System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting historical data of an individual; means for analyzing the collected data to identify strengths and efforts of the individual; means for generating personalized rewards based on the identified strengths and efforts; means for presenting the generated rewards to the individual; means for collecting performance data of the individual after the presentation of the rewards; and means for analyzing the collected performance data to evaluate the effect of the rewards and update a reward generation algorithm.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] Previous compliment generation systems only provided generic compliments and were unable to provide personalized, effective compliments based on individual characteristics and past performance. This limited the effectiveness of compliments, and they were unable to fully improve performance after receiving a compliment. Furthermore, there was a lack of a way to use the effectiveness of compliments as feedback to improve the compliment generation algorithm for future use. [Means for solving the problem]

[0005] The present invention provides a system including: means for collecting past data of an individual; means for analyzing the collected data to identify the strengths and efforts of the individual; means for generating personalized compliments based on the identified strengths and efforts; means for presenting the generated compliments to the individual; means for collecting performance data of the individual after the compliments have been presented; and means for analyzing the collected performance data to evaluate the effectiveness of the compliments and update a compliment generation algorithm. This system enables more effective compliments by providing individually optimized compliments, thereby promoting improved performance after receiving a compliment.

[0006] "Individual past data" refers to information about an individual's past achievements, efforts, and evaluations, such as project completion reports, final evaluations, and feedback.

[0007] "Means of collecting data" refers to the mechanism by which past data on individuals is collected in an appropriate manner and prepared for analysis.

[0008] "Means of analyzing data" refers to the process of analyzing collected data using natural language processing techniques and extracting useful information.

[0009] "Means for identifying individual strengths and efforts" is a method that uses the results of data analysis to clarify the characteristics that individuals possess and the special efforts they have made in the past.

[0010] "Method of generating personalized praise" is the process of creating specific praise that is tailored to an individual based on their identified strengths and efforts.

[0011] The "means for presenting compliments" is a mechanism for providing the generated compliments to individuals in an appropriate format, such as via notifications or dashboard displays.

[0012] "Means for collecting individual performance data" refers to methods for continuously monitoring and recording an individual's achievements and progress after receiving praise.

[0013] "Means for analyzing performance data" refers to the process of analyzing the collected performance data and evaluating the effectiveness of praise.

[0014] The "means for updating the compliment generation algorithm" is a mechanism for improving the compliment generation process from the next time onwards based on the results of analyzing performance data. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention is a system that uses generative AI to provide individually optimized compliments. The system includes three entities: a server, a terminal, and a user, which work together to perform the following steps:

[0037] Data Collection Phase

[0038] The server first issues a request to collect past data about an individual (user). The data includes project completion reports, final evaluations, feedback, etc., and is stored on the user's device. The user's device is responsible for sending this data to the server.

[0039] Data analysis phase

[0040] The server analyzes the received data and identifies individual strengths and efforts. Specifically, it uses natural language processing technology to extract useful keywords and phrases from the collected text data. For example, it identifies characteristics such as "leadership" and "creative problem solving" from project reports.

[0041] Compliment generation phase

[0042] The server then generates the optimal compliment based on the analysis results. First, it selects a compliment template that corresponds to the identified strengths and efforts. Then, it creates a compliment that is optimized for each individual user based on that template. During this process, it incorporates the user's specific achievements and name to enhance specificity and personalization.

[0043] Feedback gathering phase

[0044] The device presents the generated compliment to the user. After presenting the compliment, the device continuously monitors and records new performance data of the user, thereby collecting data that measures the impact of the compliment.

[0045] Learning Phase

[0046] The server analyzes the collected new performance data and evaluates the effectiveness of the compliments. It identifies whether a particular compliment was effective and uses the results as feedback to improve the algorithm. This cycle allows the server to constantly learn in order to generate more effective compliments.

[0047] ---

[0048] For example, a server collects reports of recently completed projects from users and analyzes them to identify strengths such as leadership and creative problem-solving. Based on the results, the server generates a compliment like this:

[0049] "Your recent project was particularly impressive, especially the way you led your team to come up with creative solutions. Your leadership skills are truly impressive!"

[0050] The praise is then displayed on the user's device, and the user is motivated by the praise to take on a new project. The progress and results are recorded by the device, and the server analyzes the data again to evaluate the effectiveness of the praise.

[0051] Through this process, the system continues to provide the user with more appropriate and effective praise, promoting personal growth.

[0052] The processing flow will be explained below.

[0053] Step 1: Submit a data request

[0054] The server requests past data from the user's device, specifically specifying data such as project completion reports, final evaluations, and feedback.

[0055] Step 2: Collect data

[0056] The user's device searches and collects the specified data from the local storage, and if the data is found, sends it to the server.

[0057] Step 3: Receiving and Preprocessing Data

[0058] The server receives the data sent from the terminal and performs preprocessing, which unifies the data format and converts it into a format that is easy to analyze.

[0059] Step 4: Text analysis of the data

[0060] The server analyzes the collected text data using natural language processing technology, specifically, keyword extraction, morphological analysis, and context analysis.

[0061] Step 5: Identify strengths and efforts

[0062] The server identifies the user's strengths and efforts from the analysis results, for example, by extracting evaluation items such as "leadership" and "creative problem solving."

[0063] Step 6: Select a compliment template

[0064] The server selects from a database praise templates that correspond to the identified strengths and efforts.

[0065] Step 7: Personalize your compliment

[0066] The server then generates a personalized compliment based on the selected template, incorporating the user's name and specific achievements.

[0067] Step 8: Send a compliment

[0068] The server transmits the generated compliment to the user's terminal.

[0069] Step 9: Offer a compliment

[0070] The device will notify the user of any compliments received, including via a pop-up notification or display on the dashboard.

[0071] Step 10: Monitor performance data

[0072] The device continuously monitors and records new performance data of the user after the praise is given, such as the progress and deliverables of a new project.

[0073] Step 11: Submitting feedback data

[0074] The terminal transmits the collected performance data to the server.

[0075] Step 12: Analyze the feedback data

[0076] The server analyzes the feedback data sent from the device and evaluates the effectiveness of the compliments, checking whether a particular compliment was effective.

[0077] Step 13: Update the algorithm

[0078] The server updates the compliment generation algorithm based on the evaluation results, thereby improving the compliment generation algorithm to be more effective.

[0079] Through this series of steps, the generative AI continues to provide the user with optimized praise, helping to increase their motivation and improve their performance.

[0080] Example 1

[0081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0082] Conventional compliment generation systems lacked a means to effectively provide personalized compliments to individuals. Furthermore, there was no way to evaluate the impact of compliments on the user's performance and reflect that feedback in the generation of next compliments. This made it difficult to provide sustained support for improving motivation.

[0083] 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.

[0084] In this invention, the server includes: means for collecting past data of an individual; means for analyzing the collected data to identify the individual's strengths and efforts; means for generating personalized compliments based on the identified strengths and efforts; means for presenting the generated compliments to the individual; means for collecting performance data of the individual after the compliments have been presented; means for analyzing the collected performance data to evaluate the effectiveness of the compliments and updating the compliment generation algorithm; means for including a series of programs for performing multiple data processing phases; means for using a communication protocol required for transmitting and receiving data; means for generating compliments corresponding to the identified strengths and efforts using generative AI technology; and means for inputting prompt sentences into the generative AI model. This makes it possible to continuously provide personalized compliments and improve user motivation.

[0085] "Personal historical data" refers to information related to a user's past activities and achievements, including work reports, evaluation results, and feedback comments.

[0086] "Means of collection" refers to the method or device used to collect data. It refers to the communication protocol or software used by the server to obtain data from the user's device.

[0087] "Means of analysis" refers to the technologies, algorithms, and software used to analyze data. Specifically, this includes natural language processing technology and data analysis algorithms.

[0088] "Means for identifying strengths and efforts" refers to a method for identifying users' advantages and efforts from the collected data. This is achieved using natural language processing techniques.

[0089] A "compliment generator" is a method or device that generates optimal compliments for a user, using generative AI technology to create compliments that correspond to specific strengths or efforts.

[0090] The "presenting means" refers to a method or device for showing the generated compliment to the user. This is done through the terminal.

[0091] "Performance data" is information related to new user activity and achievements collected after the praise is given.

[0092] The "measures for evaluation and updating" are methods for analyzing collected performance data, measuring the effectiveness of praise, and improving the algorithm.

[0093] The "data processing phase" refers to a series of processing steps: data collection, analysis, praise generation, presentation, feedback collection, and learning.

[0094] A "communications protocol" is a set of rules or standardized methods used to send and receive data. Examples include HTTPS.

[0095] "Generative AI technology" is an artificial intelligence technology that generates natural language based on specific input. The generative AI model uses this technology to create compliments.

[0096] A "prompt" is text that is input to a generative AI model, which then generates an appropriate compliment.

[0097] This invention is a system that uses generative AI to provide individually optimized compliments. The system mainly consists of three entities: a server, a device, and a user. These entities work together to perform the following processes:

[0098] The server first issues a request to collect past data for an individual (user). This request is sent to the user's device via the HTTP protocol. For example, an Amazon Web Services (AWS) EC2 instance is used as the server, and Apache or Nginx is used to send and receive data. The user's device (smartphone or PC) sends data via a client application that sends text data such as project completion reports, evaluation results, and feedback comments to the server.

[0099] The server then analyzes the received text data using natural language processing (NLP) techniques. This analysis is performed using Python libraries such as SpaCy and NLTK. The server uses these libraries to extract useful keywords and phrases (e.g., "leadership" or "creative problem solving") from the data. This extracted data is then stored in a database (e.g., PostgreSQL or MongoDB).

[0100] Once the analysis is complete, the server uses generative AI technology to generate the optimal compliment based on the analysis results. Specifically, it uses an AI model such as OpenAI's GPT-3 to select a compliment template and input a specific prompt. For example, the prompt could read, "The user demonstrated leadership and provided a creative solution in a recent project. Please generate a compliment based on this content." The AI ​​model then generates a specific compliment based on this prompt.

[0101] The server sends the generated compliments to the device, which displays them to the user. The device also continuously monitors and records new performance data to measure the impact of the compliments on the user's performance. This data is then sent back to the server, which analyzes the new data and evaluates which compliments were most effective. The evaluation results are fed back to the algorithm and reflected in future compliment generation.

[0102] For example, a server collects reports of recently completed projects from users and analyzes them to identify strengths such as leadership and creative problem-solving. Based on the results, the server generates a compliment like this:

[0103] "Your recent project was particularly impressive, especially the way you led your team to come up with creative solutions. Your leadership skills are truly impressive!"

[0104] The praise is then displayed on the user's device, and the user is motivated by the praise to take on a new project. The progress and results are recorded by the device, and the server analyzes the data again to evaluate the effectiveness of the praise.

[0105] By implementing this system, it is possible to continuously provide appropriate and effective praise to users and promote their personal growth.

[0106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0107] Step 1: Data collection phase

[0108] The server first issues an HTTP request to the device to collect past performance data for the individual. This is a data collection request, requesting data such as project completion reports, evaluation results, and feedback comments stored on the user's device.

[0109] Input: HTTP request

[0110] Output: Text data saved on the device (project completion report, evaluation results, feedback comments)

[0111] After receiving the request, the device sends the stored data to the server using a secure communication protocol (e.g., HTTPS).

[0112] The server stores the received data in temporary storage and prepares for the next phase.

[0113] Step 2: Data analysis phase

[0114] The server analyzes the collected text data using natural language processing (NLP) techniques, specifically using the Python libraries SpaCy and NLTK.

[0115] Input: Collected text data

[0116] Output: Keywords or phrases (e.g., "leadership," "creative problem solving")

[0117] The server extracts useful keywords and phrases from the analysis results and stores them in a database.

[0118] Step 3: Compliment generation phase

[0119] The server uses a generative AI model based on the analysis results to generate the optimal compliment, specifically using a generative AI model such as OpenAI's GPT-3.

[0120] Input: Keyword or phrase

[0121] Output: Generated compliment

[0122] The generative AI model is given a specific prompt, such as "The user demonstrated leadership and provided a creative solution in a recent project. Based on this, please generate a compliment."

[0123] The server stores the generated compliments in a database and prepares them to be sent to the device.

[0124] Step 4: Feedback gathering phase

[0125] The terminal displays the compliment sent from the server to the user.

[0126] Input: Generated compliment

[0127] Output: The compliment displayed to the user

[0128] After displaying the compliment, the device collects new performance data (e.g., progress on a new project).

[0129] Input: User's new performance data

[0130] Output: New performance data collected

[0131] New performance data is sent from the terminal to the server.

[0132] Step 5: Learning Phase

[0133] The server analyzes the new performance data sent from the device, again using NLP techniques and data analysis algorithms.

[0134] Input: New performance data

[0135] Output: Evaluation results of the effectiveness of compliments

[0136] The server evaluates the impact that a particular compliment had on the user's performance and feeds the results back into the algorithm, which then influences the next compliment generation.

[0137] The server feeds the evaluation results back into the algorithm to improve the accuracy of compliment generation.

[0138] (Application example 1)

[0139] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0140] In modern society, it is important to provide optimal feedback and praise to individual users to improve their viewing experience. However, existing systems do not adequately establish methods for generating personalized praise based on viewing history and rating data to improve user motivation. Therefore, a method for providing effective, personalized feedback and improving the viewing experience is needed.

[0141] 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.

[0142] In this invention, the server includes means for collecting past data of an individual, means for analyzing the collected data to identify the individual's strengths and efforts, means for generating personalized compliments based on the identified strengths and efforts, means for presenting the generated compliments to the individual, means for collecting performance data of the individual after the compliments have been presented, means for analyzing the collected performance data to evaluate the effectiveness of the compliments and update the compliment generation algorithm, and means for generating personalized compliments in the content distribution service and improving the user's viewing experience based on the viewing data, thereby making it possible to generate and provide individually optimized compliments based on the user's viewing history.

[0143] "Personal past data" refers to information about an individual's past actions and results, including viewing history, rating data, and feedback.

[0144] "Means of collection" refers to methods and devices for collecting necessary data from personal devices and servers using databases and APIs.

[0145] "Means for analysis" refers to technologies for analyzing collected data and evaluating individual characteristics and performance, including natural language processing and machine learning algorithms.

[0146] "Identification methods" refers to techniques and methods for extracting useful information from the analyzed data and identifying individual strengths and efforts.

[0147] "Means for generation" refers to AI models and templates for creating personalized compliments based on the analysis results.

[0148] The term "presenting means" refers to a device or method, including a user interface or notification function, for visually or audibly displaying the generated compliment to the user.

[0149] "Collected performance data" is information recorded by the device regarding an individual's new behavior or achievements after the praise is given.

[0150] "Means to update the algorithm" refers to techniques or methods for reevaluating collected performance data and improving or adjusting the original compliment generation algorithm.

[0151] "Content distribution service" refers to a service that provides users with viewing content such as movies, television programs, and documentaries.

[0152] "Viewing data" is information relating to content viewed by a user, and includes viewing history, viewing time, ratings, comments, and the like.

[0153] A "generative AI model" refers to an artificial intelligence algorithm that generates new text or compliments based on given data.

[0154] A "prompt" is a sentence that describes a question or instruction to be input to a generative AI model.

[0155] This invention is a system that provides individually optimized compliments to improve the user's viewing experience in a content distribution service. The system of the present invention is mainly composed of three entities: a server, a terminal, and a user.

[0156] First, the server collects the user's past data, including viewing history, rating data, and feedback. To collect this data, the server issues a data request to the device, and the device sends the data to the server. Based on this collected data, the server identifies the individual's strengths and efforts.

[0157] Based on the information identified from the analyzed data, the server generates personalized compliments using a generative AI model that selects appropriate templates to generate specific compliments. For example, if a user has watched many documentaries, a compliment acknowledging their curiosity and inquisitiveness will be generated.

[0158] The generated compliment is presented to the user via the terminal. After the compliment is presented to the user, the terminal continuously monitors and records the user's new performance data, allowing the server to collect data to measure the impact of the compliment.

[0159] The server analyzes the collected new performance data and evaluates the effectiveness of the compliments. It identifies whether a particular compliment was effective and uses the results as feedback to improve the algorithm. This cycle allows the server to constantly learn in order to generate more effective compliments.

[0160] For example, if the user has watched a lot of documentaries about "environmental issues," we might generate a compliment for their interest and curiosity:

[0161] "You've been watching a lot of documentaries about environmental issues recently. Your interest and inquisitiveness are admirable! I was particularly impressed by your deep understanding of the 'plastic ocean.'"

[0162] Examples of prompts include:

[0163] "Users watch a lot of documentaries about 'environmental issues.' Generate compliments based on this. For example, we have viewing data for 'Plastic Oceans' and 'The Truth About Climate Change.'"

[0164] This invention makes it possible to generate and provide personalized compliments based on a user's viewing history, which is expected to improve the user's viewing experience and further motivate them to learn and pursue knowledge.

[0165] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0166] Step 1:

[0167] The server issues a data request to the device using a means of collecting personal past data. The device collects data such as viewing history, rating data, and feedback, and sends it to the server. The data request is the input, and the viewing data sent from the device is the output.

[0168] Step 2:

[0169] The server analyzes the collected data and analyzes the viewing history and rating data using a means to identify individual strengths and efforts. Specifically, it uses natural language processing techniques and machine learning algorithms to extract useful keywords and phrases. The viewing data is the input, and the identification of strengths and efforts is the output.

[0170] Step 3:

[0171] The server uses a generative AI model to generate personalized compliments based on the identified strengths and efforts. During this process, it selects an appropriate template and creates a specific compliment. For example, if a user has watched many documentaries, it generates a compliment that recognizes their curiosity and inquisitiveness. The identified results are the input, and the generated compliment is the output.

[0172] Step 4:

[0173] The server sends the generated compliment to the terminal and presents it to the user. The terminal displays the compliment visually or audibly. The generated compliment is the input, and the compliment presented to the user is the output.

[0174] Step 5:

[0175] The device continuously monitors and records new performance data of the user after the compliment is given. This data includes the user's new viewing history and rating data. The performance data after the compliment is given is the input, and the collected performance data is the output.

[0176] Step 6:

[0177] The server analyzes the new performance data collected and evaluates the effectiveness of the compliments. It evaluates whether the compliments were effective and updates the compliment generation algorithm based on the results. The performance data is the input, and the updated algorithm is the output.

