "Example 1"

[1487] Step 1: The user enters their evaluation comments into the system.

[1488] Step 2: The entered evaluation comments are sent to the artificial intelligence module.

[1489] Step 3: The AI ​​module uses natural language processing technology to analyze the evaluation comments and convert them into more specific and clearer forms, such as converting an abstract evaluation comment like "You did a good job" into a concrete evaluation comment like "You delivered high-quality deliverables within the project deadline."

[1490] Step 4: The converted rating comments are displayed to the user.

[1491] "Example 2"

[1492] Step 1: The user enters their evaluation comments into the system.

[1493] Step 2: The entered evaluation comments are sent to the improvement advice addition module.

[1494] Step 3: The improvement advice addition module generates specific improvement advice based on the evaluation comments and adds it to the evaluation comments. For example, in response to the evaluation comment "You delivered high-quality deliverables within the project deadline," the improvement advice added is "In the next project, why not consider a more efficient work flow?"

[1495] Step 4: The evaluation comment with the added improvement advice is displayed to the user.

[1496] "Example 3"

[1497] Step 1: The user launches a module that provides a format for the evaluation comment field.

[1498] Step 2: The module provides an interface for users to write evaluation comments.

[1499] Step 3: The user enters the evaluation comments into the interface.

[1500] Step 4: The aforementioned AI module and improvement advice addition module are activated to ensure consistency and fairness in the evaluation comments.

[1501] Example 1

[1502] Next, a description will be given of Example 1 of Form 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."

[1503] Conventional evaluation comments are abstract, making it difficult to provide specific feedback. It is also difficult to provide evaluation comments as improvement advice from a third-party perspective. This makes it difficult for the person being evaluated to understand specific areas for improvement, potentially resulting in missed growth opportunities.

[1504] 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.

[1505] In this invention, the server includes means for a user to input an evaluation comment, means for a terminal to transmit the input evaluation comment to the server, means for the server to receive the evaluation comment and analyze it using natural language processing technology, means for the server to generate a prompt sentence to input the analysis result to the generative AI model, means for the server to input the prompt sentence to the generative AI model and generate a specific evaluation comment, means for the server to transmit the generated specific evaluation comment to the terminal, means for the terminal to display the specific evaluation comment to the user, and means for providing a format for an evaluation comment entry field that implements these functions. This makes it possible to convert evaluation comments into specific and clear information and provide useful feedback to users.

[1506] A "user" is an individual or group that uses the system to input evaluation comments.

[1507] A "terminal" is a device through which a user inputs evaluation comments and communicates with a server.

[1508] The "server" is a computer system that receives and analyzes evaluation comments and generates specific evaluation comments using a generative AI model.

[1509] An "evaluation comment" is a feedback or evaluation text entered by a user.

[1510] "Natural language processing technology" is a technology for analyzing evaluation comments and extracting grammatical structures and keywords.

[1511] A "generative AI model" is an artificial intelligence model that generates specific evaluation comments based on analyzed evaluation comments.

[1512] A "prompt sentence" is an instruction sentence to be input into a generative AI model.

[1513] The "format of the evaluation comment entry field" is a format that provides an interface for the user to input evaluation comments.

[1514] This invention is a system for converting evaluation comments specifically and clearly. The program processing of this system will be specifically explained below.

[1515] First, the user inputs an evaluation comment using a terminal. The terminal then sends the evaluation comment to the server. The server then analyzes the received evaluation comment using natural language processing technology. This analysis uses natural language processing libraries such as "spaCy" and "NLTK."

[1516] Next, the server generates a prompt sentence to be input into the generative AI model based on the analysis results. For example, "GPT-4" is used as the generative AI model. An example of a prompt sentence is "Please convert the following abstract evaluation comment into a concrete evaluation comment: 'Good job'."

[1517] The server inputs the generated prompt into the generative AI model to generate a specific evaluation comment. Based on the prompt, the generative AI model outputs a specific evaluation comment such as "A high-quality deliverable was delivered within the project deadline."

[1518] The server then transmits the generated specific evaluation comment to the terminal, and the terminal displays the received specific evaluation comment to the user. For example, a comment such as "You provided a high-quality deliverable within the project deadline" is displayed on the user's screen.

[1519] As a concrete example, consider the case where a user inputs an evaluation comment such as "Good job." This comment is sent by the device to the server, which analyzes it using natural language processing technology. Based on the analysis results, the server generates a prompt saying, "Please convert the following abstract evaluation comment into a concrete evaluation comment: 'Good job'." The prompt is then input into a generative AI model, which generates a concrete evaluation comment: "You delivered a high-quality deliverable within the project deadline." The server then sends this concrete evaluation comment to the device, which displays it to the user.

[1520] In this way, it is possible to convert evaluation comments into specific and clear comments and provide useful feedback to users.

[1521] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1522] Step 1:

[1523] The user inputs an evaluation comment.

[1524] The user inputs an evaluation comment through the device interface, for example, by inputting "good job" in the text box. The input evaluation comment is temporarily stored in the device memory.

[1525] Step 2:

[1526] The terminal transmits the input evaluation comment to the server.

[1527] The terminal sends the evaluation comment entered by the user to the server as an HTTP request. At this time, the evaluation comment is packaged in JSON format. The input is the evaluation comment "Good job" and the output is an HTTP request to the server.

[1528] Step 3:

[1529] The server receives the evaluation comments and analyzes them using natural language processing technology.