[0178] Step 7:

[0179] The server then uses the analyzed results and feedback to retune the algorithm to be more effective when generating the next compliment. This step reinforces the algorithm's learning. The updated algorithm is the input, and the retuned algorithm is the output.

[0180] 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.

[0181] This invention is a system that uses generative AI and an emotion engine to provide personalized compliments to individuals (users). This system operates in cooperation with three entities: a server, a device, and a user, as shown below.

[0182] Data Collection Phase

[0183] The server requests past data from the user's device. The data types include project completion reports, final evaluations, feedback, etc. The user's device searches for this data from its local storage, collects it, and sends it to the server.

[0184] Data analysis phase

[0185] The server analyzes the received data and uses natural language processing technology to identify individual strengths and efforts. For example, it can extract keywords such as "leadership" and "creative problem solving" from project reports to identify individual characteristics.

[0186] Emotion Recognition Phase

[0187] The server uses an emotion engine to recognize the user's emotions. The emotion engine includes voice analysis technology and facial expression analysis technology to determine the user's emotions from the voice and facial expressions they make. For example, if the user is on a voice call, the server analyzes the tone and speed of the voice to identify the user's emotional state.

[0188] Compliment generation phase

[0189] The server generates optimal praise based on the analyzed individual's strengths and efforts, as well as the recognized emotions. First, it selects a praise template that corresponds to the identified strengths and efforts, and then adjusts the expression to match the user's emotional state. For example, if the user is stressed, it reinforces encouraging words, while if the user is relaxed, it emphasizes specific achievements.

[0190] Offering compliments

[0191] The generated compliment is sent from the server to the user's device, which notifies the user, for example, by displaying the compliment as a pop-up notification or as part of a dashboard.

[0192] Feedback gathering phase

[0193] After the compliment is given, the device continuously monitors and records the user's new performance data, including progress and deliverables for new projects.

[0194] Learning Phase

[0195] The server analyzes new performance data sent from the device and evaluates the effectiveness of the compliments. It evaluates how a particular compliment affected the user's performance and updates the compliment generation algorithm based on the results. This process allows the server to provide more effective compliments to the user.

[0196] ---

[0197] As a concrete example, the server collects reports of projects recently completed by users and analyzes the results of their leadership and creative problem-solving. At the same time, the emotion engine identifies when the user is feeling stressed. As a result, the following compliments are generated:

[0198] "Your leadership and creative problem-solving skills have helped the entire team. Your ability to remain calm in difficult situations, especially on this project, has been impressive. Get well rested and move on to the next step!"

[0199] In this way, by linking generative AI with an emotion engine, this invention can provide more personalized compliments to users, improving their performance and motivation.

[0200] The processing flow will be explained below.

[0201] Step 1: Submit a data request

[0202] The server requests past data from the user's device, specifically specifying data such as project completion reports, final evaluations, and feedback.

[0203] Step 2: Collect data

[0204] The device searches for and collects the specified data from the local storage, and then transmits the collected data to the server.

[0205] Step 3: Receiving and Preprocessing Data

[0206] The server receives the data sent from the terminal, converts it into a unified format, and performs preprocessing to make it suitable for analysis.

[0207] Step 4: Text analysis of the data

[0208] The server analyzes the preprocessed text data using natural language processing techniques, specifically, keyword extraction, morphological analysis, and context analysis.

[0209] Step 5: Identify strengths and efforts

[0210] The server identifies the user's strengths and efforts from the analysis results, for example, by extracting evaluation items such as "leadership" and "creative problem solving."

[0211] Step 6: Request Emotion Recognition

[0212] The server sends a request to the device to temporarily collect voice and facial expression data in order to recognize the user's current emotion.

[0213] Step 7: Collect and analyze emotion data

[0214] The device collects the user's voice and facial expression data and sends it to a server, which uses an emotion engine to analyze it and determine the user's current emotional state.

[0215] Step 8: Choose a compliment template

[0216] The server selects from a database praise templates that correspond to the identified strengths and efforts.

[0217] Step 9: Personalize your compliment

[0218] The server generates a personalized compliment based on the selected template, incorporating the user's name, specific achievements, and emotional state.

[0219] Step 10: Send a compliment

[0220] The server transmits the generated compliment to the user's terminal.

[0221] Step 11: Offer a compliment

[0222] The device will notify the user of the compliments it receives, for example, by presenting them as a pop-up notification or as part of the dashboard.

[0223] Step 12: Monitor performance data

[0224] The device continuously monitors and records the user's new performance data after the praise is given, and records the progress and deliverables of the new project.

[0225] Step 13: Submitting feedback data

[0226] The terminal transmits the collected performance data to the server.

[0227] Step 14: Analyze feedback data

[0228] The server analyzes the feedback data sent from the device and evaluates the effectiveness of the compliments, determining how a particular compliment affected the user's performance.

[0229] Step 15: Update the algorithm

[0230] The server updates the compliment generation algorithm based on the evaluation results, improving the effectiveness of the next compliment.

[0231] Through this series of steps, the generative AI and emotion engine work together to provide users with optimized compliments, helping to increase their motivation and improve their performance.

[0232] Example 2

[0233] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0234] Conventionally, feedback received by individuals has been uniform and has not taken into account individual characteristics or emotional states. This has made it difficult to effectively contribute to improving individual motivation and performance. Furthermore, there has been a lack of systems that measure the effectiveness of feedback and improve feedback methods based on that measurement. The present invention aims to solve these problems and provide a system that provides individually optimized feedback.

[0235] 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.

[0236] In this invention, the server includes means for collecting past data of an individual, means for analyzing the collected data to identify the strengths and efforts of the individual, means for generating personalized compliments based on the identified strengths and efforts, means for presenting the generated compliments to the individual, means for collecting performance data of the individual after the compliments have been presented, means for analyzing the collected performance data to evaluate the effectiveness of the compliments and updating the compliment generation algorithm, means for recognizing the user's emotions, and means for adjusting the compliments based on the emotion recognition results, thereby making it possible to provide individually optimized feedback and continuously improve the effectiveness of the feedback.

[0237] "Personal past data" refers to data that records a user's past actions and achievements, including project completion reports, end-of-term evaluations, and feedback.

[0238] "Means of collection" refers to the technology and methods for importing the necessary data from the user's device to the server, and typically involves the use of communication protocols and APIs.

[0239] "Means for analyzing and identifying" refers to techniques and methods for examining received data and identifying individual strengths and efforts, primarily natural language processing techniques.

[0240] "Personalized compliment generators" refer to techniques or methods for creating unique and appropriate compliments based on identified personal characteristics, often leveraging generative AI models.

[0241] "Presentation means" refers to techniques and methods for effectively communicating the generated compliments to the user, including notification systems and dashboard display functions.

[0242] "Means of collecting performance data" refers to the technology or method of capturing data on new user behaviors or outcomes after praise is given, such as a continuous data monitoring system.

[0243] "Means of analyzing collected performance data" refers to techniques and methods for analyzing new data to evaluate the effectiveness of praise, primarily using statistical analysis and machine learning techniques.

[0244] "Means for updating the compliment generation algorithm" refers to techniques and methods for improving the compliment generation method or model based on the analysis results, including training and parameter adjustment of the generative AI model.

[0245] "Means for recognizing a user's emotions" refers to techniques and methods for determining emotions from a user's voice and facial expressions, including voice analysis techniques and facial expression analysis techniques.

[0246] "Means for adjusting compliments based on emotion recognition results" refers to technologies and methods for appropriately changing the content and expression of compliments according to the recognized emotion, such as dynamic language generation using a generative AI model.

[0247] This invention is a system that uses generative AI and an emotion engine to provide personalized compliments to individuals (users). This system works in cooperation with three entities: a server, a device, and a user.

[0248] System configuration

[0249] 1. Data Collection Phase

[0250] The server requests past data from the user's device. Specifically, it sends an HTTP GET request to request project completion reports, final evaluations, feedback, etc. The device retrieves this data from local storage and sends it to the server as an HTTP response. For example, the server sends a request to the device saying, "Please send me the project completion report data," and the device responds by returning the data.

[0251] 2. Data analysis phase

[0252] The server analyzes the received data and uses natural language processing technologies such as Python's NLTK library and Spacy to identify individual strengths and efforts. For example, it extracts keywords such as "leadership" and "creative problem solving" from project reports. This reveals the user's characteristics.

[0253] 3. Emotion Recognition Phase

[0254] The server uses an emotion engine (such as Microsoft Azure Emotion API or Amazon Rekognition) to recognize the user's emotions. Specifically, it analyzes the tone and speed of the voice call and identifies emotions from the user's voice and facial expressions. For example, it uses Google Cloud Speech-to-Text to convert the voice data into text and recognizes emotions based on that text.

[0255] 4. Compliment Generation Phase

[0256] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate optimal compliments based on the analyzed individual's strengths and efforts, as well as the perceived emotions. A prompt is input to the generative AI model, which tailors the response to the user's situation. An example prompt is, "Please praise the user for their leadership and creative problem-solving skills."

[0257] 5. Offering compliments

[0258] The server sends the generated compliment to the user's device, where it can be displayed as a pop-up notification or as part of a dashboard. For example, a compliment might read, "Your leadership and creative problem-solving skills have helped the entire team. It's particularly impressive how you remained calm in difficult situations on this project. Please rest well and move on to the next step."

[0259] 6. Feedback gathering phase

[0260] After the compliment is given, the device continuously monitors and records the user's new performance data, including new project progress and deliverables, and periodically transmits this data to the server.

[0261] 7. Learning Phase

[0262] The server analyzes new performance data sent from the device and evaluates the effectiveness of the compliments. It evaluates how a particular compliment affected the user's performance and updates the compliment generation algorithm based on the results. This process uses machine learning algorithms (e.g., scikit-learn and TensorFlow).

[0263] In this way, by linking generative AI with an emotion engine, the system can provide more personalized compliments to users, improving their performance and motivation.

[0264] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0265] Step 1:

[0266] Data Collection Phase

[0267] The server requests past data from the user's device, specifically by sending an HTTP GET request for data such as project completion reports, final evaluations, and feedback.

[0268] In response to the request, the device retrieves the data from its local storage and sends it to the server as an HTTP response. For example, the server may send a request such as "Please send project completion report data," and the device may provide past data in response.

[0269] Input: Data request from server

[0270] Output: Data response (project completion report, final evaluation, feedback)

[0271] Step 2:

[0272] Data analysis phase

[0273] The server then analyzes the data it receives, using natural language processing techniques like Python's NLTK library and Spacy to identify individual strengths and efforts, such as extracting keywords like "leadership" and "creative problem solving" from project reports.

[0274] Input: User's past data (project completion report, final evaluation, feedback)

[0275] Output: Identified strengths and efforts (e.g., "Leadership," "Creative Problem Solving")

[0276] Step 3:

[0277] Emotion Recognition Phase

[0278] The server recognizes the user's emotions using an emotion engine (e.g., Microsoft Azure Emotion API or Amazon Rekognition).

[0279] It analyzes the tone and speed of voice calls and identifies emotions from the user's voice and facial expressions. For example, it uses Google Cloud Speech-to-Text to convert voice data into text and recognizes emotions based on that text.

[0280] Input: User voice and facial expression data

[0281] Output: User's emotional state (e.g., "stressed," "relaxed")

[0282] Step 4:

[0283] Compliment generation phase

[0284] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate the optimal compliment based on the analyzed individual's strengths, effort, and perceived emotions.

[0285] A prompt is fed into the generative AI model, which tailors its response to the user's situation, such as "Please praise the user for their leadership and creative problem-solving skills."

[0286] Input: personal strengths and efforts, user emotional state, prompt text

[0287] Output: Personalized compliment

[0288] Step 5:

[0289] Offering compliments

[0290] The generated compliment is sent from the server to the user's terminal.

[0291] The device will display the compliment as a pop-up notification or as part of the dashboard, such as, "Your leadership and creative problem-solving skills have helped the entire team. Your calmness in difficult situations, especially on this project, has been impressive. Please rest well and move on to the next step."

[0292] Input: Generated compliment

[0293] Output: User notification

[0294] Step 6:

[0295] Feedback gathering phase

[0296] After the compliment is given, the device continuously monitors and records the user's new performance data, including new project progress and deliverables, and periodically transmits this data to the server.

[0297] Input: User's new performance data

[0298] Output: Send data to the server

[0299] Step 7:

[0300] Learning Phase

[0301] The server analyzes new performance data sent from the device and evaluates the effectiveness of the compliments, assessing how a particular compliment affected the user's performance and updating the compliment-generation algorithm based on the results.

[0302] This process uses machine learning algorithms (e.g., scikit-learn and TensorFlow).

[0303] Input: New performance data, effectiveness evaluation results

[0304] Output: The updated compliment generation algorithm

[0305] (Application example 2)

[0306] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0307] Conventional performance improvement systems provide uniform feedback without considering the individual's emotional state, which limits their effectiveness in improving motivation and performance. Furthermore, the content of the feedback is not optimized for the individual's characteristics and circumstances, reducing the feedback's acceptability and effectiveness. Furthermore, providing feedback in real time is difficult and often lacks timeliness. Therefore, there is a need for a system that can recognize each individual's emotional state in real time and provide optimized praise.

[0308] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting past data of an individual, means for analyzing the collected data to identify the individual's strengths and efforts, means for generating personalized compliments based on the identified strengths and efforts, means for presenting the generated compliments to the individual, means for collecting performance data of the individual after the compliments have been presented, means for analyzing the collected performance data to evaluate the effectiveness of the compliments and updating the compliment generation algorithm, means for recognizing the individual's emotional state via an external device that collects audio and video data, means for adjusting the compliments based on the recognized emotional state, and means for displaying the adjusted compliments on the external device. This allows personalized compliments optimized for the individual's emotional state to be provided in real time, thereby improving motivation and performance.

[0309] "Personal past data" refers to information about an individual's past performance and behavior, such as project completion reports, end-of-period evaluations, and feedback.

[0310] "Means of collection" refers to the means by which an individual's historical data is collected in a particular manner, such as by local scanning or retrieval from a remote server.

[0311] "Means of analysis" refers to technologies for analyzing collected data and extracting meaningful information, including natural language processing technology and data mining technology.

[0312] "Means for identifying individual strengths and efforts" refers to technologies that identify individual talents and struggles from analyzed data, including specialized algorithms and machine learning models.

[0313] "Means for generating personalized compliments" refers to technology for creating personalized compliments based on identified strengths and efforts.

[0314] "Means for presenting the generated compliment to the individual" refers to technology that notifies or displays the generated compliment to the user, and includes, for example, devices such as smart glasses or a smartphone.

[0315] "Performance data" is data about an individual's achievements and behavior obtained after the presentation of praise.

[0316] "Means for evaluating the effectiveness of compliments and updating the compliment generation algorithm" refers to technology that measures the impact of presented compliments on an individual's performance and, based on the results, improves the algorithm that generates future compliments.

[0317] "External device for collecting audio and video data" refers to a device for capturing personal audio and video, including smart glasses and head-mounted displays.

[0318] "Means for recognizing an individual's emotional state" refers to technology that analyzes collected audio and video data to identify an individual's emotions (e.g., joy, sadness, stress, etc.).

[0319] "Methods for tailoring compliments based on perceived emotional state" refers to techniques for altering the content and tone of compliments to match identified emotional states.

[0320] "Means for displaying the tailored compliment on an external device" refers to display technology for providing the tailored compliment to the user in a viewable manner, including smart glasses or other display devices.

[0321] As an embodiment of the present invention, a factory worker support system using smart glasses will be taken as an example. This system operates in cooperation with three entities: a server, smart glasses (terminals), and a user.

[0322] First, the smart glasses collect the worker's voice and video data and transmit it to a server in real time. The smart glasses are equipped with a camera and microphone, which are used to record daily work.

[0323] The server utilizes several technologies to execute the following series of processes: First, the server analyzes the audio and video data received from the smart glasses and recognizes the user's emotional state using an emotion engine (e.g., Microsoft Azure Cognitive Services' Emotion API or Face API). The server analyzes tone, speed, volume, etc. from the audio data, and facial expressions from the video data.

[0324] Next, the server collects the user's past data (e.g., project completion reports, final evaluations, feedback, etc.) and analyzes it using natural language processing techniques (e.g., Google Cloud Natural Language API and Hugging Face transformers) to identify the user's strengths and efforts.

[0325] Based on the identified strengths and efforts, as well as the perceived emotional state, the server uses a generative AI model (e.g., OpenAI's GPT-4) to generate a personalized compliment using prompts such as:

[0326] Example prompt sentence:

[0327] Username: Yamada Taro

[0328] Project: Launching a new product line

[0329] Rating: Very High Leadership

[0330] Emotional state: Stressed

[0331] Generate a suitable compliment

[0332] The generated compliments are sent to the smart glasses and displayed to the user in real time, for example as a pop-up notification on the smart glasses display.

[0333] After the user receives a compliment, new performance data collected from the smart glasses continues to be sent to the server, which analyzes the data and evaluates the effect of the compliment on the user's performance. Based on the evaluation results, the compliment generation algorithm is updated accordingly.

[0334] This allows the system to provide users with personalized praise that is optimized for their emotional state, thereby increasing motivation and improving performance.

[0335] As a concrete example, if a user demonstrates exceptional leadership in the launch of a new product line and analysis using the emotion engine reveals that they are feeling stressed, the following praise could be offered: "Your leadership and creative problem-solving skills have helped the entire team. It's particularly impressive that you were able to remain calm in difficult situations in this project. Take a good rest and move on to the next step!" In this way, appropriate feedback can be provided to users in real time, improving their performance and motivation.

[0336] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0337] Step 1:

[0338] Smart glasses (terminals) collect the voice and video data of workers. The smart glasses are equipped with a camera and microphone to capture video and audio data of daily work. This data is sent to a server in real time.

[0339] Input: Video and audio data of worker

[0340] Output: Video and audio data transmitted in real time

[0341] Step 2:

[0342] The server analyzes the received audio and video data and uses an emotion engine to recognize the user's emotional state. Specifically, it uses the Emotion API and Face API of Microsoft Azure Cognitive Services to analyze tone, speed, and volume from audio data and facial expressions from video data.