[1530] The server analyzes the received evaluation comments using a natural language processing library (e.g., spaCy or NLTK). The analysis includes extracting the grammatical structure and keywords of the evaluation comments. The input is the evaluation comment "Good job," and the output is the analysis results (grammatical structure and keywords).

[1531] Step 4:

[1532] The server generates a prompt sentence to input the analysis results into the AI ​​model.

[1533] The server generates a prompt sentence to be input to the generative AI model based on the analysis results. For example, it generates a prompt sentence such as "Please convert the following abstract evaluation comment into a concrete evaluation comment: 'Good job'." The input is the analysis result, and the output is the prompt sentence.

[1534] Step 5:

[1535] The server inputs a prompt sentence into the generative AI model and generates a specific evaluation comment.

[1536] The server inputs the generated prompt into a generative AI model (e.g., GPT-4) to generate a specific evaluation comment. Based on the prompt, the generative AI model outputs a specific evaluation comment such as "You provided a high-quality deliverable within the project deadline." The input is the prompt, and the output is a specific evaluation comment.

[1537] Step 6:

[1538] The server transmits the generated specific evaluation comments to the terminal.

[1539] The server sends the generated specific evaluation comments to the terminal as an HTTP response. At this time, the evaluation comments are packaged again in JSON format. The input is the specific evaluation comments, and the output is the HTTP response to the terminal.

[1540] Step 7:

[1541] The terminal displays specific evaluation comments to the user.

[1542] The terminal displays the received specific evaluation comments to the user. For example, a comment such as "You provided a high-quality deliverable within the project deadline" is displayed on the user's screen. The input is the specific evaluation comment, and the output is the display to the user.

[1543] (Application example 1)

[1544] Next, a description will be given of Application Example 1 of Form 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."

[1545] Previous evaluation comments were abstract, making it difficult to convey specific details. Furthermore, in factory work evaluations, managers' evaluations of robots lacked specificity, making it difficult to accurately convey the evaluation details. This led to problems such as a decrease in the transparency and reliability of the evaluations, making it difficult to identify areas for improvement.

[1546] 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.

[1547] In this invention, the server includes means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, means for adding comments of improvement advice from a third-party perspective in accordance with the default style of the messenger app, means for using a generative AI model for converting evaluation comments into a specific form, and means for providing an interface for converting in-factory work evaluation comments into a specific form. As a result, evaluation comments are converted into a specific and clear form, and in-factory work evaluations can be accurately communicated.

[1548] "Artificial intelligence" is the technology that enables computer systems to learn, reason, and self-correct by imitating human intelligence.

[1549] An "evaluation comment" is written feedback given in response to a specific action or achievement.

[1550] "Converting succinctly, accurately, and specifically" means converting abstract evaluation comments into concise, accurate, and detailed content.

[1551] A "messenger app" is a software application for sending and receiving text and multimedia messages.

[1552] "Adding comments offering advice on improvement from a third-party perspective" means adding comments to the evaluation comments that point out areas for improvement from an objective point of view.

[1553] A "generative AI model" is a machine learning model that is trained by an artificial intelligence to perform a specific task.

[1554] An "interface" is the means or method by which a user interacts with a system.

[1555] The "format of the evaluation comment entry field" refers to a standard format or layout for inputting and displaying evaluation comments.

[1556] To put the present invention into practice, it is necessary to build a system for converting evaluation comments into concrete terms. This system includes a program that utilizes artificial intelligence to convert evaluation comments succinctly, accurately, and concretely.

[1557] The server first receives the evaluation comment entered by the user. This evaluation comment is often abstract, such as "You did a good job." The server then analyzes the evaluation comment using natural language processing technology and converts it into concrete content. At this time, it uses a generative AI model to generate prompt sentences that convert the evaluation comment into a concrete form.

[1558] Specifically, the server generates a prompt like this:

[1559] Please translate the following evaluation comments into specific, clear statements: Good job

[1560] This prompt is then input into the generative AI model to obtain a specific evaluation comment, such as "The parts were assembled within the specified time and met the quality standards."

[1561] The server then formats these specific evaluation comments to match the messaging app's default style and adds third-party advice for improvement, such as "Next time, please consider revising your work procedures to improve efficiency."

[1562] The specific evaluation comments and improvement advice generated in this way are sent to the user's device and displayed in the evaluation comment section. Through this interface, users can check the specific and clear evaluation comments and identify areas for improvement as needed.

[1563] By implementing this system, evaluation comments can be converted into specific and clear forms, enabling work evaluations to be accurately communicated within the factory. This improves the transparency and reliability of evaluations and makes it easier to identify areas for improvement.

[1564] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1565] Step 1:

[1566] The user inputs an evaluation comment.

[1567] Input: The user inputs an evaluation comment through the terminal.

[1568] Output: The entered evaluation comments are sent to the server.

[1569] Specific operation: The user uses the terminal interface to input an evaluation comment, such as "Good job." The input comment is sent to the server.

[1570] Step 2:

[1571] The server receives the evaluation comments and analyzes them using natural language processing technology.

[1572] Input: Rating comment submitted by user.

[1573] Output: Structured data of parsed rating comments.

[1574] Specific operation: The server analyzes the received evaluation comments using natural language processing techniques (e.g., morphological analysis and grammatical analysis) and generates structured data to understand the meaning and context of the evaluation comments.

[1575] Step 3:

[1576] The server uses a generative AI model to generate prompts that convert the evaluation comments into concrete forms.

[1577] Input: Parsed structured data of rating comments.

[1578] Output: The generated prompt statement.