[0343] Input: Video and audio data

[0344] Data processing / data calculation: Emotion analysis of audio and video

[0345] Output: User's emotional state (e.g., stress, joy)

[0346] Step 3:

[0347] The server collects users' past data (project completion reports, final evaluations, feedback, etc.) and analyzes it using natural language processing technology. It uses Google Cloud Natural Language API and Hugging Face transformers to identify individual strengths and efforts.

[0348] Input: Historical data

[0349] Data processing / data calculation: Analysis using natural language processing

[0350] Output: User strengths and efforts (e.g., leadership, creative problem-solving)

[0351] Step 4:

[0352] The server uses a generative AI model to generate personalized compliments based on the perceived emotional state and identified strengths and efforts, using OpenAI's GPT-4 to create prompts and generate results.

[0353] Input: User strengths, effort, and emotional state

[0354] Data processing / data calculation: Generating compliments using generative AI models

[0355] Output: Personalized compliment

[0356] Step 5:

[0357] The server sends the generated compliment to the smart glasses and presents it to the user in real time, as a pop-up notification on the smart glasses' display.

[0358] Input: Generated compliment

[0359] Output: Compliments displayed on the smart glasses display

[0360] Step 6:

[0361] After the user receives the compliment, the smart glasses collect new performance data and send it to the server, such as project progress and deliverables.

[0362] Input: User's new performance data

[0363] Output: New performance data sent to the server

[0364] Step 7:

[0365] The server analyzes the new performance data, evaluates the effectiveness of the compliments, and updates the compliment generation algorithm based on the evaluation results.

[0366] Input: New performance data

[0367] Data processing / data calculation: analysis of performance data and evaluation of effects

[0368] Output: Updated compliment generation algorithm

[0369] 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.

[0370] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0371] 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.

[0372] [Second embodiment]

[0373] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0374] 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.

[0375] 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).

[0376] 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.

[0377] 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.

[0378] 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).

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0385] This invention is a system that uses generative AI to provide individually optimized compliments. The system includes three entities: a server, a terminal, and a user, which work together to perform the following steps:

[0386] Data Collection Phase

[0387] The server first issues a request to collect past data about an individual (user). The data includes project completion reports, final evaluations, feedback, etc., and is stored on the user's device. The user's device is responsible for sending this data to the server.

[0388] Data analysis phase

[0389] The server analyzes the received data and identifies individual strengths and efforts. Specifically, it uses natural language processing technology to extract useful keywords and phrases from the collected text data. For example, it identifies characteristics such as "leadership" and "creative problem solving" from project reports.

[0390] Compliment generation phase

[0391] The server then generates the optimal compliment based on the analysis results. First, it selects a compliment template that corresponds to the identified strengths and efforts. Then, it creates a compliment that is optimized for each individual user based on that template. During this process, it incorporates the user's specific achievements and name to enhance specificity and personalization.

[0392] Feedback gathering phase

[0393] The device presents the generated compliment to the user. After presenting the compliment, the device continuously monitors and records new performance data of the user, thereby collecting data that measures the impact of the compliment.

[0394] Learning Phase

[0395] The server analyzes the collected new performance data and evaluates the effectiveness of the compliments. It identifies whether a particular compliment was effective and uses the results as feedback to improve the algorithm. This cycle allows the server to constantly learn in order to generate more effective compliments.

[0396] ---

[0397] For example, a server collects reports of recently completed projects from users and analyzes them to identify strengths such as leadership and creative problem-solving. Based on the results, the server generates a compliment like this:

[0398] "Your recent project was particularly impressive, especially the way you led your team to come up with creative solutions. Your leadership skills are truly impressive!"

[0399] The praise is then displayed on the user's device, and the user is motivated by the praise to take on a new project. The progress and results are recorded by the device, and the server analyzes the data again to evaluate the effectiveness of the praise.

[0400] Through this process, the system continues to provide the user with more appropriate and effective praise, promoting personal growth.

[0401] The processing flow will be explained below.

[0402] Step 1: Submit a data request

[0403] The server requests past data from the user's device, specifically specifying data such as project completion reports, final evaluations, and feedback.

[0404] Step 2: Collect data

[0405] The user's device searches and collects the specified data from the local storage, and if the data is found, sends it to the server.

[0406] Step 3: Receiving and Preprocessing Data

[0407] The server receives the data sent from the terminal and performs preprocessing, which unifies the data format and converts it into a format that is easy to analyze.

[0408] Step 4: Text analysis of the data

[0409] The server analyzes the collected text data using natural language processing technology, specifically, keyword extraction, morphological analysis, and context analysis.

[0410] Step 5: Identify strengths and efforts

[0411] The server identifies the user's strengths and efforts from the analysis results, for example, by extracting evaluation items such as "leadership" and "creative problem solving."

[0412] Step 6: Select a compliment template

[0413] The server selects from a database praise templates that correspond to the identified strengths and efforts.

[0414] Step 7: Personalize your compliment

[0415] The server then generates a personalized compliment based on the selected template, incorporating the user's name and specific achievements.

[0416] Step 8: Send a compliment

[0417] The server transmits the generated compliment to the user's terminal.

[0418] Step 9: Offer a compliment

[0419] The device will notify the user of any compliments received, including via a pop-up notification or display on the dashboard.

[0420] Step 10: Monitor performance data

[0421] The device continuously monitors and records new performance data of the user after the praise is given, such as the progress and deliverables of a new project.

[0422] Step 11: Submitting feedback data

[0423] The terminal transmits the collected performance data to the server.

[0424] Step 12: Analyze the feedback data

[0425] The server analyzes the feedback data sent from the device and evaluates the effectiveness of the compliments, checking whether a particular compliment was effective.

[0426] Step 13: Update the algorithm

[0427] The server updates the compliment generation algorithm based on the evaluation results, thereby improving the compliment generation algorithm to be more effective.

[0428] Through this series of steps, the generative AI continues to provide the user with optimized praise, helping to increase their motivation and improve their performance.

[0429] Example 1

[0430] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0431] Conventional compliment generation systems lacked a means to effectively provide personalized compliments to individuals. Furthermore, there was no way to evaluate the impact of compliments on the user's performance and reflect that feedback in the generation of next compliments. This made it difficult to provide sustained support for improving motivation.

[0432] 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.

[0433] In this invention, the server includes: means for collecting past data of an individual; means for analyzing the collected data to identify the individual's strengths and efforts; means for generating personalized compliments based on the identified strengths and efforts; means for presenting the generated compliments to the individual; means for collecting performance data of the individual after the compliments have been presented; means for analyzing the collected performance data to evaluate the effectiveness of the compliments and updating the compliment generation algorithm; means for including a series of programs for performing multiple data processing phases; means for using a communication protocol required for transmitting and receiving data; means for generating compliments corresponding to the identified strengths and efforts using generative AI technology; and means for inputting prompt sentences into the generative AI model. This makes it possible to continuously provide personalized compliments and improve user motivation.

[0434] "Personal historical data" refers to information related to a user's past activities and achievements, including work reports, evaluation results, and feedback comments.

[0435] "Means of collection" refers to the method or device used to collect data. It refers to the communication protocol or software used by the server to obtain data from the user's device.

[0436] "Means of analysis" refers to the technologies, algorithms, and software used to analyze data. Specifically, this includes natural language processing technology and data analysis algorithms.

[0437] "Means for identifying strengths and efforts" refers to a method for identifying users' advantages and efforts from the collected data. This is achieved using natural language processing techniques.

[0438] A "compliment generator" is a method or device that generates optimal compliments for a user, using generative AI technology to create compliments that correspond to specific strengths or efforts.

[0439] The "presenting means" refers to a method or device for showing the generated compliment to the user. This is done through the terminal.

[0440] "Performance data" is information related to new user activity and achievements collected after the praise is given.

[0441] The "measures for evaluation and updating" are methods for analyzing collected performance data, measuring the effectiveness of praise, and improving the algorithm.

[0442] The "data processing phase" refers to a series of processing steps: data collection, analysis, praise generation, presentation, feedback collection, and learning.

[0443] A "communications protocol" is a set of rules or standardized methods used to send and receive data. Examples include HTTPS.

[0444] "Generative AI technology" is an artificial intelligence technology that generates natural language based on specific input. The generative AI model uses this technology to create compliments.

[0445] A "prompt" is text that is input to a generative AI model, which then generates an appropriate compliment.

[0446] This invention is a system that uses generative AI to provide individually optimized compliments. The system mainly consists of three entities: a server, a device, and a user. These entities work together to perform the following processes:

[0447] The server first issues a request to collect past data for an individual (user). This request is sent to the user's device via the HTTP protocol. For example, an Amazon Web Services (AWS) EC2 instance is used as the server, and Apache or Nginx is used to send and receive data. The user's device (smartphone or PC) sends data via a client application that sends text data such as project completion reports, evaluation results, and feedback comments to the server.

[0448] The server then analyzes the received text data using natural language processing (NLP) techniques. This analysis is performed using Python libraries such as SpaCy and NLTK. The server uses these libraries to extract useful keywords and phrases (e.g., "leadership" or "creative problem solving") from the data. This extracted data is then stored in a database (e.g., PostgreSQL or MongoDB).

[0449] Once the analysis is complete, the server uses generative AI technology to generate the optimal compliment based on the analysis results. Specifically, it uses an AI model such as OpenAI's GPT-3 to select a compliment template and input a specific prompt. For example, the prompt could read, "The user demonstrated leadership and provided a creative solution in a recent project. Please generate a compliment based on this content." The AI ​​model then generates a specific compliment based on this prompt.

[0450] The server sends the generated compliments to the device, which displays them to the user. The device also continuously monitors and records new performance data to measure the impact of the compliments on the user's performance. This data is then sent back to the server, which analyzes the new data and evaluates which compliments were most effective. The evaluation results are fed back to the algorithm and reflected in future compliment generation.

[0451] For example, a server collects reports of recently completed projects from users and analyzes them to identify strengths such as leadership and creative problem-solving. Based on the results, the server generates a compliment like this:

[0452] "Your recent project was particularly impressive, especially the way you led your team to come up with creative solutions. Your leadership skills are truly impressive!"

[0453] The praise is then displayed on the user's device, and the user is motivated by the praise to take on a new project. The progress and results are recorded by the device, and the server analyzes the data again to evaluate the effectiveness of the praise.

[0454] By implementing this system, it is possible to continuously provide appropriate and effective praise to users and promote their personal growth.

[0455] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0456] Step 1: Data collection phase

[0457] The server first issues an HTTP request to the device to collect past performance data for the individual. This is a data collection request, requesting data such as project completion reports, evaluation results, and feedback comments stored on the user's device.

[0458] Input: HTTP request

[0459] Output: Text data saved on the device (project completion report, evaluation results, feedback comments)

[0460] After receiving the request, the device sends the stored data to the server using a secure communication protocol (e.g., HTTPS).

[0461] The server stores the received data in temporary storage and prepares for the next phase.

[0462] Step 2: Data analysis phase

[0463] The server analyzes the collected text data using natural language processing (NLP) techniques, specifically using the Python libraries SpaCy and NLTK.

[0464] Input: Collected text data

[0465] Output: Keywords or phrases (e.g., "leadership," "creative problem solving")

[0466] The server extracts useful keywords and phrases from the analysis results and stores them in a database.

[0467] Step 3: Compliment generation phase

[0468] The server uses a generative AI model based on the analysis results to generate the optimal compliment, specifically using a generative AI model such as OpenAI's GPT-3.

[0469] Input: Keyword or phrase

[0470] Output: Generated compliment

[0471] The generative AI model is given a specific prompt, such as "The user demonstrated leadership and provided a creative solution in a recent project. Based on this, please generate a compliment."

[0472] The server stores the generated compliments in a database and prepares them to be sent to the device.

[0473] Step 4: Feedback gathering phase

[0474] The terminal displays the compliment sent from the server to the user.

[0475] Input: Generated compliment

[0476] Output: The compliment displayed to the user

[0477] After displaying the compliment, the device collects new performance data (e.g., progress on a new project).

[0478] Input: User's new performance data

[0479] Output: New performance data collected

[0480] New performance data is sent from the terminal to the server.

[0481] Step 5: Learning Phase

[0482] The server analyzes the new performance data sent from the device, again using NLP techniques and data analysis algorithms.

[0483] Input: New performance data

[0484] Output: Evaluation results of the effectiveness of compliments

[0485] The server evaluates the impact that a particular compliment had on the user's performance and feeds the results back into the algorithm, which then influences the next compliment generation.

[0486] The server feeds the evaluation results back into the algorithm to improve the accuracy of compliment generation.

[0487] (Application example 1)

[0488] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0489] In modern society, it is important to provide optimal feedback and praise to individual users to improve their viewing experience. However, existing systems do not adequately establish methods for generating personalized praise based on viewing history and rating data to improve user motivation. Therefore, a method for providing effective, personalized feedback and improving the viewing experience is needed.

[0490] 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.

[0491] In this invention, the server includes means for collecting past data of an individual, means for analyzing the collected data to identify the individual's strengths and efforts, means for generating personalized compliments based on the identified strengths and efforts, means for presenting the generated compliments to the individual, means for collecting performance data of the individual after the compliments have been presented, means for analyzing the collected performance data to evaluate the effectiveness of the compliments and update the compliment generation algorithm, and means for generating personalized compliments in the content distribution service and improving the user's viewing experience based on the viewing data, thereby making it possible to generate and provide individually optimized compliments based on the user's viewing history.

[0492] "Personal past data" refers to information about an individual's past actions and results, including viewing history, rating data, and feedback.

[0493] "Means of collection" refers to methods and devices for collecting necessary data from personal devices and servers using databases and APIs.

[0494] "Means for analysis" refers to technologies for analyzing collected data and evaluating individual characteristics and performance, including natural language processing and machine learning algorithms.

[0495] "Identification methods" refers to techniques and methods for extracting useful information from the analyzed data and identifying individual strengths and efforts.

[0496] "Means for generation" refers to AI models and templates for creating personalized compliments based on the analysis results.

[0497] The term "presenting means" refers to a device or method, including a user interface or notification function, for visually or audibly displaying the generated compliment to the user.

[0498] "Collected performance data" is information recorded by the device regarding an individual's new behavior or achievements after the praise is given.

[0499] "Means to update the algorithm" refers to techniques or methods for reevaluating collected performance data and improving or adjusting the original compliment generation algorithm.

[0500] "Content distribution service" refers to a service that provides users with viewing content such as movies, television programs, and documentaries.

[0501] "Viewing data" is information relating to content viewed by a user, and includes viewing history, viewing time, ratings, comments, and the like.

[0502] A "generative AI model" refers to an artificial intelligence algorithm that generates new text or compliments based on given data.

[0503] A "prompt" is a sentence that describes a question or instruction to be input to a generative AI model.

[0504] This invention is a system that provides individually optimized compliments to improve the user's viewing experience in a content distribution service. The system of the present invention is mainly composed of three entities: a server, a terminal, and a user.

[0505] First, the server collects the user's past data, including viewing history, rating data, and feedback. To collect this data, the server issues a data request to the device, and the device sends the data to the server. Based on this collected data, the server identifies the individual's strengths and efforts.

[0506] Based on the information identified from the analyzed data, the server generates personalized compliments using a generative AI model that selects appropriate templates to generate specific compliments. For example, if a user has watched many documentaries, a compliment acknowledging their curiosity and inquisitiveness will be generated.

[0507] The generated compliment is presented to the user via the terminal. After the compliment is presented to the user, the terminal continuously monitors and records the user's new performance data, allowing the server to collect data to measure the impact of the compliment.

[0508] The server analyzes the collected new performance data and evaluates the effectiveness of the compliments. It identifies whether a particular compliment was effective and uses the results as feedback to improve the algorithm. This cycle allows the server to constantly learn in order to generate more effective compliments.

[0509] For example, if the user has watched a lot of documentaries about "environmental issues," we might generate a compliment for their interest and curiosity:

[0510] "You've been watching a lot of documentaries about environmental issues recently. Your interest and inquisitiveness are admirable! I was particularly impressed by your deep understanding of the 'plastic ocean.'"

[0511] Examples of prompts include:

[0512] "Users watch a lot of documentaries about 'environmental issues.' Generate compliments based on this. For example, we have viewing data for 'Plastic Oceans' and 'The Truth About Climate Change.'"

[0513] This invention makes it possible to generate and provide personalized compliments based on a user's viewing history, which is expected to improve the user's viewing experience and further motivate them to learn and pursue knowledge.

[0514] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0515] Step 1:

[0516] The server issues a data request to the device using a means of collecting personal past data. The device collects data such as viewing history, rating data, and feedback, and sends it to the server. The data request is the input, and the viewing data sent from the device is the output.

[0517] Step 2:

[0518] The server analyzes the collected data and analyzes the viewing history and rating data using a means to identify individual strengths and efforts. Specifically, it uses natural language processing techniques and machine learning algorithms to extract useful keywords and phrases. The viewing data is the input, and the identification of strengths and efforts is the output.

[0519] Step 3:

[0520] The server uses a generative AI model to generate personalized compliments based on the identified strengths and efforts. During this process, it selects an appropriate template and creates a specific compliment. For example, if a user has watched many documentaries, it generates a compliment that recognizes their curiosity and inquisitiveness. The identified results are the input, and the generated compliment is the output.

[0521] Step 4:

[0522] The server sends the generated compliment to the terminal and presents it to the user. The terminal displays the compliment visually or audibly. The generated compliment is the input, and the compliment presented to the user is the output.

[0523] Step 5:

[0524] The device continuously monitors and records new performance data of the user after the compliment is given. This data includes the user's new viewing history and rating data. The performance data after the compliment is given is the input, and the collected performance data is the output.

[0525] Step 6:

[0526] The server analyzes the new performance data collected and evaluates the effectiveness of the compliments. It evaluates whether the compliments were effective and updates the compliment generation algorithm based on the results. The performance data is the input, and the updated algorithm is the output.

[0527] Step 7:

[0528] The server then uses the analyzed results and feedback to retune the algorithm to be more effective when generating the next compliment. This step reinforces the algorithm's learning. The updated algorithm is the input, and the retuned algorithm is the output.

[0529] 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.

[0530] This invention is a system that uses generative AI and an emotion engine to provide personalized compliments to individuals (users). This system operates in cooperation with three entities: a server, a device, and a user, as shown below.

[0531] Data Collection Phase

[0532] The server requests past data from the user's device. The data types include project completion reports, final evaluations, feedback, etc. The user's device searches for this data from its local storage, collects it, and sends it to the server.

[0533] Data analysis phase

[0534] The server analyzes the received data and uses natural language processing technology to identify individual strengths and efforts. For example, it can extract keywords such as "leadership" and "creative problem solving" from project reports to identify individual characteristics.

[0535] Emotion Recognition Phase

[0536] The server uses an emotion engine to recognize the user's emotions. The emotion engine includes voice analysis technology and facial expression analysis technology to determine the user's emotions from the voice and facial expressions they make. For example, if the user is on a voice call, the server analyzes the tone and speed of the voice to identify the user's emotional state.

[0537] Compliment generation phase

[0538] The server generates optimal praise based on the analyzed individual's strengths and efforts, as well as the recognized emotions. First, it selects a praise template that corresponds to the identified strengths and efforts, and then adjusts the expression to match the user's emotional state. For example, if the user is stressed, it reinforces encouraging words, while if the user is relaxed, it emphasizes specific achievements.

[0539] Offering compliments

[0540] The generated compliment is sent from the server to the user's device, which notifies the user, for example, by displaying the compliment as a pop-up notification or as part of a dashboard.

[0541] Feedback gathering phase

[0542] After the compliment is given, the device continuously monitors and records the user's new performance data, including progress and deliverables for new projects.

[0543] Learning Phase

[0544] The server analyzes new performance data sent from the device and evaluates the effectiveness of the compliments. It evaluates how a particular compliment affected the user's performance and updates the compliment generation algorithm based on the results. This process allows the server to provide more effective compliments to the user.

[0545] ---

[0546] As a concrete example, the server collects reports of projects recently completed by users and analyzes the results of their leadership and creative problem-solving. At the same time, the emotion engine identifies when the user is feeling stressed. As a result, the following compliments are generated:

[0547] "Your leadership and creative problem-solving skills have helped the entire team. Your ability to remain calm in difficult situations, especially on this project, has been impressive. Get well rested and move on to the next step!"

[0548] In this way, by linking generative AI with an emotion engine, this invention can provide more personalized compliments to users, improving their performance and motivation.

[0549] The processing flow will be explained below.

[0550] Step 1: Submit a data request

[0551] The server requests past data from the user's device, specifically specifying data such as project completion reports, final evaluations, and feedback.

[0552] Step 2: Collect data

[0553] The device searches for and collects the specified data from the local storage, and then transmits the collected data to the server.

[0554] Step 3: Receiving and Preprocessing Data

[0555] The server receives the data sent from the terminal, converts it into a unified format, and performs preprocessing to make it suitable for analysis.

[0556] Step 4: Text analysis of the data

[0557] The server analyzes the preprocessed text data using natural language processing techniques, specifically, keyword extraction, morphological analysis, and context analysis.

[0558] Step 5: Identify strengths and efforts

[0559] The server identifies the user's strengths and efforts from the analysis results, for example, by extracting evaluation items such as "leadership" and "creative problem solving."

[0560] Step 6: Request Emotion Recognition

[0561] The server sends a request to the device to temporarily collect voice and facial expression data in order to recognize the user's current emotion.

[0562] Step 7: Collect and analyze emotion data

[0563] The device collects the user's voice and facial expression data and sends it to a server, which uses an emotion engine to analyze it and determine the user's current emotional state.

[0564] Step 8: Choose a compliment template

[0565] The server selects from a database praise templates that correspond to the identified strengths and efforts.

[0566] Step 9: Personalize your compliment

[0567] The server generates a personalized compliment based on the selected template, incorporating the user's name, specific achievements, and emotional state.

[0568] Step 10: Send a compliment

[0569] The server transmits the generated compliment to the user's terminal.

[0570] Step 11: Offer a compliment

[0571] The device will notify the user of the compliments it receives, for example, by presenting them as a pop-up notification or as part of the dashboard.

[0572] Step 12: Monitor performance data

[0573] The device continuously monitors and records the user's new performance data after the praise is given, and records the progress and deliverables of the new project.

[0574] Step 13: Submitting feedback data

[0575] The terminal transmits the collected performance data to the server.

[0576] Step 14: Analyze feedback data

[0577] The server analyzes the feedback data sent from the device and evaluates the effectiveness of the compliments, determining how a particular compliment affected the user's performance.

[0578] Step 15: Update the algorithm

[0579] The server updates the compliment generation algorithm based on the evaluation results, improving the effectiveness of the next compliment.

[0580] Through this series of steps, the generative AI and emotion engine work together to provide users with optimized compliments, helping to increase their motivation and improve their performance.

[0581] Example 2

[0582] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0583] Conventionally, feedback received by individuals has been uniform and has not taken into account individual characteristics or emotional states. This has made it difficult to effectively contribute to improving individual motivation and performance. Furthermore, there has been a lack of systems that measure the effectiveness of feedback and improve feedback methods based on that measurement. The present invention aims to solve these problems and provide a system that provides individually optimized feedback.

[0584] 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.

[0585] In this invention, the server includes means for collecting past data of an individual, means for analyzing the collected data to identify the strengths and efforts of the individual, means for generating personalized compliments based on the identified strengths and efforts, means for presenting the generated compliments to the individual, means for collecting performance data of the individual after the compliments have been presented, means for analyzing the collected performance data to evaluate the effectiveness of the compliments and updating the compliment generation algorithm, means for recognizing the user's emotions, and means for adjusting the compliments based on the emotion recognition results, thereby making it possible to provide individually optimized feedback and continuously improve the effectiveness of the feedback.

[0586] "Personal past data" refers to data that records a user's past actions and achievements, including project completion reports, end-of-term evaluations, and feedback.

[0587] "Means of collection" refers to the technology and methods for importing the necessary data from the user's device to the server, and typically involves the use of communication protocols and APIs.

[0588] "Means for analyzing and identifying" refers to techniques and methods for examining received data and identifying individual strengths and efforts, primarily natural language processing techniques.

[0589] "Personalized compliment generators" refer to techniques or methods for creating unique and appropriate compliments based on identified personal characteristics, often leveraging generative AI models.

[0590] "Presentation means" refers to techniques and methods for effectively communicating the generated compliments to the user, including notification systems and dashboard display functions.

[0591] "Means of collecting performance data" refers to the technology or method of capturing data on new user behaviors or outcomes after praise is given, such as a continuous data monitoring system.

[0592] "Means of analyzing collected performance data" refers to techniques and methods for analyzing new data to evaluate the effectiveness of praise, primarily using statistical analysis and machine learning techniques.

[0593] "Means for updating the compliment generation algorithm" refers to techniques and methods for improving the compliment generation method or model based on the analysis results, including training and parameter adjustment of the generative AI model.

[0594] "Means for recognizing a user's emotions" refers to techniques and methods for determining emotions from a user's voice and facial expressions, including voice analysis techniques and facial expression analysis techniques.

[0595] "Means for adjusting compliments based on emotion recognition results" refers to technologies and methods for appropriately changing the content and expression of compliments according to the recognized emotion, such as dynamic language generation using a generative AI model.

[0596] This invention is a system that uses generative AI and an emotion engine to provide personalized compliments to individuals (users). This system works in cooperation with three entities: a server, a device, and a user.

[0597] System configuration

[0598] 1. Data Collection Phase

[0599] The server requests past data from the user's device. Specifically, it sends an HTTP GET request to request project completion reports, final evaluations, feedback, etc. The device retrieves this data from local storage and sends it to the server as an HTTP response. For example, the server sends a request to the device saying, "Please send me the project completion report data," and the device responds by returning the data.

[0600] 2. Data analysis phase

[0601] The server analyzes the received data and uses natural language processing technologies such as Python's NLTK library and Spacy to identify individual strengths and efforts. For example, it extracts keywords such as "leadership" and "creative problem solving" from project reports. This reveals the user's characteristics.

[0602] 3. Emotion Recognition Phase

[0603] The server uses an emotion engine (such as Microsoft Azure Emotion API or Amazon Rekognition) to recognize the user's emotions. Specifically, it analyzes the tone and speed of the voice call and identifies emotions from the user's voice and facial expressions. For example, it uses Google Cloud Speech-to-Text to convert the voice data into text and recognizes emotions based on that text.

[0604] 4. Compliment Generation Phase

[0605] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate optimal compliments based on the analyzed individual's strengths and efforts, as well as the perceived emotions. A prompt is input to the generative AI model, which tailors the response to the user's situation. An example prompt is, "Please praise the user for their leadership and creative problem-solving skills."

[0606] 5. Offering compliments

[0607] The server sends the generated compliment to the user's device, where it can be displayed as a pop-up notification or as part of a dashboard. For example, a compliment might read, "Your leadership and creative problem-solving skills have helped the entire team. It's particularly impressive how you remained calm in difficult situations on this project. Please rest well and move on to the next step."

[0608] 6. Feedback gathering phase

[0609] After the compliment is given, the device continuously monitors and records the user's new performance data, including new project progress and deliverables, and periodically transmits this data to the server.

[0610] 7. Learning Phase

[0611] The server analyzes new performance data sent from the device and evaluates the effectiveness of the compliments. It evaluates how a particular compliment affected the user's performance and updates the compliment generation algorithm based on the results. This process uses machine learning algorithms (e.g., scikit-learn and TensorFlow).

[0612] In this way, by linking generative AI with an emotion engine, the system can provide more personalized compliments to users, improving their performance and motivation.

[0613] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0614] Step 1:

[0615] Data Collection Phase

[0616] The server requests past data from the user's device, specifically by sending an HTTP GET request for data such as project completion reports, final evaluations, and feedback.

[0617] In response to the request, the device retrieves the data from its local storage and sends it to the server as an HTTP response. For example, the server may send a request such as "Please send project completion report data," and the device may provide past data in response.

[0618] Input: Data request from server

[0619] Output: Data response (project completion report, final evaluation, feedback)

[0620] Step 2:

[0621] Data analysis phase

[0622] The server then analyzes the data it receives, using natural language processing techniques like Python's NLTK library and Spacy to identify individual strengths and efforts, such as extracting keywords like "leadership" and "creative problem solving" from project reports.

[0623] Input: User's past data (project completion report, final evaluation, feedback)

[0624] Output: Identified strengths and efforts (e.g., "Leadership," "Creative Problem Solving")

[0625] Step 3:

[0626] Emotion Recognition Phase

[0627] The server recognizes the user's emotions using an emotion engine (e.g., Microsoft Azure Emotion API or Amazon Rekognition).

[0628] It analyzes the tone and speed of voice calls and identifies emotions from the user's voice and facial expressions. For example, it uses Google Cloud Speech-to-Text to convert voice data into text and recognizes emotions based on that text.

[0629] Input: User voice and facial expression data

[0630] Output: User's emotional state (e.g., "stressed," "relaxed")

[0631] Step 4:

[0632] Compliment generation phase

[0633] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate the optimal compliment based on the analyzed individual's strengths, effort, and perceived emotions.

[0634] A prompt is fed into the generative AI model, which tailors its response to the user's situation, such as "Please praise the user for their leadership and creative problem-solving skills."

[0635] Input: personal strengths and efforts, user emotional state, prompt text

[0636] Output: Personalized compliment

[0637] Step 5:

[0638] Offering compliments

[0639] The generated compliment is sent from the server to the user's terminal.

[0640] The device will display the compliment as a pop-up notification or as part of the dashboard, such as, "Your leadership and creative problem-solving skills have helped the entire team. Your calmness in difficult situations, especially on this project, has been impressive. Please rest well and move on to the next step."

[0641] Input: Generated compliment

[0642] Output: User notification

[0643] Step 6:

[0644] Feedback gathering phase

[0645] After the compliment is given, the device continuously monitors and records the user's new performance data, including new project progress and deliverables, and periodically transmits this data to the server.

[0646] Input: User's new performance data

[0647] Output: Send data to the server

[0648] Step 7:

[0649] Learning Phase

[0650] The server analyzes new performance data sent from the device and evaluates the effectiveness of the compliments, assessing how a particular compliment affected the user's performance and updating the compliment-generation algorithm based on the results.

[0651] This process uses machine learning algorithms (e.g., scikit-learn and TensorFlow).

[0652] Input: New performance data, effectiveness evaluation results

[0653] Output: The updated compliment generation algorithm

[0654] (Application example 2)

[0655] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0656] Conventional performance improvement systems provide uniform feedback without considering the individual's emotional state, which limits their effectiveness in improving motivation and performance. Furthermore, the content of the feedback is not optimized for the individual's characteristics and circumstances, reducing the feedback's acceptability and effectiveness. Furthermore, providing feedback in real time is difficult and often lacks timeliness. Therefore, there is a need for a system that can recognize each individual's emotional state in real time and provide optimized praise.

[0657] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting past data of an individual, means for analyzing the collected data to identify the individual's strengths and efforts, means for generating personalized compliments based on the identified strengths and efforts, means for presenting the generated compliments to the individual, means for collecting performance data of the individual after the compliments have been presented, means for analyzing the collected performance data to evaluate the effectiveness of the compliments and updating the compliment generation algorithm, means for recognizing the individual's emotional state via an external device that collects audio and video data, means for adjusting the compliments based on the recognized emotional state, and means for displaying the adjusted compliments on the external device. This allows personalized compliments optimized for the individual's emotional state to be provided in real time, thereby improving motivation and performance.

[0658] "Personal past data" refers to information about an individual's past performance and behavior, such as project completion reports, end-of-period evaluations, and feedback.

[0659] "Means of collection" refers to the means by which an individual's historical data is collected in a particular manner, such as by local scanning or retrieval from a remote server.

[0660] "Means of analysis" refers to technologies for analyzing collected data and extracting meaningful information, including natural language processing technology and data mining technology.

[0661] "Means for identifying individual strengths and efforts" refers to technologies that identify individual talents and struggles from analyzed data, including specialized algorithms and machine learning models.

[0662] "Means for generating personalized compliments" refers to technology for creating personalized compliments based on identified strengths and efforts.

[0663] "Means for presenting the generated compliment to the individual" refers to technology that notifies or displays the generated compliment to the user, and includes, for example, devices such as smart glasses or a smartphone.

[0664] "Performance data" is data about an individual's achievements and behavior obtained after the presentation of praise.

[0665] "Means for evaluating the effectiveness of compliments and updating the compliment generation algorithm" refers to technology that measures the impact of presented compliments on an individual's performance and, based on the results, improves the algorithm that generates future compliments.

[0666] "External device for collecting audio and video data" refers to a device for capturing personal audio and video, including smart glasses and head-mounted displays.

[0667] "Means for recognizing an individual's emotional state" refers to technology that analyzes collected audio and video data to identify an individual's emotions (e.g., joy, sadness, stress, etc.).

[0668] "Methods for tailoring compliments based on perceived emotional state" refers to techniques for altering the content and tone of compliments to match identified emotional states.

[0669] "Means for displaying the tailored compliment on an external device" refers to display technology for providing the tailored compliment to the user in a viewable manner, including smart glasses or other display devices.

[0670] As an embodiment of the present invention, a factory worker support system using smart glasses will be taken as an example. This system operates in cooperation with three entities: a server, smart glasses (terminals), and a user.

[0671] First, the smart glasses collect the worker's voice and video data and transmit it to a server in real time. The smart glasses are equipped with a camera and microphone, which are used to record daily work.

[0672] The server utilizes several technologies to execute the following series of processes: First, the server analyzes the audio and video data received from the smart glasses and recognizes the user's emotional state using an emotion engine (e.g., Microsoft Azure Cognitive Services' Emotion API or Face API). The server analyzes tone, speed, volume, etc. from the audio data, and facial expressions from the video data.

[0673] Next, the server collects the user's past data (e.g., project completion reports, final evaluations, feedback, etc.) and analyzes it using natural language processing techniques (e.g., Google Cloud Natural Language API and Hugging Face transformers) to identify the user's strengths and efforts.

[0674] Based on the identified strengths and efforts, as well as the perceived emotional state, the server uses a generative AI model (e.g., OpenAI's GPT-4) to generate a personalized compliment using prompts such as:

[0675] Example prompt sentence:

[0676] Username: Yamada Taro

[0677] Project: Launching a new product line

[0678] Rating: Very High Leadership

[0679] Emotional state: Stressed

[0680] Generate a suitable compliment

[0681] The generated compliments are sent to the smart glasses and displayed to the user in real time, for example as a pop-up notification on the smart glasses display.

[0682] After the user receives a compliment, new performance data collected from the smart glasses continues to be sent to the server, which analyzes the data and evaluates the effect of the compliment on the user's performance. Based on the evaluation results, the compliment generation algorithm is updated accordingly.

[0683] This allows the system to provide users with personalized praise that is optimized for their emotional state, thereby increasing motivation and improving performance.

[0684] As a concrete example, if a user demonstrates exceptional leadership in the launch of a new product line and analysis using the emotion engine reveals that they are feeling stressed, the following praise could be offered: "Your leadership and creative problem-solving skills have helped the entire team. It's particularly impressive that you were able to remain calm in difficult situations in this project. Take a good rest and move on to the next step!" In this way, appropriate feedback can be provided to users in real time, improving their performance and motivation.

[0685] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0686] Step 1:

[0687] Smart glasses (terminals) collect the voice and video data of workers. The smart glasses are equipped with a camera and microphone to capture video and audio data of daily work. This data is sent to a server in real time.

[0688] Input: Video and audio data of worker

[0689] Output: Video and audio data transmitted in real time

[0690] Step 2:

[0691] The server analyzes the received audio and video data and uses an emotion engine to recognize the user's emotional state. Specifically, it uses the Emotion API and Face API of Microsoft Azure Cognitive Services to analyze tone, speed, and volume from audio data and facial expressions from video data.

[0692] Input: Video and audio data

[0693] Data processing / data calculation: Emotion analysis of audio and video

[0694] Output: User's emotional state (e.g., stress, joy)

[0695] Step 3:

[0696] The server collects users' past data (project completion reports, final evaluations, feedback, etc.) and analyzes it using natural language processing technology. It uses Google Cloud Natural Language API and Hugging Face transformers to identify individual strengths and efforts.