[1579] Specific action: Based on the parsed evaluation comments, the server generates a prompt sentence such as the following: "Please convert the following evaluation comments into a specific and clear form: Good job."

[1580] Step 4:

[1581] The server inputs a prompt sentence into the generative AI model and obtains specific evaluation comments.

[1582] Input: The generated prompt statement.

[1583] Output: Specific evaluation comments.

[1584] Specific operation: The server inputs the prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) to generate a specific evaluation comment, such as "The parts assembly was completed within the specified time and met the quality standards."

[1585] Step 5:

[1586] The server formats specific evaluation comments according to the messenger app's standard style and adds comments offering advice on improvement from a third-party perspective.

[1587] Input: Specific evaluation comments.

[1588] Output: Formatted evaluation comments and improvement advice.

[1589] Specific actions: The server formats the specific evaluation comment to match the messaging app's default style and adds improvement advice, such as "Next time, please consider revising your work procedures to be more efficient."

[1590] Step 6:

[1591] The server sends the formatted evaluation comments and improvement advice to the user's terminal.

[1592] Input: Formatted evaluation comments and improvement suggestions.

[1593] Output: Evaluation comments and improvement advice displayed on the user's device.

[1594] Specific operation: The server sends the formatted evaluation comments and improvement advice to the user's device, and the user can check them through the device interface.

[1595] Example 2

[1596] Next, a description will be given of Example 2 of Form 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."

[1597] In conventional evaluation comment systems, evaluation comments are often abstract and lack specificity, making it difficult for the recipient to clearly understand how to improve. Furthermore, there is a lack of a way to add specific improvement advice to evaluation comments, which leads to a problem of reduced feedback quality. Furthermore, the evaluation comment format is not standardized, which can lead to a lack of consistency in the comments.

[1598] 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.

[1599] In this invention, the server includes: a means for a user to input an evaluation comment; a means for a terminal to send the evaluation comment to the server; a means for the server to receive the evaluation comment and perform text analysis; a means for the server to input the analysis results into a generative AI model and generate improvement advice; a means for the server to add the generated improvement advice to the original evaluation comment; a means for the server to return the final comment to the terminal; a means for the terminal to display the final comment to the user; and a means for providing a format for an evaluation comment entry field that implements these functions. This makes it possible to add specific improvement advice to evaluation comments, thereby improving the quality of feedback. Furthermore, by standardizing the evaluation comment format, consistent comments can be provided.

[1600] A "user" is an individual or group that uses the system to input evaluation comments.

[1601] A "terminal" is a device through which a user inputs evaluation comments and communicates with a server.

[1602] The "server" is a computer system that receives and analyzes evaluation comments, generates improvement advice using a generative AI model, and returns the final comments to the terminal.

[1603] An "evaluation comment" refers to the content of feedback entered by a user, and is text that includes an evaluation of a project or work.

[1604] "Text analysis" is an analytical process using natural language processing technology that the server performs to understand the content of the evaluation comments.

[1605] A "generative AI model" is an artificial intelligence model that generates specific improvement advice based on evaluation comments.

[1606] "Improvement advice" refers to specific improvements or suggestions that are added to the evaluation comments.

[1607] The "evaluation comment entry field format" is a unified interface for users to input evaluation comments and for the server to return the final comments.

[1608] This invention is a system that allows users to input evaluation comments and adds specific improvement advice to them. This system is composed of three main elements: the user, the terminal, and the server.

[1609] First, the user inputs an evaluation comment. The terminal used by the user provides an interface for inputting the evaluation comment. This interface has a standardized format for the evaluation comment entry field, making it easy for the user to input the evaluation comment.

[1610] The terminal then transmits the evaluation comments entered by the user to the server, which uses natural language processing technology to analyze the received evaluation comments. Through this analysis, the content of the evaluation comments is understood.

[1611] The server inputs the analysis results into a generative AI model. For example, OpenAI's GPT-4 is used for this generative AI model. The generative AI model generates specific improvement advice based on the input evaluation comments. The generated improvement advice is added to the evaluation comments.

[1612] As a concrete example, suppose a user enters the following rating comment:

[1613] "We delivered high-quality deliverables within the project deadline."

[1614] The server parses this comment and inputs the following prompt into the generative AI model:

[1615] "Evaluation comment: High-quality deliverables were delivered within the project deadline. Please add any suggestions for improvement."

[1616] The generative AI model generates improvement advice such as:

[1617] "Why not consider a more efficient workflow for your next project?"

[1618] The server adds this improvement advice to the original rating comment to generate the final comment:

[1619] "We delivered high-quality deliverables within the project deadline. Why not consider a more efficient workflow for the next project?"

[1620] The final comments are sent back from the server to the terminal, which then displays them to the user, who can then check the evaluation comments with the added advice for improvement.

[1621] This system allows users to add specific advice for improvement to evaluation comments, improving the quality of feedback. Also, by standardizing the format of evaluation comments, users can provide consistent comments.

[1622] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1623] Step 1:

[1624] The user inputs an evaluation comment.

[1625] The user enters a review comment in the review comment input field of the messenger app. For example, the user might enter "They provided high-quality deliverables within the project deadline." The review comment is then sent to the device.

[1626] Step 2:

[1627] The terminal transmits the evaluation comment to the server.

[1628] The terminal transmits the evaluation comments entered by the user to the server in an appropriate format. The input is the evaluation comments, and the output is the data to be sent to the server.

[1629] Step 3:

[1630] The server receives the evaluation comments and performs text analysis.