[0697] Input: Historical data

[0698] Data processing / data calculation: Analysis using natural language processing

[0699] Output: User strengths and efforts (e.g., leadership, creative problem-solving)

[0700] Step 4:

[0701] The server uses a generative AI model to generate personalized compliments based on the perceived emotional state and identified strengths and efforts, using OpenAI's GPT-4 to create prompts and generate results.

[0702] Input: User strengths, effort, and emotional state

[0703] Data processing / data calculation: Generating compliments using generative AI models

[0704] Output: Personalized compliment

[0705] Step 5:

[0706] The server sends the generated compliment to the smart glasses and presents it to the user in real time, as a pop-up notification on the smart glasses' display.

[0707] Input: Generated compliment

[0708] Output: Compliments displayed on the smart glasses display

[0709] Step 6:

[0710] After the user receives the compliment, the smart glasses collect new performance data and send it to the server, such as project progress and deliverables.

[0711] Input: User's new performance data

[0712] Output: New performance data sent to the server

[0713] Step 7:

[0714] The server analyzes the new performance data, evaluates the effectiveness of the compliments, and updates the compliment generation algorithm based on the evaluation results.

[0715] Input: New performance data

[0716] Data processing / data calculation: analysis of performance data and evaluation of effects

[0717] Output: Updated compliment generation algorithm

[0718] 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.

[0719] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0720] 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.

[0721] [Third embodiment]

[0722] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0723] 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.

[0724] 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).

[0725] 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.

[0726] 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.

[0727] 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).

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0734] This invention is a system that uses generative AI to provide individually optimized compliments. The system includes three entities: a server, a terminal, and a user, which work together to perform the following steps:

[0735] Data Collection Phase

[0736] The server first issues a request to collect past data about an individual (user). The data includes project completion reports, final evaluations, feedback, etc., and is stored on the user's device. The user's device is responsible for sending this data to the server.

[0737] Data analysis phase

[0738] The server analyzes the received data and identifies individual strengths and efforts. Specifically, it uses natural language processing technology to extract useful keywords and phrases from the collected text data. For example, it identifies characteristics such as "leadership" and "creative problem solving" from project reports.

[0739] Compliment generation phase

[0740] The server then generates the optimal compliment based on the analysis results. First, it selects a compliment template that corresponds to the identified strengths and efforts. Then, it creates a compliment that is optimized for each individual user based on that template. During this process, it incorporates the user's specific achievements and name to enhance specificity and personalization.

[0741] Feedback gathering phase

[0742] The device presents the generated compliment to the user. After presenting the compliment, the device continuously monitors and records new performance data of the user, thereby collecting data that measures the impact of the compliment.

[0743] Learning Phase

[0744] The server analyzes the collected new performance data and evaluates the effectiveness of the compliments. It identifies whether a particular compliment was effective and uses the results as feedback to improve the algorithm. This cycle allows the server to constantly learn in order to generate more effective compliments.

[0745] ---

[0746] For example, a server collects reports of recently completed projects from users and analyzes them to identify strengths such as leadership and creative problem-solving. Based on the results, the server generates a compliment like this:

[0747] "Your recent project was particularly impressive, especially the way you led your team to come up with creative solutions. Your leadership skills are truly impressive!"

[0748] The praise is then displayed on the user's device, and the user is motivated by the praise to take on a new project. The progress and results are recorded by the device, and the server analyzes the data again to evaluate the effectiveness of the praise.

[0749] Through this process, the system continues to provide the user with more appropriate and effective praise, promoting personal growth.

[0750] The processing flow will be explained below.

[0751] Step 1: Submit a data request

[0752] The server requests past data from the user's device, specifically specifying data such as project completion reports, final evaluations, and feedback.

[0753] Step 2: Collect data

[0754] The user's device searches and collects the specified data from the local storage, and if the data is found, sends it to the server.

[0755] Step 3: Receiving and Preprocessing Data

[0756] The server receives the data sent from the terminal and performs preprocessing, which unifies the data format and converts it into a format that is easy to analyze.

[0757] Step 4: Text analysis of the data

[0758] The server analyzes the collected text data using natural language processing technology, specifically, keyword extraction, morphological analysis, and context analysis.

[0759] Step 5: Identify strengths and efforts

[0760] The server identifies the user's strengths and efforts from the analysis results, for example, by extracting evaluation items such as "leadership" and "creative problem solving."

[0761] Step 6: Select a compliment template

[0762] The server selects from a database praise templates that correspond to the identified strengths and efforts.

[0763] Step 7: Personalize your compliment

[0764] The server then generates a personalized compliment based on the selected template, incorporating the user's name and specific achievements.

[0765] Step 8: Send a compliment

[0766] The server transmits the generated compliment to the user's terminal.

[0767] Step 9: Offer a compliment

[0768] The device will notify the user of any compliments received, including via a pop-up notification or display on the dashboard.

[0769] Step 10: Monitor performance data

[0770] The device continuously monitors and records new performance data of the user after the praise is given, such as the progress and deliverables of a new project.

[0771] Step 11: Submitting feedback data

[0772] The terminal transmits the collected performance data to the server.

[0773] Step 12: Analyze the feedback data

[0774] The server analyzes the feedback data sent from the device and evaluates the effectiveness of the compliments, checking whether a particular compliment was effective.

[0775] Step 13: Update the algorithm

[0776] The server updates the compliment generation algorithm based on the evaluation results, thereby improving the compliment generation algorithm to be more effective.

[0777] Through this series of steps, the generative AI continues to provide the user with optimized praise, helping to increase their motivation and improve their performance.

[0778] Example 1

[0779] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0780] Conventional compliment generation systems lacked a means to effectively provide personalized compliments to individuals. Furthermore, there was no way to evaluate the impact of compliments on the user's performance and reflect that feedback in the generation of next compliments. This made it difficult to provide sustained support for improving motivation.

[0781] 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.

[0782] In this invention, the server includes: means for collecting past data of an individual; means for analyzing the collected data to identify the individual's strengths and efforts; means for generating personalized compliments based on the identified strengths and efforts; means for presenting the generated compliments to the individual; means for collecting performance data of the individual after the compliments have been presented; means for analyzing the collected performance data to evaluate the effectiveness of the compliments and updating the compliment generation algorithm; means for including a series of programs for performing multiple data processing phases; means for using a communication protocol required for transmitting and receiving data; means for generating compliments corresponding to the identified strengths and efforts using generative AI technology; and means for inputting prompt sentences into the generative AI model. This makes it possible to continuously provide personalized compliments and improve user motivation.

[0783] "Personal historical data" refers to information related to a user's past activities and achievements, including work reports, evaluation results, and feedback comments.

[0784] "Means of collection" refers to the method or device used to collect data. It refers to the communication protocol or software used by the server to obtain data from the user's device.

[0785] "Means of analysis" refers to the technologies, algorithms, and software used to analyze data. Specifically, this includes natural language processing technology and data analysis algorithms.

[0786] "Means for identifying strengths and efforts" refers to a method for identifying users' advantages and efforts from the collected data. This is achieved using natural language processing techniques.

[0787] A "compliment generator" is a method or device that generates optimal compliments for a user, using generative AI technology to create compliments that correspond to specific strengths or efforts.

[0788] The "presenting means" refers to a method or device for showing the generated compliment to the user. This is done through the terminal.

[0789] "Performance data" is information related to new user activity and achievements collected after the praise is given.

[0790] The "measures for evaluation and updating" are methods for analyzing collected performance data, measuring the effectiveness of praise, and improving the algorithm.

[0791] The "data processing phase" refers to a series of processing steps: data collection, analysis, praise generation, presentation, feedback collection, and learning.

[0792] A "communications protocol" is a set of rules or standardized methods used to send and receive data. Examples include HTTPS.

[0793] "Generative AI technology" is an artificial intelligence technology that generates natural language based on specific input. The generative AI model uses this technology to create compliments.

[0794] A "prompt" is text that is input to a generative AI model, which then generates an appropriate compliment.

[0795] This invention is a system that uses generative AI to provide individually optimized compliments. The system mainly consists of three entities: a server, a device, and a user. These entities work together to perform the following processes:

[0796] The server first issues a request to collect past data for an individual (user). This request is sent to the user's device via the HTTP protocol. For example, an Amazon Web Services (AWS) EC2 instance is used as the server, and Apache or Nginx is used to send and receive data. The user's device (smartphone or PC) sends data via a client application that sends text data such as project completion reports, evaluation results, and feedback comments to the server.

[0797] The server then analyzes the received text data using natural language processing (NLP) techniques. This analysis is performed using Python libraries such as SpaCy and NLTK. The server uses these libraries to extract useful keywords and phrases (e.g., "leadership" or "creative problem solving") from the data. This extracted data is then stored in a database (e.g., PostgreSQL or MongoDB).

[0798] Once the analysis is complete, the server uses generative AI technology to generate the optimal compliment based on the analysis results. Specifically, it uses an AI model such as OpenAI's GPT-3 to select a compliment template and input a specific prompt. For example, the prompt could read, "The user demonstrated leadership and provided a creative solution in a recent project. Please generate a compliment based on this content." The AI ​​model then generates a specific compliment based on this prompt.

[0799] The server sends the generated compliments to the device, which displays them to the user. The device also continuously monitors and records new performance data to measure the impact of the compliments on the user's performance. This data is then sent back to the server, which analyzes the new data and evaluates which compliments were most effective. The evaluation results are fed back to the algorithm and reflected in future compliment generation.

[0800] For example, a server collects reports of recently completed projects from users and analyzes them to identify strengths such as leadership and creative problem-solving. Based on the results, the server generates a compliment like this:

[0801] "Your recent project was particularly impressive, especially the way you led your team to come up with creative solutions. Your leadership skills are truly impressive!"

[0802] The praise is then displayed on the user's device, and the user is motivated by the praise to take on a new project. The progress and results are recorded by the device, and the server analyzes the data again to evaluate the effectiveness of the praise.

[0803] By implementing this system, it is possible to continuously provide appropriate and effective praise to users and promote their personal growth.

[0804] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0805] Step 1: Data collection phase

[0806] The server first issues an HTTP request to the device to collect past performance data for the individual. This is a data collection request, requesting data such as project completion reports, evaluation results, and feedback comments stored on the user's device.

[0807] Input: HTTP request

[0808] Output: Text data saved on the device (project completion report, evaluation results, feedback comments)

[0809] After receiving the request, the device sends the stored data to the server using a secure communication protocol (e.g., HTTPS).

[0810] The server stores the received data in temporary storage and prepares for the next phase.

[0811] Step 2: Data analysis phase

[0812] The server analyzes the collected text data using natural language processing (NLP) techniques, specifically using the Python libraries SpaCy and NLTK.

[0813] Input: Collected text data

[0814] Output: Keywords or phrases (e.g., "leadership," "creative problem solving")

[0815] The server extracts useful keywords and phrases from the analysis results and stores them in a database.

[0816] Step 3: Compliment generation phase

[0817] The server uses a generative AI model based on the analysis results to generate the optimal compliment, specifically using a generative AI model such as OpenAI's GPT-3.

[0818] Input: Keyword or phrase

[0819] Output: Generated compliment

[0820] The generative AI model is given a specific prompt, such as "The user demonstrated leadership and provided a creative solution in a recent project. Based on this, please generate a compliment."

[0821] The server stores the generated compliments in a database and prepares them to be sent to the device.

[0822] Step 4: Feedback gathering phase

[0823] The terminal displays the compliment sent from the server to the user.

[0824] Input: Generated compliment

[0825] Output: The compliment displayed to the user

[0826] After displaying the compliment, the device collects new performance data (e.g., progress on a new project).

[0827] Input: User's new performance data

[0828] Output: New performance data collected

[0829] New performance data is sent from the terminal to the server.

[0830] Step 5: Learning Phase

[0831] The server analyzes the new performance data sent from the device, again using NLP techniques and data analysis algorithms.

[0832] Input: New performance data

[0833] Output: Evaluation results of the effectiveness of compliments

[0834] The server evaluates the impact that a particular compliment had on the user's performance and feeds the results back into the algorithm, which then influences the next compliment generation.

[0835] The server feeds the evaluation results back into the algorithm to improve the accuracy of compliment generation.

[0836] (Application example 1)

[0837] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0838] In modern society, it is important to provide optimal feedback and praise to individual users to improve their viewing experience. However, existing systems do not adequately establish methods for generating personalized praise based on viewing history and rating data to improve user motivation. Therefore, a method for providing effective, personalized feedback and improving the viewing experience is needed.

[0839] 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.

[0840] In this invention, the server includes means for collecting past data of an individual, means for analyzing the collected data to identify the individual's strengths and efforts, means for generating personalized compliments based on the identified strengths and efforts, means for presenting the generated compliments to the individual, means for collecting performance data of the individual after the compliments have been presented, means for analyzing the collected performance data to evaluate the effectiveness of the compliments and update the compliment generation algorithm, and means for generating personalized compliments in the content distribution service and improving the user's viewing experience based on the viewing data, thereby making it possible to generate and provide individually optimized compliments based on the user's viewing history.

[0841] "Personal past data" refers to information about an individual's past actions and results, including viewing history, rating data, and feedback.

[0842] "Means of collection" refers to methods and devices for collecting necessary data from personal devices and servers using databases and APIs.

[0843] "Means for analysis" refers to technologies for analyzing collected data and evaluating individual characteristics and performance, including natural language processing and machine learning algorithms.

[0844] "Identification methods" refers to techniques and methods for extracting useful information from the analyzed data and identifying individual strengths and efforts.

[0845] "Means for generation" refers to AI models and templates for creating personalized compliments based on the analysis results.

[0846] The term "presenting means" refers to a device or method, including a user interface or notification function, for visually or audibly displaying the generated compliment to the user.

[0847] "Collected performance data" is information recorded by the device regarding an individual's new behavior or achievements after the praise is given.

[0848] "Means to update the algorithm" refers to techniques or methods for reevaluating collected performance data and improving or adjusting the original compliment generation algorithm.

[0849] "Content distribution service" refers to a service that provides users with viewing content such as movies, television programs, and documentaries.

[0850] "Viewing data" is information relating to content viewed by a user, and includes viewing history, viewing time, ratings, comments, and the like.

[0851] A "generative AI model" refers to an artificial intelligence algorithm that generates new text or compliments based on given data.

[0852] A "prompt" is a sentence that describes a question or instruction to be input to a generative AI model.

[0853] This invention is a system that provides individually optimized compliments to improve the user's viewing experience in a content distribution service. The system of the present invention is mainly composed of three entities: a server, a terminal, and a user.

[0854] First, the server collects the user's past data, including viewing history, rating data, and feedback. To collect this data, the server issues a data request to the device, and the device sends the data to the server. Based on this collected data, the server identifies the individual's strengths and efforts.

[0855] Based on the information identified from the analyzed data, the server generates personalized compliments using a generative AI model that selects appropriate templates to generate specific compliments. For example, if a user has watched many documentaries, a compliment acknowledging their curiosity and inquisitiveness will be generated.

[0856] The generated compliment is presented to the user via the terminal. After the compliment is presented to the user, the terminal continuously monitors and records the user's new performance data, allowing the server to collect data to measure the impact of the compliment.

[0857] The server analyzes the collected new performance data and evaluates the effectiveness of the compliments. It identifies whether a particular compliment was effective and uses the results as feedback to improve the algorithm. This cycle allows the server to constantly learn in order to generate more effective compliments.

[0858] For example, if the user has watched a lot of documentaries about "environmental issues," we might generate a compliment for their interest and curiosity:

[0859] "You've been watching a lot of documentaries about environmental issues recently. Your interest and inquisitiveness are admirable! I was particularly impressed by your deep understanding of the 'plastic ocean.'"

[0860] Examples of prompts include:

[0861] "Users watch a lot of documentaries about 'environmental issues.' Generate compliments based on this. For example, we have viewing data for 'Plastic Oceans' and 'The Truth About Climate Change.'"

[0862] This invention makes it possible to generate and provide personalized compliments based on a user's viewing history, which is expected to improve the user's viewing experience and further motivate them to learn and pursue knowledge.

[0863] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0864] Step 1:

[0865] The server issues a data request to the device using a means of collecting personal past data. The device collects data such as viewing history, rating data, and feedback, and sends it to the server. The data request is the input, and the viewing data sent from the device is the output.

[0866] Step 2:

[0867] The server analyzes the collected data and analyzes the viewing history and rating data using a means to identify individual strengths and efforts. Specifically, it uses natural language processing techniques and machine learning algorithms to extract useful keywords and phrases. The viewing data is the input, and the identification of strengths and efforts is the output.

[0868] Step 3:

[0869] The server uses a generative AI model to generate personalized compliments based on the identified strengths and efforts. During this process, it selects an appropriate template and creates a specific compliment. For example, if a user has watched many documentaries, it generates a compliment that recognizes their curiosity and inquisitiveness. The identified results are the input, and the generated compliment is the output.

[0870] Step 4:

[0871] The server sends the generated compliment to the terminal and presents it to the user. The terminal displays the compliment visually or audibly. The generated compliment is the input, and the compliment presented to the user is the output.

[0872] Step 5:

[0873] The device continuously monitors and records new performance data of the user after the compliment is given. This data includes the user's new viewing history and rating data. The performance data after the compliment is given is the input, and the collected performance data is the output.

[0874] Step 6:

[0875] The server analyzes the new performance data collected and evaluates the effectiveness of the compliments. It evaluates whether the compliments were effective and updates the compliment generation algorithm based on the results. The performance data is the input, and the updated algorithm is the output.

[0876] Step 7:

[0877] The server then uses the analyzed results and feedback to retune the algorithm to be more effective when generating the next compliment. This step reinforces the algorithm's learning. The updated algorithm is the input, and the retuned algorithm is the output.

[0878] 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.

[0879] This invention is a system that uses generative AI and an emotion engine to provide personalized compliments to individuals (users). This system operates in cooperation with three entities: a server, a device, and a user, as shown below.

[0880] Data Collection Phase

[0881] The server requests past data from the user's device. The data types include project completion reports, final evaluations, feedback, etc. The user's device searches for this data from its local storage, collects it, and sends it to the server.

[0882] Data analysis phase

[0883] The server analyzes the received data and uses natural language processing technology to identify individual strengths and efforts. For example, it can extract keywords such as "leadership" and "creative problem solving" from project reports to identify individual characteristics.