[1631] The server receives the evaluation comments sent from the terminal. After receiving the evaluation comments, the server performs text analysis using natural language processing technology to understand the content of the evaluation comments. The input is the evaluation comments, and the output is the analysis results.

[1632] Step 4:

[1633] The server inputs the analysis results into a generative AI model to generate improvement advice.

[1634] The server inputs the analysis results into a generative AI model (e.g., GPT-4). The generative AI model generates specific improvement advice based on the input evaluation comments. The input is the analysis results, and the output is improvement advice.

[1635] Step 5:

[1636] The server adds the generated improvement advice to the original evaluation comment.

[1637] The server adds the improvement advice obtained from the generative AI model to the original evaluation comment. This results in an evaluation comment that reads, "You delivered a high-quality deliverable within the project deadline. For the next project, we suggest you consider a more efficient workflow." The input is the improvement advice and the original evaluation comment, and the output is the final comment.

[1638] Step 6:

[1639] The server sends the final comment back to the terminal.

[1640] The server returns the final comment to the terminal, sending it in the appropriate format. The input is the final comment, and the output is the data sent to the terminal.

[1641] Step 7:

[1642] The terminal displays the final comment to the user.

[1643] The terminal displays the final comments received from the server to the user. The user can check the evaluation comments to which improvement advice has been added. The input is the final comments, and the output is the display data for the user.

[1644] (Application example 2)

[1645] Next, a description will be given of Application Example 2 of Form 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."

[1646] In order to improve work efficiency in factories, it is important to provide specific improvement advice based on the evaluation comments of workers and robots. However, the current system does not efficiently collect evaluation comments, generate appropriate improvement advice, and notify it to workers and managers. This poses the issue of not achieving sufficient improvements in work efficiency.

[1647] 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.

[1648] In this invention, the server includes means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, means for adding improvement advice comments from a third-party perspective in accordance with the default style of the messenger app, means for collecting evaluation comments from workers and robots in the factory, means for generating specific improvement advice using a generative AI model based on the collected evaluation comments, means for notifying workers and managers of the generated improvement advice, and means for providing a format for an evaluation comment entry field that implements these functions. This makes it possible to efficiently carry out the process from collecting evaluation comments to generating and notifying improvement advice, thereby improving work efficiency in the factory.

[1649] "Artificial intelligence" is the technology that enables computer systems to learn, reason, and self-correct by imitating human intelligence.

[1650] An "evaluation comment" is a sentence that describes an evaluation of the work of a worker or robot.

[1651] A "messenger app" is application software for sending and receiving text messages and multimedia messages.

[1652] A "third-party perspective" refers to an objective viewpoint other than that of the evaluator or the person being evaluated.

[1653] "Improvement advice" is a specific proposal for improving the efficiency and quality of work based on the evaluation comments.

[1654] "In-plant" means the interior of a facility where manufacturing operations take place.

[1655] "Workers" refers to personnel who perform manufacturing work within a factory.

[1656] A "robot" is a mechanical device that performs tasks automatically according to programmed instructions.

[1657] A "generative AI model" is a model that uses artificial intelligence technology to generate text and data.

[1658] "Notification" is the act of conveying information to a specific recipient.

[1659] The "evaluation comment entry field" is an interface for inputting and displaying evaluation comments.

[1660] A "format" is a framework for organizing and arranging data or information in a particular way.

[1661] A system for implementing this invention is configured as follows: First, the server uses artificial intelligence to convert evaluation comments into concise, accurate, and specific ones. Next, it adds improvement advice comments from a third-party perspective in accordance with the default style of the messenger app. Furthermore, it collects evaluation comments from workers and robots in the factory and generates specific improvement advice using a generative AI model based on the collected evaluation comments. Finally, it notifies the generated improvement advice to workers and managers.

[1662] Hardware and software used

[1663] Hardware: Servers, smartphones, tablets, factory computers

[1664] Software: Python 3.x, OpenAI API, messenger app

[1665] Data processing and calculation

[1666] The server first collects evaluation comments from workers and robots in the factory. These evaluation comments are sent to the server in text format. The server then analyzes the collected evaluation comments using natural language processing technology and generates specific improvement advice using a generative AI model (OpenAI's GPT-3). This generated improvement advice is added to the evaluation comments and ultimately notified to workers and managers.

[1667] Specific examples

[1668] For example, if evaluation comments are collected that Robot A quickly assembled parts in a factory, the server inputs the following prompt sentence into the generative AI model:

[1669] Prompt Sentence Examples

[1670] Evaluation comments: Robot A assembled the parts quickly.

[1671] Improvement advice:

[1672] The generative AI model generates specific improvement advice based on this prompt. For example, it might generate advice such as, "Next time, consider optimizing the placement of parts to further increase efficiency." This advice is added to the evaluation comments and notified to the worker or manager via smartphone or tablet.

[1673] In this way, the process from collecting evaluation comments to generating and notifying improvement advice can be carried out efficiently, making it possible to improve work efficiency within the factory.

[1674] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1675] Step 1:

[1676] The server collects evaluation comments from workers and robots in the factory.

[1677] Input: Evaluation comments from workers and robots (text format)

[1678] Output: Collected evaluation comments

[1679] Specific operation: A worker or a robot inputs an evaluation comment, which is sent to the server, which stores it in a database.

[1680] Step 2:

[1681] The server analyzes the collected evaluation comments using natural language processing technology.

[1682] Input: Collected evaluation comments

[1683] Output: Parsed rating comments

[1684] Specific operation: The server passes the evaluation comments to a text analysis engine to analyze grammar and semantics. The analysis results are used as part of the prompt sentence to input to the generative AI model.

[1685] Step 3:

[1686] The server generates specific improvement advice using a generative AI model based on the analyzed evaluation comments.

[1687] Input: Parsed rating comments

[1688] Output: Generated improvement advice

[1689] Specific operation: The server inputs the analyzed evaluation comments as prompt sentences into the generative AI model, which then generates specific improvement advice based on the prompt sentences.

[1690] Step 4:

[1691] The server adds the generated improvement advice to the evaluation comment.

[1692] Input: Generated improvement advice, evaluation comments

[1693] Output: Evaluation comment with improvement advice added

[1694] Specific behavior: The server appends the generated improvement advice to the original rating comment and formats it as a complete rating comment.

[1695] Step 5:

[1696] The server notifies the worker or manager of the evaluation comment with the added improvement advice.

[1697] Input: Evaluation comment with improvement advice added

[1698] Output: Notification to workers and managers

[1699] Specific operation: The server sends the evaluation comments with additional improvement advice to the worker or manager via a messenger app or notification system. The notification is displayed on the worker's smartphone or tablet.

[1700] Example 3

[1701] Next, a third embodiment of the third embodiment will be described. 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."

[1702] In conventional evaluation and comment systems, the evaluation comments written by users were often inconsistent, and specific improvement advice was often not provided. Furthermore, the analysis of evaluation comments and the generation of improvement advice were done manually, which was time-consuming and labor-intensive. This resulted in issues such as a lack of fairness and transparency in evaluations and a decline in user satisfaction.

[1703] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1704] In this invention, the server includes means for providing an interface for users to write evaluation comments, means for analyzing the evaluation comments using artificial intelligence on the interface and generating improvement advice, and means for presenting the generated improvement advice to the user, thereby improving the consistency and specificity of the evaluation comments and maintaining the fairness and transparency of the evaluations.

[1705] "User" means an individual or organization that uses the system to post evaluation comments and receive advice on improvements.

[1706] An "interface" is the screen or application operating part that allows users to input and submit evaluation comments.

[1707] "Artificial intelligence" refers to the machine learning models and algorithms used to analyze evaluation comments and generate improvement advice.

[1708] "Evaluation comments" are feedback and opinions written by users about products and services.

[1709] "Improvement advice" is specific suggestions and feedback generated by artificial intelligence by analyzing evaluation comments.

[1710] The "server" is a computer system that receives evaluation comments from users, analyzes them using artificial intelligence, and generates improvement advice.

[1711] "Format" refers to the consistent format and layout of the evaluation comment field, and is a structure that makes it easy for users to write evaluation comments.

[1712] "Natural language processing technology" is a technology used by artificial intelligence to analyze evaluation comments, and is a method for understanding text data and extracting meaning.

[1713] The present invention is a system that allows users to write evaluation comments, analyzes the comments using artificial intelligence, and generates specific advice for improvement. Specific embodiments of this system are described below.

[1714] Hardware and software used

[1715] Hardware: Servers, devices (PCs, smartphones, tablets, etc.)

[1716] Software: Generative AI model, evaluation comment writing module, improvement advice addition module

[1717] System configuration

[1718] 1. User Interface

[1719] The user accesses a web page or application provided by the evaluation comment writing module using a terminal. This interface includes UI elements such as a text box for inputting evaluation comments and a submit button.

[1720] 2. Enter and submit your evaluation comments

[1721] The user enters their review comments in a text box on the interface, for example, "This product is easy to use, but the battery life is poor." Once they are done, they click the "Submit" button.

[1722] 3. Receipt of rating comments by the server

[1723] The evaluation comments sent from the device are sent to the server, which receives the comments and stores them in a database.

[1724] 4. Analysis using generative AI models

[1725] The server passes the saved evaluation comments to a generative AI model for analysis, which uses natural language processing technology to understand the content of the comments.

[1726] 5. Generating Improvement Advice

[1727] Based on the analysis results of the generative AI model, the server calls the improvement advice addition module and generates specific improvement advice, such as "To extend battery life, consider improving the following: 1. Increase battery capacity. 2. Optimize software to reduce power consumption. 3. Add a power-saving mode."

[1728] 6. Providing advice to users

[1729] The server sends the generated improvement advice back to the user and displays it on the terminal interface, where the user can review it and modify the evaluation comments as necessary.

[1730] Specific examples

[1731] Example of a review comment: "This product is easy to use, but the battery life is poor."

[1732] Example prompt for a generative AI model: "If a user complains about the battery life of a product, what improvement advice should you provide?"

[1733] This system allows users to write evaluation comments in a consistent format, and the operation of the generative AI model and the improvement advice addition module ensures fairness and transparency of the evaluation. The flow of the identification process in Example 3 will be explained using Figure 15.

[1734] Step 1:

[1735] The user accesses the rating and comment writing interface.

[1736] Input: A user uses a device (PC, smartphone, tablet, etc.) to access the web page or application provided by the evaluation comment writing module.

[1737] Specific operation: The user opens a browser and enters the specified URL to access the site. The interface displays a text box for entering evaluation comments and a submit button.

[1738] Output: The user can now enter a rating comment.

[1739] Step 2:

[1740] The user enters and submits an evaluation comment.

[1741] Input: The user enters a rating comment in a text box on the interface.