[0884] Emotion Recognition Phase

[0885] The server uses an emotion engine to recognize the user's emotions. The emotion engine includes voice analysis technology and facial expression analysis technology to determine the user's emotions from the voice and facial expressions they make. For example, if the user is on a voice call, the server analyzes the tone and speed of the voice to identify the user's emotional state.

[0886] Compliment generation phase

[0887] The server generates optimal praise based on the analyzed individual's strengths and efforts, as well as the recognized emotions. First, it selects a praise template that corresponds to the identified strengths and efforts, and then adjusts the expression to match the user's emotional state. For example, if the user is stressed, it reinforces encouraging words, while if the user is relaxed, it emphasizes specific achievements.

[0888] Offering compliments

[0889] The generated compliment is sent from the server to the user's device, which notifies the user, for example, by displaying the compliment as a pop-up notification or as part of a dashboard.

[0890] Feedback gathering phase

[0891] After the compliment is given, the device continuously monitors and records the user's new performance data, including progress and deliverables for new projects.

[0892] Learning Phase

[0893] The server analyzes new performance data sent from the device and evaluates the effectiveness of the compliments. It evaluates how a particular compliment affected the user's performance and updates the compliment generation algorithm based on the results. This process allows the server to provide more effective compliments to the user.

[0894] ---

[0895] As a concrete example, the server collects reports of projects recently completed by users and analyzes the results of their leadership and creative problem-solving. At the same time, the emotion engine identifies when the user is feeling stressed. As a result, the following compliments are generated:

[0896] "Your leadership and creative problem-solving skills have helped the entire team. Your ability to remain calm in difficult situations, especially on this project, has been impressive. Get well rested and move on to the next step!"

[0897] In this way, by linking generative AI with an emotion engine, this invention can provide more personalized compliments to users, improving their performance and motivation.

[0898] The processing flow will be explained below.

[0899] Step 1: Submit a data request

[0900] The server requests past data from the user's device, specifically specifying data such as project completion reports, final evaluations, and feedback.

[0901] Step 2: Collect data

[0902] The device searches for and collects the specified data from the local storage, and then transmits the collected data to the server.

[0903] Step 3: Receiving and Preprocessing Data

[0904] The server receives the data sent from the terminal, converts it into a unified format, and performs preprocessing to make it suitable for analysis.

[0905] Step 4: Text analysis of the data

[0906] The server analyzes the preprocessed text data using natural language processing techniques, specifically, keyword extraction, morphological analysis, and context analysis.

[0907] Step 5: Identify strengths and efforts

[0908] The server identifies the user's strengths and efforts from the analysis results, for example, by extracting evaluation items such as "leadership" and "creative problem solving."

[0909] Step 6: Request Emotion Recognition

[0910] The server sends a request to the device to temporarily collect voice and facial expression data in order to recognize the user's current emotion.

[0911] Step 7: Collect and analyze emotion data

[0912] The device collects the user's voice and facial expression data and sends it to a server, which uses an emotion engine to analyze it and determine the user's current emotional state.

[0913] Step 8: Choose a compliment template

[0914] The server selects from a database praise templates that correspond to the identified strengths and efforts.

[0915] Step 9: Personalize your compliment

[0916] The server generates a personalized compliment based on the selected template, incorporating the user's name, specific achievements, and emotional state.

[0917] Step 10: Send a compliment

[0918] The server transmits the generated compliment to the user's terminal.

[0919] Step 11: Offer a compliment

[0920] The device will notify the user of the compliments it receives, for example, by presenting them as a pop-up notification or as part of the dashboard.

[0921] Step 12: Monitor performance data

[0922] The device continuously monitors and records the user's new performance data after the praise is given, and records the progress and deliverables of the new project.

[0923] Step 13: Submitting feedback data

[0924] The terminal transmits the collected performance data to the server.

[0925] Step 14: Analyze feedback data

[0926] The server analyzes the feedback data sent from the device and evaluates the effectiveness of the compliments, determining how a particular compliment affected the user's performance.

[0927] Step 15: Update the algorithm

[0928] The server updates the compliment generation algorithm based on the evaluation results, improving the effectiveness of the next compliment.

[0929] Through this series of steps, the generative AI and emotion engine work together to provide users with optimized compliments, helping to increase their motivation and improve their performance.

[0930] Example 2

[0931] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0932] Conventionally, feedback received by individuals has been uniform and has not taken into account individual characteristics or emotional states. This has made it difficult to effectively contribute to improving individual motivation and performance. Furthermore, there has been a lack of systems that measure the effectiveness of feedback and improve feedback methods based on that measurement. The present invention aims to solve these problems and provide a system that provides individually optimized feedback.

[0933] 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.

[0934] In this invention, the server includes means for collecting past data of an individual, means for analyzing the collected data to identify the strengths and efforts of the individual, means for generating personalized compliments based on the identified strengths and efforts, means for presenting the generated compliments to the individual, means for collecting performance data of the individual after the compliments have been presented, means for analyzing the collected performance data to evaluate the effectiveness of the compliments and updating the compliment generation algorithm, means for recognizing the user's emotions, and means for adjusting the compliments based on the emotion recognition results, thereby making it possible to provide individually optimized feedback and continuously improve the effectiveness of the feedback.

[0935] "Personal past data" refers to data that records a user's past actions and achievements, including project completion reports, end-of-term evaluations, and feedback.

[0936] "Means of collection" refers to the technology and methods for importing the necessary data from the user's device to the server, and typically involves the use of communication protocols and APIs.

[0937] "Means for analyzing and identifying" refers to techniques and methods for examining received data and identifying individual strengths and efforts, primarily natural language processing techniques.

[0938] "Personalized compliment generators" refer to techniques or methods for creating unique and appropriate compliments based on identified personal characteristics, often leveraging generative AI models.

[0939] "Presentation means" refers to techniques and methods for effectively communicating the generated compliments to the user, including notification systems and dashboard display functions.

[0940] "Means of collecting performance data" refers to the technology or method of capturing data on new user behaviors or outcomes after praise is given, such as a continuous data monitoring system.

[0941] "Means of analyzing collected performance data" refers to techniques and methods for analyzing new data to evaluate the effectiveness of praise, primarily using statistical analysis and machine learning techniques.

[0942] "Means for updating the compliment generation algorithm" refers to techniques and methods for improving the compliment generation method or model based on the analysis results, including training and parameter adjustment of the generative AI model.

[0943] "Means for recognizing a user's emotions" refers to techniques and methods for determining emotions from a user's voice and facial expressions, including voice analysis techniques and facial expression analysis techniques.

[0944] "Means for adjusting compliments based on emotion recognition results" refers to technologies and methods for appropriately changing the content and expression of compliments according to the recognized emotion, such as dynamic language generation using a generative AI model.

[0945] This invention is a system that uses generative AI and an emotion engine to provide personalized compliments to individuals (users). This system works in cooperation with three entities: a server, a device, and a user.

[0946] System configuration

[0947] 1. Data Collection Phase

[0948] The server requests past data from the user's device. Specifically, it sends an HTTP GET request to request project completion reports, final evaluations, feedback, etc. The device retrieves this data from local storage and sends it to the server as an HTTP response. For example, the server sends a request to the device saying, "Please send me the project completion report data," and the device responds by returning the data.

[0949] 2. Data analysis phase

[0950] The server analyzes the received data and uses natural language processing technologies such as Python's NLTK library and Spacy to identify individual strengths and efforts. For example, it extracts keywords such as "leadership" and "creative problem solving" from project reports. This reveals the user's characteristics.

[0951] 3. Emotion Recognition Phase

[0952] The server uses an emotion engine (such as Microsoft Azure Emotion API or Amazon Rekognition) to recognize the user's emotions. Specifically, it analyzes the tone and speed of the voice call and identifies emotions from the user's voice and facial expressions. For example, it uses Google Cloud Speech-to-Text to convert the voice data into text and recognizes emotions based on that text.

[0953] 4. Compliment Generation Phase

[0954] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate optimal compliments based on the analyzed individual's strengths and efforts, as well as the perceived emotions. A prompt is input to the generative AI model, which tailors the response to the user's situation. An example prompt is, "Please praise the user for their leadership and creative problem-solving skills."

[0955] 5. Offering compliments

[0956] The server sends the generated compliment to the user's device, where it can be displayed as a pop-up notification or as part of a dashboard. For example, a compliment might read, "Your leadership and creative problem-solving skills have helped the entire team. It's particularly impressive how you remained calm in difficult situations on this project. Please rest well and move on to the next step."

[0957] 6. Feedback gathering phase

[0958] After the compliment is given, the device continuously monitors and records the user's new performance data, including new project progress and deliverables, and periodically transmits this data to the server.

[0959] 7. Learning Phase

[0960] The server analyzes new performance data sent from the device and evaluates the effectiveness of the compliments. It evaluates how a particular compliment affected the user's performance and updates the compliment generation algorithm based on the results. This process uses machine learning algorithms (e.g., scikit-learn and TensorFlow).

[0961] In this way, by linking generative AI with an emotion engine, the system can provide more personalized compliments to users, improving their performance and motivation.

[0962] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0963] Step 1:

[0964] Data Collection Phase

[0965] The server requests past data from the user's device, specifically by sending an HTTP GET request for data such as project completion reports, final evaluations, and feedback.

[0966] In response to the request, the device retrieves the data from its local storage and sends it to the server as an HTTP response. For example, the server may send a request such as "Please send project completion report data," and the device may provide past data in response.

[0967] Input: Data request from server

[0968] Output: Data response (project completion report, final evaluation, feedback)

[0969] Step 2:

[0970] Data analysis phase

[0971] The server then analyzes the data it receives, using natural language processing techniques like Python's NLTK library and Spacy to identify individual strengths and efforts, such as extracting keywords like "leadership" and "creative problem solving" from project reports.

[0972] Input: User's past data (project completion report, final evaluation, feedback)

[0973] Output: Identified strengths and efforts (e.g., "Leadership," "Creative Problem Solving")

[0974] Step 3:

[0975] Emotion Recognition Phase

[0976] The server recognizes the user's emotions using an emotion engine (e.g., Microsoft Azure Emotion API or Amazon Rekognition).

[0977] It analyzes the tone and speed of voice calls and identifies emotions from the user's voice and facial expressions. For example, it uses Google Cloud Speech-to-Text to convert voice data into text and recognizes emotions based on that text.

[0978] Input: User voice and facial expression data

[0979] Output: User's emotional state (e.g., "stressed," "relaxed")

[0980] Step 4:

[0981] Compliment generation phase

[0982] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate the optimal compliment based on the analyzed individual's strengths, effort, and perceived emotions.

[0983] A prompt is fed into the generative AI model, which tailors its response to the user's situation, such as "Please praise the user for their leadership and creative problem-solving skills."

[0984] Input: personal strengths and efforts, user emotional state, prompt text

[0985] Output: Personalized compliment

[0986] Step 5:

[0987] Offering compliments

[0988] The generated compliment is sent from the server to the user's terminal.

[0989] The device will display the compliment as a pop-up notification or as part of the dashboard, such as, "Your leadership and creative problem-solving skills have helped the entire team. Your calmness in difficult situations, especially on this project, has been impressive. Please rest well and move on to the next step."

[0990] Input: Generated compliment

[0991] Output: User notification

[0992] Step 6:

[0993] Feedback gathering phase

[0994] After the compliment is given, the device continuously monitors and records the user's new performance data, including new project progress and deliverables, and periodically transmits this data to the server.

[0995] Input: User's new performance data

[0996] Output: Send data to the server

[0997] Step 7:

[0998] Learning Phase

[0999] The server analyzes new performance data sent from the device and evaluates the effectiveness of the compliments, assessing how a particular compliment affected the user's performance and updating the compliment-generation algorithm based on the results.

[1000] This process uses machine learning algorithms (e.g., scikit-learn and TensorFlow).

[1001] Input: New performance data, effectiveness evaluation results

[1002] Output: The updated compliment generation algorithm

[1003] (Application example 2)

[1004] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1005] Conventional performance improvement systems provide uniform feedback without considering the individual's emotional state, which limits their effectiveness in improving motivation and performance. Furthermore, the content of the feedback is not optimized for the individual's characteristics and circumstances, reducing the feedback's acceptability and effectiveness. Furthermore, providing feedback in real time is difficult and often lacks timeliness. Therefore, there is a need for a system that can recognize each individual's emotional state in real time and provide optimized praise.

[1006] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting past data of an individual, means for analyzing the collected data to identify the individual's strengths and efforts, means for generating personalized compliments based on the identified strengths and efforts, means for presenting the generated compliments to the individual, means for collecting performance data of the individual after the compliments have been presented, means for analyzing the collected performance data to evaluate the effectiveness of the compliments and updating the compliment generation algorithm, means for recognizing the individual's emotional state via an external device that collects audio and video data, means for adjusting the compliments based on the recognized emotional state, and means for displaying the adjusted compliments on the external device. This allows personalized compliments optimized for the individual's emotional state to be provided in real time, thereby improving motivation and performance.

[1007] "Personal past data" refers to information about an individual's past performance and behavior, such as project completion reports, end-of-period evaluations, and feedback.

[1008] "Means of collection" refers to the means by which an individual's historical data is collected in a particular manner, such as by local scanning or retrieval from a remote server.

[1009] "Means of analysis" refers to technologies for analyzing collected data and extracting meaningful information, including natural language processing technology and data mining technology.

[1010] "Means for identifying individual strengths and efforts" refers to technologies that identify individual talents and struggles from analyzed data, including specialized algorithms and machine learning models.

[1011] "Means for generating personalized compliments" refers to technology for creating personalized compliments based on identified strengths and efforts.

[1012] "Means for presenting the generated compliment to the individual" refers to technology that notifies or displays the generated compliment to the user, and includes, for example, devices such as smart glasses or a smartphone.

[1013] "Performance data" is data about an individual's achievements and behavior obtained after the presentation of praise.

[1014] "Means for evaluating the effectiveness of compliments and updating the compliment generation algorithm" refers to technology that measures the impact of presented compliments on an individual's performance and, based on the results, improves the algorithm that generates future compliments.

[1015] "External device for collecting audio and video data" refers to a device for capturing personal audio and video, including smart glasses and head-mounted displays.

[1016] "Means for recognizing an individual's emotional state" refers to technology that analyzes collected audio and video data to identify an individual's emotions (e.g., joy, sadness, stress, etc.).

[1017] "Methods for tailoring compliments based on perceived emotional state" refers to techniques for altering the content and tone of compliments to match identified emotional states.

[1018] "Means for displaying the tailored compliment on an external device" refers to display technology for providing the tailored compliment to the user in a viewable manner, including smart glasses or other display devices.

[1019] As an embodiment of the present invention, a factory worker support system using smart glasses will be taken as an example. This system operates in cooperation with three entities: a server, smart glasses (terminals), and a user.

[1020] First, the smart glasses collect the worker's voice and video data and transmit it to a server in real time. The smart glasses are equipped with a camera and microphone, which are used to record daily work.

[1021] The server utilizes several technologies to execute the following series of processes: First, the server analyzes the audio and video data received from the smart glasses and recognizes the user's emotional state using an emotion engine (e.g., Microsoft Azure Cognitive Services' Emotion API or Face API). The server analyzes tone, speed, volume, etc. from the audio data, and facial expressions from the video data.

[1022] Next, the server collects the user's past data (e.g., project completion reports, final evaluations, feedback, etc.) and analyzes it using natural language processing techniques (e.g., Google Cloud Natural Language API and Hugging Face transformers) to identify the user's strengths and efforts.

[1023] Based on the identified strengths and efforts, as well as the perceived emotional state, the server uses a generative AI model (e.g., OpenAI's GPT-4) to generate a personalized compliment using prompts such as:

[1024] Example prompt sentence:

[1025] Username: Yamada Taro

[1026] Project: Launching a new product line

[1027] Rating: Very High Leadership

[1028] Emotional state: Stressed

[1029] Generate a suitable compliment

[1030] The generated compliments are sent to the smart glasses and displayed to the user in real time, for example as a pop-up notification on the smart glasses display.

[1031] After the user receives a compliment, new performance data collected from the smart glasses continues to be sent to the server, which analyzes the data and evaluates the effect of the compliment on the user's performance. Based on the evaluation results, the compliment generation algorithm is updated accordingly.

[1032] This allows the system to provide users with personalized praise that is optimized for their emotional state, thereby increasing motivation and improving performance.

[1033] As a concrete example, if a user demonstrates exceptional leadership in the launch of a new product line and analysis using the emotion engine reveals that they are feeling stressed, the following praise could be offered: "Your leadership and creative problem-solving skills have helped the entire team. It's particularly impressive that you were able to remain calm in difficult situations in this project. Take a good rest and move on to the next step!" In this way, appropriate feedback can be provided to users in real time, improving their performance and motivation.

[1034] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1035] Step 1:

[1036] Smart glasses (terminals) collect the voice and video data of workers. The smart glasses are equipped with a camera and microphone to capture video and audio data of daily work. This data is sent to a server in real time.

[1037] Input: Video and audio data of worker

[1038] Output: Video and audio data transmitted in real time

[1039] Step 2:

[1040] The server analyzes the received audio and video data and uses an emotion engine to recognize the user's emotional state. Specifically, it uses the Emotion API and Face API of Microsoft Azure Cognitive Services to analyze tone, speed, and volume from audio data and facial expressions from video data.

[1041] Input: Video and audio data

[1042] Data processing / data calculation: Emotion analysis of audio and video

[1043] Output: User's emotional state (e.g., stress, joy)

[1044] Step 3:

[1045] The server collects users' past data (project completion reports, final evaluations, feedback, etc.) and analyzes it using natural language processing technology. It uses Google Cloud Natural Language API and Hugging Face transformers to identify individual strengths and efforts.

[1046] Input: Historical data

[1047] Data processing / data calculation: Analysis using natural language processing

[1048] Output: User strengths and efforts (e.g., leadership, creative problem-solving)

[1049] Step 4:

[1050] The server uses a generative AI model to generate personalized compliments based on the perceived emotional state and identified strengths and efforts, using OpenAI's GPT-4 to create prompts and generate results.