[1742] Specific action: For example, enter "This product is easy to use, but the battery life is poor." After completing the entry, the user clicks the "Submit" button.

[1743] Output: The rating comment is sent from the device to the server.

[1744] Step 3:

[1745] The server receives the rating comments.

[1746] Input: Rating comment sent from the device.

[1747] Specific operation: The server receives the HTTP request, analyzes the rating comments, and stores them in a database.

[1748] Output: The rating comments are saved in the database.

[1749] Step 4:

[1750] The server analyzes the evaluation comments using a generative AI model.

[1751] Input: Rating comments stored in the database.

[1752] Specific operation: The server inputs the evaluation comments in text format into the generative AI model and obtains the analysis results. The generative AI model uses natural language processing technology to understand the content of the comments.

[1753] Output: Analysis results are generated.

[1754] Step 5:

[1755] The server generates advice using the improvement advice addition module.

[1756] Input: Analysis results of the generative AI model.

[1757] Specific operation: Based on the analysis results, the server calls the improvement advice addition module and generates specific improvement advice. For example, the advice generated might be, "To extend battery life, consider improving the following: 1. Increase battery capacity. 2. Optimize software to reduce power consumption. 3. Add a power-saving mode."

[1758] Output: Improvement advice is generated.

[1759] Step 6:

[1760] The server sends the generated advice back to the user

[1761] Input: The generated improvement advice.

[1762] Specific operation: The server generates an HTTP response and sends data including improvement advice to the terminal.

[1763] Output: Improvement advice is displayed on the terminal interface.

[1764] Step 7:

[1765] The user checks the improvement advice and modifies the evaluation comments as necessary.

[1766] Input: Improvement advice displayed on the terminal interface.

[1767] Specific behavior: The user reads the displayed advice, re-edits the rating comment, and resubmits it.

[1768] Output: The corrected rating comment is sent to the server again.

[1769] (Application example 3)

[1770] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1771] In conventional evaluation and comment systems, users often leave inconsistent comments that lack specificity and accuracy. Furthermore, there is a lack of specific advice on how to improve the quality of reviews, making it difficult for users to provide useful information for other users. Furthermore, writing reviews is cumbersome, making it difficult for users to easily write high-quality reviews.

[1772] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes: means for utilizing artificial intelligence to convert evaluation comments succinctly, accurately, and specifically; means for adding improvement advice comments from a third-party perspective in accordance with the default style of the messenger app; means for providing a format for the evaluation comment entry field that implements these functions; means for providing an interface for users to write product reviews; means for an artificial intelligence module to operate on the interface and analyze the content of the user's review; means for an improvement advice addition module to provide advice for improving the quality of the review in real time; and means for presenting guidelines for writing reviews in a consistent format. This enables users to easily write high-quality reviews and makes it easier for them to provide information that is useful to other users.

[1773] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1774] An "evaluation comment" is a description of a user's opinion or impression about a particular product or service.

[1775] A "messenger app" is a software application for sending and receiving text and multimedia messages over the Internet.

[1776] A "third-party perspective" is an objective viewpoint from the standpoint of a third party who is not a party involved when making an evaluation or giving an opinion.

[1777] A "format" is a framework for arranging data or information in a specific form or structure.

[1778] An "interface" is the means or method by which a user interacts with a system or application.

[1779] An "artificial intelligence module" is an artificial intelligence component designed to perform a specific task.

[1780] "Analysis" is the process of examining data or information in detail to understand its structure and meaning.

[1781] The "improvement advice addition module" is a component for providing specific advice for improving quality based on user input.

[1782] "Guidelines" are guidelines or standards for performing specific actions or tasks.

[1783] A system for carrying out this invention comprises a server and a user terminal. The server includes means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, means for adding comments of improvement advice from a third-party perspective in accordance with the specified style of the messenger app, means for providing a format for the evaluation comment entry field that implements these functions, means for providing an interface for users to write product reviews, means for an artificial intelligence module to operate on the interface and analyze the content of the user's review, means for an improvement advice adding module to provide advice for improving the quality of the review in real time, and means for presenting guidelines so that reviews can be written in a consistent format.

[1784] Hardware and software used

[1785] Server: A server for hosting the Flask application.

[1786] User device: Smartphone

[1787] Software: Flask (a Python web framework), OpenAI API (an API for using generative AI models)

[1788] Data processing and calculation

[1789] 1. User device: The user enters the review on the smartphone app.

[1790] 2. Server: The entered review is sent to the Flask server.

[1791] 3. Server: The Flask server calls the OpenAI API and parses the reviews.

[1792] 4. Server: The generative AI model analyzes the reviews and generates improvement advice.

[1793] 5. Server: The Flask server returns the generated advice to the user.

[1794] Specific examples

[1795] If a user writes a review saying, "This product was very good. It was easy to use and convenient," the generative AI model will provide advice such as, "Your review will be even better if you add specific usage scenarios and information that would be useful to other users."

[1796] Prompt Sentence Examples

[1797] Please analyze the following reviews and provide your suggestions for improvement:

[1798] This product was very good. It was easy to use and convenient.

[1799] In this way, users can easily write high-quality reviews, making it easier for them to provide useful information to other users.

[1800] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1801] Step 1:

[1802] A user starts the smartphone app and enters a product review. The entered review is sent from the user's device to the server. The input data is the text review written by the user.

[1803] Step 2:

[1804] The server processes the received reviews using a Flask application, which prepares to call the OpenAI API to parse the reviews. The input data is the text review written by the user, and the output data is a prompt to send to the OpenAI API.