[1051] Input: User strengths, effort, and emotional state

[1052] Data processing / data calculation: Generating compliments using generative AI models

[1053] Output: Personalized compliment

[1054] Step 5:

[1055] The server sends the generated compliment to the smart glasses and presents it to the user in real time, as a pop-up notification on the smart glasses' display.

[1056] Input: Generated compliment

[1057] Output: Compliments displayed on the smart glasses display

[1058] Step 6:

[1059] After the user receives the compliment, the smart glasses collect new performance data and send it to the server, such as project progress and deliverables.

[1060] Input: User's new performance data

[1061] Output: New performance data sent to the server

[1062] Step 7:

[1063] The server analyzes the new performance data, evaluates the effectiveness of the compliments, and updates the compliment generation algorithm based on the evaluation results.

[1064] Input: New performance data

[1065] Data processing / data calculation: analysis of performance data and evaluation of effects

[1066] Output: Updated compliment generation algorithm

[1067] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1068] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1069] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1070] [Fourth embodiment]

[1071] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1072] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1073] 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).

[1074] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1075] 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.

[1076] 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).

[1077] 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.

[1078] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1079] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1080] 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.

[1081] 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.

[1082] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1083] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1084] This invention is a system that uses generative AI to provide individually optimized compliments. The system includes three entities: a server, a terminal, and a user, which work together to perform the following steps:

[1085] Data Collection Phase

[1086] The server first issues a request to collect past data about an individual (user). The data includes project completion reports, final evaluations, feedback, etc., and is stored on the user's device. The user's device is responsible for sending this data to the server.

[1087] Data analysis phase

[1088] The server analyzes the received data and identifies individual strengths and efforts. Specifically, it uses natural language processing technology to extract useful keywords and phrases from the collected text data. For example, it identifies characteristics such as "leadership" and "creative problem solving" from project reports.

[1089] Compliment generation phase

[1090] The server then generates the optimal compliment based on the analysis results. First, it selects a compliment template that corresponds to the identified strengths and efforts. Then, it creates a compliment that is optimized for each individual user based on that template. During this process, it incorporates the user's specific achievements and name to enhance specificity and personalization.

[1091] Feedback gathering phase

[1092] The device presents the generated compliment to the user. After presenting the compliment, the device continuously monitors and records new performance data of the user, thereby collecting data that measures the impact of the compliment.

[1093] Learning Phase

[1094] The server analyzes the collected new performance data and evaluates the effectiveness of the compliments. It identifies whether a particular compliment was effective and uses the results as feedback to improve the algorithm. This cycle allows the server to constantly learn in order to generate more effective compliments.

[1095] ---

[1096] For example, a server collects reports of recently completed projects from users and analyzes them to identify strengths such as leadership and creative problem-solving. Based on the results, the server generates a compliment like this:

[1097] "Your recent project was particularly impressive, especially the way you led your team to come up with creative solutions. Your leadership skills are truly impressive!"

[1098] The praise is then displayed on the user's device, and the user is motivated by the praise to take on a new project. The progress and results are recorded by the device, and the server analyzes the data again to evaluate the effectiveness of the praise.

[1099] Through this process, the system continues to provide the user with more appropriate and effective praise, promoting personal growth.

[1100] The processing flow will be explained below.

[1101] Step 1: Submit a data request

[1102] The server requests past data from the user's device, specifically specifying data such as project completion reports, final evaluations, and feedback.

[1103] Step 2: Collect data

[1104] The user's device searches and collects the specified data from the local storage, and if the data is found, sends it to the server.

[1105] Step 3: Receiving and Preprocessing Data

[1106] The server receives the data sent from the terminal and performs preprocessing, which unifies the data format and converts it into a format that is easy to analyze.

[1107] Step 4: Text analysis of the data

[1108] The server analyzes the collected text data using natural language processing technology, specifically, keyword extraction, morphological analysis, and context analysis.

[1109] Step 5: Identify strengths and efforts

[1110] The server identifies the user's strengths and efforts from the analysis results, for example, by extracting evaluation items such as "leadership" and "creative problem solving."

[1111] Step 6: Select a compliment template

[1112] The server selects from a database praise templates that correspond to the identified strengths and efforts.

[1113] Step 7: Personalize your compliment

[1114] The server then generates a personalized compliment based on the selected template, incorporating the user's name and specific achievements.

[1115] Step 8: Send a compliment

[1116] The server transmits the generated compliment to the user's terminal.

[1117] Step 9: Offer a compliment

[1118] The device will notify the user of any compliments received, including via a pop-up notification or display on the dashboard.

[1119] Step 10: Monitor performance data

[1120] The device continuously monitors and records new performance data of the user after the praise is given, such as the progress and deliverables of a new project.

[1121] Step 11: Submitting feedback data

[1122] The terminal transmits the collected performance data to the server.

[1123] Step 12: Analyze the feedback data

[1124] The server analyzes the feedback data sent from the device and evaluates the effectiveness of the compliments, checking whether a particular compliment was effective.

[1125] Step 13: Update the algorithm

[1126] The server updates the compliment generation algorithm based on the evaluation results, thereby improving the compliment generation algorithm to be more effective.

[1127] Through this series of steps, the generative AI continues to provide the user with optimized praise, helping to increase their motivation and improve their performance.

[1128] Example 1

[1129] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1130] Conventional compliment generation systems lacked a means to effectively provide personalized compliments to individuals. Furthermore, there was no way to evaluate the impact of compliments on the user's performance and reflect that feedback in the generation of next compliments. This made it difficult to provide sustained support for improving motivation.

[1131] 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.

[1132] In this invention, the server includes: means for collecting past data of an individual; means for analyzing the collected data to identify the individual's strengths and efforts; means for generating personalized compliments based on the identified strengths and efforts; means for presenting the generated compliments to the individual; means for collecting performance data of the individual after the compliments have been presented; means for analyzing the collected performance data to evaluate the effectiveness of the compliments and updating the compliment generation algorithm; means for including a series of programs for performing multiple data processing phases; means for using a communication protocol required for transmitting and receiving data; means for generating compliments corresponding to the identified strengths and efforts using generative AI technology; and means for inputting prompt sentences into the generative AI model. This makes it possible to continuously provide personalized compliments and improve user motivation.

[1133] "Personal historical data" refers to information related to a user's past activities and achievements, including work reports, evaluation results, and feedback comments.

[1134] "Means of collection" refers to the method or device used to collect data. It refers to the communication protocol or software used by the server to obtain data from the user's device.

[1135] "Means of analysis" refers to the technologies, algorithms, and software used to analyze data. Specifically, this includes natural language processing technology and data analysis algorithms.

[1136] "Means for identifying strengths and efforts" refers to a method for identifying users' advantages and efforts from the collected data. This is achieved using natural language processing techniques.

[1137] A "compliment generator" is a method or device that generates optimal compliments for a user, using generative AI technology to create compliments that correspond to specific strengths or efforts.

[1138] The "presenting means" refers to a method or device for showing the generated compliment to the user. This is done through the terminal.

[1139] "Performance data" is information related to new user activity and achievements collected after the praise is given.

[1140] The "measures for evaluation and updating" are methods for analyzing collected performance data, measuring the effectiveness of praise, and improving the algorithm.

[1141] The "data processing phase" refers to a series of processing steps: data collection, analysis, praise generation, presentation, feedback collection, and learning.

[1142] A "communications protocol" is a set of rules or standardized methods used to send and receive data. Examples include HTTPS.

[1143] "Generative AI technology" is an artificial intelligence technology that generates natural language based on specific input. The generative AI model uses this technology to create compliments.

[1144] A "prompt" is text that is input to a generative AI model, which then generates an appropriate compliment.

[1145] This invention is a system that uses generative AI to provide individually optimized compliments. The system mainly consists of three entities: a server, a device, and a user. These entities work together to perform the following processes:

[1146] The server first issues a request to collect past data for an individual (user). This request is sent to the user's device via the HTTP protocol. For example, an Amazon Web Services (AWS) EC2 instance is used as the server, and Apache or Nginx is used to send and receive data. The user's device (smartphone or PC) sends data via a client application that sends text data such as project completion reports, evaluation results, and feedback comments to the server.

[1147] The server then analyzes the received text data using natural language processing (NLP) techniques. This analysis is performed using Python libraries such as SpaCy and NLTK. The server uses these libraries to extract useful keywords and phrases (e.g., "leadership" or "creative problem solving") from the data. This extracted data is then stored in a database (e.g., PostgreSQL or MongoDB).

[1148] Once the analysis is complete, the server uses generative AI technology to generate the optimal compliment based on the analysis results. Specifically, it uses an AI model such as OpenAI's GPT-3 to select a compliment template and input a specific prompt. For example, the prompt could read, "The user demonstrated leadership and provided a creative solution in a recent project. Please generate a compliment based on this content." The AI ​​model then generates a specific compliment based on this prompt.

[1149] The server sends the generated compliments to the device, which displays them to the user. The device also continuously monitors and records new performance data to measure the impact of the compliments on the user's performance. This data is then sent back to the server, which analyzes the new data and evaluates which compliments were most effective. The evaluation results are fed back to the algorithm and reflected in future compliment generation.

[1150] For example, a server collects reports of recently completed projects from users and analyzes them to identify strengths such as leadership and creative problem-solving. Based on the results, the server generates a compliment like this:

[1151] "Your recent project was particularly impressive, especially the way you led your team to come up with creative solutions. Your leadership skills are truly impressive!"

[1152] The praise is then displayed on the user's device, and the user is motivated by the praise to take on a new project. The progress and results are recorded by the device, and the server analyzes the data again to evaluate the effectiveness of the praise.

[1153] By implementing this system, it is possible to continuously provide appropriate and effective praise to users and promote their personal growth.

[1154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1155] Step 1: Data collection phase

[1156] The server first issues an HTTP request to the device to collect past performance data for the individual. This is a data collection request, requesting data such as project completion reports, evaluation results, and feedback comments stored on the user's device.

[1157] Input: HTTP request

[1158] Output: Text data saved on the device (project completion report, evaluation results, feedback comments)

[1159] After receiving the request, the device sends the stored data to the server using a secure communication protocol (e.g., HTTPS).

[1160] The server stores the received data in temporary storage and prepares for the next phase.

[1161] Step 2: Data analysis phase

[1162] The server analyzes the collected text data using natural language processing (NLP) techniques, specifically using the Python libraries SpaCy and NLTK.

[1163] Input: Collected text data

[1164] Output: Keywords or phrases (e.g., "leadership," "creative problem solving")

[1165] The server extracts useful keywords and phrases from the analysis results and stores them in a database.

[1166] Step 3: Compliment generation phase

[1167] The server uses a generative AI model based on the analysis results to generate the optimal compliment, specifically using a generative AI model such as OpenAI's GPT-3.

[1168] Input: Keyword or phrase

[1169] Output: Generated compliment

[1170] The generative AI model is given a specific prompt, such as "The user demonstrated leadership and provided a creative solution in a recent project. Based on this, please generate a compliment."

[1171] The server stores the generated compliments in a database and prepares them to be sent to the device.

[1172] Step 4: Feedback gathering phase

[1173] The terminal displays the compliment sent from the server to the user.

[1174] Input: Generated compliment

[1175] Output: The compliment displayed to the user

[1176] After displaying the compliment, the device collects new performance data (e.g., progress on a new project).

[1177] Input: User's new performance data

[1178] Output: New performance data collected

[1179] New performance data is sent from the terminal to the server.

[1180] Step 5: Learning Phase

[1181] The server analyzes the new performance data sent from the device, again using NLP techniques and data analysis algorithms.

[1182] Input: New performance data

[1183] Output: Evaluation results of the effectiveness of compliments

[1184] The server evaluates the impact that a particular compliment had on the user's performance and feeds the results back into the algorithm, which then influences the next compliment generation.

[1185] The server feeds the evaluation results back into the algorithm to improve the accuracy of compliment generation.

[1186] (Application example 1)

[1187] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1188] In modern society, it is important to provide optimal feedback and praise to individual users to improve their viewing experience. However, existing systems do not adequately establish methods for generating personalized praise based on viewing history and rating data to improve user motivation. Therefore, a method for providing effective, personalized feedback and improving the viewing experience is needed.

[1189] 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.

[1190] In this invention, the server includes means for collecting past data of an individual, means for analyzing the collected data to identify the individual's strengths and efforts, means for generating personalized compliments based on the identified strengths and efforts, means for presenting the generated compliments to the individual, means for collecting performance data of the individual after the compliments have been presented, means for analyzing the collected performance data to evaluate the effectiveness of the compliments and update the compliment generation algorithm, and means for generating personalized compliments in the content distribution service and improving the user's viewing experience based on the viewing data, thereby making it possible to generate and provide individually optimized compliments based on the user's viewing history.

[1191] "Personal past data" refers to information about an individual's past actions and results, including viewing history, rating data, and feedback.

[1192] "Means of collection" refers to methods and devices for collecting necessary data from personal devices and servers using databases and APIs.

[1193] "Means for analysis" refers to technologies for analyzing collected data and evaluating individual characteristics and performance, including natural language processing and machine learning algorithms.

[1194] "Identification methods" refers to techniques and methods for extracting useful information from the analyzed data and identifying individual strengths and efforts.

[1195] "Means for generation" refers to AI models and templates for creating personalized compliments based on the analysis results.

[1196] The term "presenting means" refers to a device or method, including a user interface or notification function, for visually or audibly displaying the generated compliment to the user.

[1197] "Collected performance data" is information recorded by the device regarding an individual's new behavior or achievements after the praise is given.

[1198] "Means to update the algorithm" refers to techniques or methods for reevaluating collected performance data and improving or adjusting the original compliment generation algorithm.

[1199] "Content distribution service" refers to a service that provides users with viewing content such as movies, television programs, and documentaries.

[1200] "Viewing data" is information relating to content viewed by a user, and includes viewing history, viewing time, ratings, comments, and the like.

[1201] A "generative AI model" refers to an artificial intelligence algorithm that generates new text or compliments based on given data.

[1202] A "prompt" is a sentence that describes a question or instruction to be input to a generative AI model.

[1203] This invention is a system that provides individually optimized compliments to improve the user's viewing experience in a content distribution service. The system of the present invention is mainly composed of three entities: a server, a terminal, and a user.

[1204] First, the server collects the user's past data, including viewing history, rating data, and feedback. To collect this data, the server issues a data request to the device, and the device sends the data to the server. Based on this collected data, the server identifies the individual's strengths and efforts.

[1205] Based on the information identified from the analyzed data, the server generates personalized compliments using a generative AI model that selects appropriate templates to generate specific compliments. For example, if a user has watched many documentaries, a compliment acknowledging their curiosity and inquisitiveness will be generated.

[1206] The generated compliment is presented to the user via the terminal. After the compliment is presented to the user, the terminal continuously monitors and records the user's new performance data, allowing the server to collect data to measure the impact of the compliment.

[1207] The server analyzes the collected new performance data and evaluates the effectiveness of the compliments. It identifies whether a particular compliment was effective and uses the results as feedback to improve the algorithm. This cycle allows the server to constantly learn in order to generate more effective compliments.

[1208] For example, if the user has watched a lot of documentaries about "environmental issues," we might generate a compliment for their interest and curiosity:

[1209] "You've been watching a lot of documentaries about environmental issues recently. Your interest and inquisitiveness are admirable! I was particularly impressed by your deep understanding of the 'plastic ocean.'"

[1210] Examples of prompts include:

[1211] "Users watch a lot of documentaries about 'environmental issues.' Generate compliments based on this. For example, we have viewing data for 'Plastic Oceans' and 'The Truth About Climate Change.'"

[1212] This invention makes it possible to generate and provide personalized compliments based on a user's viewing history, which is expected to improve the user's viewing experience and further motivate them to learn and pursue knowledge.

[1213] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1214] Step 1:

[1215] The server issues a data request to the device using a means of collecting personal past data. The device collects data such as viewing history, rating data, and feedback, and sends it to the server. The data request is the input, and the viewing data sent from the device is the output.

[1216] Step 2:

[1217] The server analyzes the collected data and analyzes the viewing history and rating data using a means to identify individual strengths and efforts. Specifically, it uses natural language processing techniques and machine learning algorithms to extract useful keywords and phrases. The viewing data is the input, and the identification of strengths and efforts is the output.

[1218] Step 3:

[1219] The server uses a generative AI model to generate personalized compliments based on the identified strengths and efforts. During this process, it selects an appropriate template and creates a specific compliment. For example, if a user has watched many documentaries, it generates a compliment that recognizes their curiosity and inquisitiveness. The identified results are the input, and the generated compliment is the output.

[1220] Step 4:

[1221] The server sends the generated compliment to the terminal and presents it to the user. The terminal displays the compliment visually or audibly. The generated compliment is the input, and the compliment presented to the user is the output.

[1222] Step 5:

[1223] The device continuously monitors and records new performance data of the user after the compliment is given. This data includes the user's new viewing history and rating data. The performance data after the compliment is given is the input, and the collected performance data is the output.

[1224] Step 6:

[1225] The server analyzes the new performance data collected and evaluates the effectiveness of the compliments. It evaluates whether the compliments were effective and updates the compliment generation algorithm based on the results. The performance data is the input, and the updated algorithm is the output.

[1226] Step 7:

[1227] The server then uses the analyzed results and feedback to retune the algorithm to be more effective when generating the next compliment. This step reinforces the algorithm's learning. The updated algorithm is the input, and the retuned algorithm is the output.

[1228] 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.

[1229] This invention is a system that uses generative AI and an emotion engine to provide personalized compliments to individuals (users). This system operates in cooperation with three entities: a server, a device, and a user, as shown below.

[1230] Data Collection Phase

[1231] The server requests past data from the user's device. The data types include project completion reports, final evaluations, feedback, etc. The user's device searches for this data from its local storage, collects it, and sends it to the server.

[1232] Data analysis phase

[1233] The server analyzes the received data and uses natural language processing technology to identify individual strengths and efforts. For example, it can extract keywords such as "leadership" and "creative problem solving" from project reports to identify individual characteristics.

[1234] Emotion Recognition Phase

[1235] The server uses an emotion engine to recognize the user's emotions. The emotion engine includes voice analysis technology and facial expression analysis technology to determine the user's emotions from the voice and facial expressions they make. For example, if the user is on a voice call, the server analyzes the tone and speed of the voice to identify the user's emotional state.