[1805] Step 3:

[1806] The server calls the OpenAI API and sends a prompt. The prompt contains instructions for analyzing the review written by the user and generating improvement advice. The input data is the prompt, and the output data is the improvement advice generated by the generative AI model.

[1807] Step 4:

[1808] The server receives the improvement advice returned from the OpenAI API. The received advice is sent back to the user device along with the user's review. The input data is the improvement advice generated by the generative AI model, and the output data is the review and advice sent back to the user device.

[1809] Step 5:

[1810] The user terminal displays the reviews and improvement advice received from the server. The user can modify or add to the review based on the displayed advice. The input data are the reviews and advice returned from the server, and the output data are the reviews modified or added by the user.

[1811] Step 6:

[1812] When the user finalizes the review and presses the submit button, the review is sent to the server again and saved as the final review. The input data is the final review with any corrections or additions made by the user, and the output data is the final review saved on the server.

[1813] 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.

[1814] "Example 1"

[1815] One embodiment of the present invention combines a system that includes a means for converting evaluation comments succinctly, accurately, and specifically, a means for adding improvement advice comments from a third-party perspective in accordance with the default style of a messaging app, and a means for providing a format for the evaluation comment entry field that implements these functions, with an emotion engine that recognizes user emotions. This emotion engine identifies emotional elements contained in the evaluation comments and converts the evaluation comments and generates improvement advice based on those elements. Specifically, from an evaluation comment such as "This project was very enjoyable," the emotion "fun" is extracted, and based on that, improvement advice is generated such as "We recommend that you work with the same team members on the next project so that you can have a similar enjoyment."

[1816] "Example 2"

[1817] In another embodiment, the emotion engine analyzes the user's emotions based on the evaluation comments and uses the results to convert the evaluation comments and generate improvement advice. In this case, the emotion engine extracts the emotion "difficult" from the evaluation comment "This project was very difficult," and based on that, generates improvement advice such as "We recommend assigning easier tasks to the next project."

[1818] "Example 3"

[1819] In another embodiment, the evaluation comment entry field format provides an interface for accepting user input, and the emotion engine operates on that interface. In this case, the user directly enters the evaluation comment into the interface, and the emotion engine analyzes the input in real time. Then, based on the analysis results, the evaluation comment is converted and improvement advice is generated, and this is fed back to the user.

[1820] The processing flow of each embodiment will be described below.

[1821] "Example 1"

[1822] Step 1: The user enters their evaluation comments into the system.

[1823] Step 2: The emotion engine extracts emotional elements from the evaluation comments.

[1824] Step 3: Based on the extracted sentiment, the evaluation comments are converted and improvement advice is generated.

[1825] Step 4: Provide the generated improvement advice to the user as feedback.

[1826] "Example 2"

[1827] Step 1: The user enters their evaluation comments into the system.

[1828] Step 2: The sentiment engine analyzes the rating comments and extracts the user's sentiment.

[1829] Step 3: Based on the extracted sentiment, the evaluation comments are converted and improvement advice is generated.

[1830] Step 4: Provide the generated improvement advice to the user as feedback.

[1831] "Example 3"

[1832] Step 1: The user enters the evaluation comment directly into the system interface.

[1833] Step 2: The emotion engine analyzes the user's input in real time.

[1834] Step 3: Based on the analysis results, the evaluation comments are converted and improvement advice is generated. Step 4: The generated improvement advice is fed back to the user in real time.

[1835] Example 1

[1836] Next, a description will be given of Example 1 of Form 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."

[1837] Conventional evaluation and comment systems have difficulty converting abstract evaluation comments into concrete, clear forms, and are unable to provide improvement advice that takes into account the user's feelings. As a result, evaluation comments are vague, and it is difficult to obtain specific feedback or areas for improvement. Furthermore, it is difficult to provide comments that fit the default style of the messaging app.

[1838] 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.

[1839] In this invention, the server includes means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence, means for adding improvement advice comments from a third-party perspective in accordance with the default style of the messenger app, means for providing a format for the evaluation comment entry field that implements these functions, and means for identifying emotional elements included in the evaluation comments using an emotion engine that recognizes user emotions and converting the evaluation comments and generating improvement advice based on the identified emotional elements. This makes it possible to convert evaluation comments into a specific and clear format and provide improvement advice that takes the user's emotions into consideration.

[1840] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1841] An "evaluation comment" is a piece of text that describes feedback or opinions about a specific action or outcome.

[1842] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[1843] A "messenger app" is a software application for sending and receiving text and multimedia messages.

[1844] An "emotion engine" is a technology for extracting and analyzing emotional elements from data such as text and voice.

[1845] A "format" is a framework for arranging data or information in a specific form or structure.

[1846] An "interface" is a part that provides the means and methods for a user to interact with a system.

[1847] "Improvement advice" is specific suggestions or advice for improving a particular behavior or outcome.

[1848] MODE FOR CARRYING OUT THE INVENTION

[1849] This invention is a system that converts evaluation comments succinctly, accurately, and specifically, and provides emotion-based improvement advice. This system is realized by combining artificial intelligence, natural language processing technology, and an emotion engine.

[1850] 1. Generate the system program

[1851] The user uses an interface for inputting evaluation comments. This interface is provided as a text box on a web browser, etc. When the user inputs an evaluation comment, the comment is sent to the server.

[1852] 2. Explain the program's processing in natural language

[1853] The server uses Python's natural language processing libraries, NLTK and spaCy, to analyze the grammatical structure of the evaluation comments received from users and extract elements such as subjects, predicates, and objects.

[1854] Next, the server converts the evaluation comments into concrete, clear comments based on the analysis results. For example, a comment such as "This project was a lot of fun" can be converted into "I recommend that you work with the same team members on the next project so that you can have the same fun experience."

[1855] The server then uses IBM Watson's sentiment analysis API to identify the emotional components of the evaluation comments. Based on the identified emotions, the server generates improvement advice. For example, based on the emotion "fun," the server generates advice such as "recommend having the same team members participate in the next project so that you can have a similarly enjoyable experience."

[1856] 3. Add examples to your description

[1857] As a specific example, the processing when the following evaluation comment is input will be shown.

[1858] Entered evaluation comment:

[1859] "This project was a lot of fun."

[1860] Evaluation comments after conversion:

[1861] "We encourage you to join the same team members so that you can have the same fun on your next project."

[1862] Example prompts to input to a generative AI model:

[1863] "Transform the following evaluation comment into a specific, clear form and add emotion-based suggestions for improvement. Evaluation comment: 'I had a lot of fun on this project.'"

[1864] In this way, users can utilize a system that converts evaluation comments into concrete and clear forms and provides emotion-based improvement advice. This system can improve the quality of evaluation comments and increase user satisfaction by providing specific feedback and suggestions for improvement.

[1865] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1866] Step 1:

[1867] The user inputs an evaluation comment.

[1868] The user enters an evaluation comment in a text box on the web browser. For example, the user enters "I really enjoyed this project." The entered comment is sent to the server.

[1869] Step 2:

[1870] The server receives the rating comments.

[1871] The server receives the evaluation comments sent by the users and temporarily stores them in a database. The received comments become input data for the next analysis step.

[1872] Step 3:

[1873] The server analyzes the evaluation comments using natural language processing technology.

[1874] The server uses Python's natural language processing libraries NLTK and spaCy to analyze the grammatical structure of the evaluation comments. Specifically, it extracts elements such as the subject, predicate, and object of the comment. For example, from the comment "This project was very fun," it extracts the elements "project" and "fun." The analysis results become the input data for the next conversion step.

[1875] Step 4:

[1876] The server converts the evaluation comments into a concrete and clear form based on the analysis results.

[1877] The server converts the evaluation comments into concrete, clear forms based on the analysis results. For example, a comment such as "This project was very enjoyable" can be converted into "I recommend that you work with the same team members on the next project so that you can have the same enjoyment." The converted comments become input data for the next sentiment analysis step.

[1878] Step 5:

[1879] The server uses an emotion engine to identify emotional elements contained in the evaluation comments.

[1880] The server uses IBM Watson's sentiment analysis API to identify the emotional elements contained in the evaluation comments. For example, it extracts the emotion "fun." The results of the sentiment analysis become input data for the next step, which is generating improvement advice.

[1881] Step 6:

[1882] The server generates improvement advice based on the emotion.

[1883] The server generates improvement advice based on the identified emotion. For example, based on the emotion "fun," it generates advice such as "recommend participating in the next project with the same team members so that you can feel the same enjoyment." The generated improvement advice becomes the final output data.

[1884] Step 7:

[1885] The server returns the converted evaluation comments and improvement advice to the user.

[1886] The server then returns the converted evaluation comments and advice for improvement to the user. The user can view this information through the system interface. For example, in a web browser, the user might see a comment and advice such as, "We recommend that you work with the same team members on your next project so that you can have the same fun."

[1887] (Application example 1)

[1888] Next, a description will be given of Application Example 1 of Form 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."

[1889] Conventional evaluation and comment systems have the problem that many of the evaluation comments are abstract, making it difficult to obtain specific feedback. Furthermore, there is a lack of improvement advice that takes emotional factors into consideration, which can lead to a decline in the quality of the evaluation comments. Furthermore, while specific and clear feedback is required for work evaluations within factories, there is a lack of means to achieve this.

[1890] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes: means for converting evaluation comments succinctly, accurately, and specifically using artificial intelligence; means for adding improvement advice comments from a third-party perspective in accordance with the default style of the messenger app; means for providing a format for the evaluation comment entry field that implements these functions; means for identifying emotional elements contained in the evaluation comments using an emotion engine and converting the evaluation comments and generating improvement advice based on the identified emotional elements; and means for providing a work evaluation feedback system to be installed in a factory robot. This makes it possible to generate specific and clear evaluation comments and provide improvement advice that takes emotional elements into consideration.

[1891] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and learn, reason, and self-correct.

[1892] An "evaluation comment" is a piece of writing that expresses opinions or feedback about a specific action or result.

[1893] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language.

[1894] An "emotion engine" is a technology that extracts emotional elements from text data and generates appropriate responses and actions based on them.

[1895] A "messenger app" is a software application for sending and receiving text message...

Claims

1. A means for analyzing the user's emotions based on the user's evaluation comments; A means for converting the user's evaluation comment succinctly and specifically based on the analyzed user's emotion using a generation AI; A means for generating specific improvement advice based on the evaluation comments and the user's feelings using the generation AI; means for adding the generated improvement advice to the evaluation comment; A system including:

2. The generating means generates the improvement advice from a third-party perspective. The system of claim 1 .

3. The converting means converts the evaluation comment based on a prompt sentence corresponding to the emotion of the user, the generating means generates the improvement advice based on a prompt sentence corresponding to the emotion of the user. The system of claim 1 .

Images