[1236] Compliment generation phase

[1237] The server generates optimal praise based on the analyzed individual's strengths and efforts, as well as the recognized emotions. First, it selects a praise template that corresponds to the identified strengths and efforts, and then adjusts the expression to match the user's emotional state. For example, if the user is stressed, it reinforces encouraging words, while if the user is relaxed, it emphasizes specific achievements.

[1238] Offering compliments

[1239] The generated compliment is sent from the server to the user's device, which notifies the user, for example, by displaying the compliment as a pop-up notification or as part of a dashboard.

[1240] Feedback gathering phase

[1241] After the compliment is given, the device continuously monitors and records the user's new performance data, including progress and deliverables for new projects.

[1242] Learning Phase

[1243] The server analyzes new performance data sent from the device and evaluates the effectiveness of the compliments. It evaluates how a particular compliment affected the user's performance and updates the compliment generation algorithm based on the results. This process allows the server to provide more effective compliments to the user.

[1244] ---

[1245] As a concrete example, the server collects reports of projects recently completed by users and analyzes the results of their leadership and creative problem-solving. At the same time, the emotion engine identifies when the user is feeling stressed. As a result, the following compliments are generated:

[1246] "Your leadership and creative problem-solving skills have helped the entire team. Your ability to remain calm in difficult situations, especially on this project, has been impressive. Get well rested and move on to the next step!"

[1247] In this way, by linking generative AI with an emotion engine, this invention can provide more personalized compliments to users, improving their performance and motivation.

[1248] The processing flow will be explained below.

[1249] Step 1: Submit a data request

[1250] The server requests past data from the user's device, specifically specifying data such as project completion reports, final evaluations, and feedback.

[1251] Step 2: Collect data

[1252] The device searches for and collects the specified data from the local storage, and then transmits the collected data to the server.

[1253] Step 3: Receiving and Preprocessing Data

[1254] The server receives the data sent from the terminal, converts it into a unified format, and performs preprocessing to make it suitable for analysis.

[1255] Step 4: Text analysis of the data

[1256] The server analyzes the preprocessed text data using natural language processing techniques, specifically, keyword extraction, morphological analysis, and context analysis.

[1257] Step 5: Identify strengths and efforts

[1258] The server identifies the user's strengths and efforts from the analysis results, for example, by extracting evaluation items such as "leadership" and "creative problem solving."

[1259] Step 6: Request Emotion Recognition

[1260] The server sends a request to the device to temporarily collect voice and facial expression data in order to recognize the user's current emotion.

[1261] Step 7: Collect and analyze emotion data

[1262] The device collects the user's voice and facial expression data and sends it to a server, which uses an emotion engine to analyze it and determine the user's current emotional state.

[1263] Step 8: Choose a compliment template

[1264] The server selects from a database praise templates that correspond to the identified strengths and efforts.

[1265] Step 9: Personalize your compliment

[1266] The server generates a personalized compliment based on the selected template, incorporating the user's name, specific achievements, and emotional state.

[1267] Step 10: Send a compliment

[1268] The server transmits the generated compliment to the user's terminal.

[1269] Step 11: Offer a compliment

[1270] The device will notify the user of the compliments it receives, for example, by presenting them as a pop-up notification or as part of the dashboard.

[1271] Step 12: Monitor performance data

[1272] The device continuously monitors and records the user's new performance data after the praise is given, and records the progress and deliverables of the new project.

[1273] Step 13: Submitting feedback data

[1274] The terminal transmits the collected performance data to the server.

[1275] Step 14: Analyze feedback data

[1276] The server analyzes the feedback data sent from the device and evaluates the effectiveness of the compliments, determining how a particular compliment affected the user's performance.

[1277] Step 15: Update the algorithm

[1278] The server updates the compliment generation algorithm based on the evaluation results, improving the effectiveness of the next compliment.

[1279] Through this series of steps, the generative AI and emotion engine work together to provide users with optimized compliments, helping to increase their motivation and improve their performance.

[1280] Example 2

[1281] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1282] Conventionally, feedback received by individuals has been uniform and has not taken into account individual characteristics or emotional states. This has made it difficult to effectively contribute to improving individual motivation and performance. Furthermore, there has been a lack of systems that measure the effectiveness of feedback and improve feedback methods based on that measurement. The present invention aims to solve these problems and provide a system that provides individually optimized feedback.

[1283] 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.

[1284] In this invention, the server includes means for collecting past data of an individual, means for analyzing the collected data to identify the strengths and efforts of the individual, means for generating personalized compliments based on the identified strengths and efforts, means for presenting the generated compliments to the individual, means for collecting performance data of the individual after the compliments have been presented, means for analyzing the collected performance data to evaluate the effectiveness of the compliments and updating the compliment generation algorithm, means for recognizing the user's emotions, and means for adjusting the compliments based on the emotion recognition results, thereby making it possible to provide individually optimized feedback and continuously improve the effectiveness of the feedback.

[1285] "Personal past data" refers to data that records a user's past actions and achievements, including project completion reports, end-of-term evaluations, and feedback.

[1286] "Means of collection" refers to the technology and methods for importing the necessary data from the user's device to the server, and typically involves the use of communication protocols and APIs.

[1287] "Means for analyzing and identifying" refers to techniques and methods for examining received data and identifying individual strengths and efforts, primarily natural language processing techniques.

[1288] "Personalized compliment generators" refer to techniques or methods for creating unique and appropriate compliments based on identified personal characteristics, often leveraging generative AI models.

[1289] "Presentation means" refers to techniques and methods for effectively communicating the generated compliments to the user, including notification systems and dashboard display functions.

[1290] "Means of collecting performance data" refers to the technology or method of capturing data on new user behaviors or outcomes after praise is given, such as a continuous data monitoring system.

[1291] "Means of analyzing collected performance data" refers to techniques and methods for analyzing new data to evaluate the effectiveness of praise, primarily using statistical analysis and machine learning techniques.

[1292] "Means for updating the compliment generation algorithm" refers to techniques and methods for improving the compliment generation method or model based on the analysis results, including training and parameter adjustment of the generative AI model.

[1293] "Means for recognizing a user's emotions" refers to techniques and methods for determining emotions from a user's voice and facial expressions, including voice analysis techniques and facial expression analysis techniques.

[1294] "Means for adjusting compliments based on emotion recognition results" refers to technologies and methods for appropriately changing the content and expression of compliments according to the recognized emotion, such as dynamic language generation using a generative AI model.

[1295] This invention is a system that uses generative AI and an emotion engine to provide personalized compliments to individuals (users). This system works in cooperation with three entities: a server, a device, and a user.

[1296] System configuration

[1297] 1. Data Collection Phase

[1298] The server requests past data from the user's device. Specifically, it sends an HTTP GET request to request project completion reports, final evaluations, feedback, etc. The device retrieves this data from local storage and sends it to the server as an HTTP response. For example, the server sends a request to the device saying, "Please send me the project completion report data," and the device responds by returning the data.

[1299] 2. Data analysis phase

[1300] The server analyzes the received data and uses natural language processing technologies such as Python's NLTK library and Spacy to identify individual strengths and efforts. For example, it extracts keywords such as "leadership" and "creative problem solving" from project reports. This reveals the user's characteristics.

[1301] 3. Emotion Recognition Phase

[1302] The server uses an emotion engine (such as Microsoft Azure Emotion API or Amazon Rekognition) to recognize the user's emotions. Specifically, it analyzes the tone and speed of the voice call and identifies emotions from the user's voice and facial expressions. For example, it uses Google Cloud Speech-to-Text to convert the voice data into text and recognizes emotions based on that text.

[1303] 4. Compliment Generation Phase

[1304] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate optimal compliments based on the analyzed individual's strengths and efforts, as well as the perceived emotions. A prompt is input to the generative AI model, which tailors the response to the user's situation. An example prompt is, "Please praise the user for their leadership and creative problem-solving skills."

[1305] 5. Offering compliments

[1306] The server sends the generated compliment to the user's device, where it can be displayed as a pop-up notification or as part of a dashboard. For example, a compliment might read, "Your leadership and creative problem-solving skills have helped the entire team. It's particularly impressive how you remained calm in difficult situations on this project. Please rest well and move on to the next step."

[1307] 6. Feedback gathering phase

[1308] After the compliment is given, the device continuously monitors and records the user's new performance data, including new project progress and deliverables, and periodically transmits this data to the server.

[1309] 7. Learning Phase

[1310] The server analyzes new performance data sent from the device and evaluates the effectiveness of the compliments. It evaluates how a particular compliment affected the user's performance and updates the compliment generation algorithm based on the results. This process uses machine learning algorithms (e.g., scikit-learn and TensorFlow).

[1311] In this way, by linking generative AI with an emotion engine, the system can provide more personalized compliments to users, improving their performance and motivation.

[1312] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1313] Step 1:

[1314] Data Collection Phase

[1315] The server requests past data from the user's device, specifically by sending an HTTP GET request for data such as project completion reports, final evaluations, and feedback.

[1316] In response to the request, the device retrieves the data from its local storage and sends it to the server as an HTTP response. For example, the server may send a request such as "Please send project completion report data," and the device may provide past data in response.

[1317] Input: Data request from server

[1318] Output: Data response (project completion report, final evaluation, feedback)

[1319] Step 2:

[1320] Data analysis phase

[1321] The server then analyzes the data it receives, using natural language processing techniques like Python's NLTK library and Spacy to identify individual strengths and efforts, such as extracting keywords like "leadership" and "creative problem solving" from project reports.

[1322] Input: User's past data (project completion report, final evaluation, feedback)

[1323] Output: Identified strengths and efforts (e.g., "Leadership," "Creative Problem Solving")

[1324] Step 3:

[1325] Emotion Recognition Phase

[1326] The server recognizes the user's emotions using an emotion engine (e.g., Microsoft Azure Emotion API or Amazon Rekognition).

[1327] It analyzes the tone and speed of voice calls and identifies emotions from the user's voice and facial expressions. For example, it uses Google Cloud Speech-to-Text to convert voice data into text and recognizes emotions based on that text.

[1328] Input: User voice and facial expression data

[1329] Output: User's emotional state (e.g., "stressed," "relaxed")

[1330] Step 4:

[1331] Compliment generation phase

[1332] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate the optimal compliment based on the analyzed individual's strengths, effort, and perceived emotions.

[1333] A prompt is fed into the generative AI model, which tailors its response to the user's situation, such as "Please praise the user for their leadership and creative problem-solving skills."

[1334] Input: personal strengths and efforts, user emotional state, prompt text

[1335] Output: Personalized compliment

[1336] Step 5:

[1337] Offering compliments

[1338] The generated compliment is sent from the server to the user's terminal.

[1339] The device will display the compliment as a pop-up notification or as part of the dashboard, such as, "Your leadership and creative problem-solving skills have helped the entire team. Your calmness in difficult situations, especially on this project, has been impressive. Please rest well and move on to the next step."

[1340] Input: Generated compliment

[1341] Output: User notification

[1342] Step 6:

[1343] Feedback gathering phase

[1344] After the compliment is given, the device continuously monitors and records the user's new performance data, including new project progress and deliverables, and periodically transmits this data to the server.

[1345] Input: User's new performance data

[1346] Output: Send data to the server

[1347] Step 7:

[1348] Learning Phase

[1349] The server analyzes new performance data sent from the device and evaluates the effectiveness of the compliments, assessing how a particular compliment affected the user's performance and updating the compliment-generation algorithm based on the results.

[1350] This process uses machine learning algorithms (e.g., scikit-learn and TensorFlow).

[1351] Input: New performance data, effectiveness evaluation results

[1352] Output: The updated compliment generation algorithm

[1353] (Application example 2)

[1354] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1355] Conventional performance improvement systems provide uniform feedback without considering the individual's emotional state, which limits their effectiveness in improving motivation and performance. Furthermore, the content of the feedback is not optimized for the individual's characteristics and circumstances, reducing the feedback's acceptability and effectiveness. Furthermore, providing feedback in real time is difficult and often lacks timeliness. Therefore, there is a need for a system that can recognize each individual's emotional state in real time and provide optimized praise.

[1356] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting past data of an individual, means for analyzing the collected data to identify the individual's strengths and efforts, means for generating personalized compliments based on the identified strengths and efforts, means for presenting the generated compliments to the individual, means for collecting performance data of the individual after the compliments have been presented, means for analyzing the collected performance data to evaluate the effectiveness of the compliments and updating the compliment generation algorithm, means for recognizing the individual's emotional state via an external device that collects audio and video data, means for adjusting the compliments based on the recognized emotional state, and means for displaying the adjusted compliments on the external device. This allows personalized compliments optimized for the individual's emotional state to be provided in real time, thereby improving motivation and performance.

[1357] "Personal past data" refers to information about an individual's past performance and behavior, such as project completion reports, end-of-period evaluations, and feedback.

[1358] "Means of collection" refers to the means by which an individual's historical data is collected in a particular manner, such as by local scanning or retrieval from a remote server.

[1359] "Means of analysis" refers to technologies for analyzing collected data and extracting meaningful information, including natural language processing technology and data mining technology.

[1360] "Means for identifying individual strengths and efforts" refers to technologies that identify individual talents and struggles from analyzed data, including specialized algorithms and machine learning models.

[1361] "Means for generating personalized compliments" refers to technology for creating personalized compliments based on identified strengths and efforts.

[1362] "Means for presenting the generated compliment to the individual" refers to technology that notifies or displays the generated compliment to the user, and includes, for example, devices such as smart glasses or a smartphone.

[1363] "Performance data" is data about an individual's achievements and behavior obtained after the presentation of praise.

[1364] "Means for evaluating the effectiveness of compliments and updating the compliment generation algorithm" refers to technology that measures the impact of presented compliments on an individual's performance and, based on the results, improves the algorithm that generates future compliments.

[1365] "External device for collecting audio and video data" refers to a device for capturing personal audio and video, including smart glasses and head-mounted displays.

[1366] "Means for recognizing an individual's emotional state" refers to technology that analyzes collected audio and video data to identify an individual's emotions (e.g., joy, sadness, stress, etc.).

[1367] "Methods for tailoring compliments based on perceived emotional state" refers to techniques for altering the content and tone of compliments to match identified emotional states.

[1368] "Means for displaying the tailored compliment on an external device" refers to display technology for providing the tailored compliment to the user in a viewable manner, including smart glasses or other display devices.

[1369] As an embodiment of the present invention, a factory worker support system using smart glasses will be taken as an example. This system operates in cooperation with three entities: a server, smart glasses (terminals), and a user.

[1370] First, the smart glasses collect the worker's voice and video data and transmit it to a server in real time. The smart glasses are equipped with a camera and microphone, which are used to record daily work.

[1371] The server utilizes several technologies to execute the following series of processes: First, the server analyzes the audio and video data received from the smart glasses and recognizes the user's emotional state using an emotion engine (e.g., Microsoft Azure Cognitive Services' Emotion API or Face API). The server analyzes tone, speed, volume, etc. from the audio data, and facial expressions from the video data.

[1372] Next, the server collects the user's past data (e.g., project completion reports, final evaluations, feedback, etc.) and analyzes it using natural language processing techniques (e.g., Google Cloud Natural Language API and Hugging Face transformers) to identify the user's strengths and efforts.

[1373] Based on the identified strengths and efforts, as well as the perceived emotional state, the server uses a generative AI model (e.g., OpenAI's GPT-4) to generate a personalized compliment using prompts such as:

[1374] Example prompt sentence:

[1375] Username: Yamada Taro

[1376] Project: Launching a new product line

[1377] Rating: Very High Leadership

[1378] Emotional state: Stressed

[1379] Generate a suitable compliment

[1380] The generated compliments are sent to the smart glasses and displayed to the user in real time, for example as a pop-up notification on the smart glasses display.

[1381] After the user receives a compliment, new performance data collected from the smart glasses continues to be sent to the server, which analyzes the data and evaluates the effect of the compliment on the user's performance. Based on the evaluation results, the compliment generation algorithm is updated accordingly.

[1382] This allows the system to provide users with personalized praise that is optimized for their emotional state, thereby increasing motivation and improving performance.

[1383] As a concrete example, if a user demonstrates exceptional leadership in the launch of a new product line and analysis using the emotion engine reveals that they are feeling stressed, the following praise could be offered: "Your leadership and creative problem-solving skills have helped the entire team. It's particularly impressive that you were able to remain calm in difficult situations in this project. Take a good rest and move on to the next step!" In this way, appropriate feedback can be provided to users in real time, improving their performance and motivation.

[1384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1385] Step 1:

[1386] Smart glasses (terminals) collect the voice and video data of workers. The smart glasses are equipped with a camera and microphone to capture video and audio data of daily work. This data is sent to a server in real time.

[1387] Input: Video and audio data of worker

[1388] Output: Video and audio data transmitted in real time

[1389] Step 2:

[1390] The server analyzes the received audio and video data and uses an emotion engine to recognize the user's emotional state. Specifically, it uses the Emotion API and Face API of Microsoft Azure Cognitive Services to analyze tone, speed, and volume from audio data and facial expressions from video data.

[1391] Input: Video and audio data

[1392] Data processing / data calculation: Emotion analysis of audio and video

[1393] Output: User's emotional state (e.g., stress, joy)

[1394] Step 3:

[1395] The server collects users' past data (project completion reports, final evaluations, feedback, etc.) and analyzes it using natural language processing technology. It uses Google Cloud Natural Language API and Hugging Face transformers to identify individual strengths and efforts.

[1396] Input: Historical data

[1397] Data processing / data calculation: Analysis using natural language processing

[1398] Output: User strengths and efforts (e.g., leadership, creative problem-solving)

[1399] Step 4:

[1400] The server uses a generative AI model to generate personalized compliments based on the perceived emotional state and identified strengths and efforts, using OpenAI's GPT-4 to create prompts and generate results.

[1401] Input: User strengths, effort, and emotional state

[1402] Data processing / data calculation: Generating compliments using generative AI models

[1403] Output: Personalized compliment

[1404] Step 5:

[1405] The server sends the generated compliment to the smart glasses and presents it to the user in real time, as a pop-up notification on the smart glasses' display.

[1406] Input: Generated compliment

[1407] Output: Compliments displayed on the smart glasses display

[1408] Step 6:

[1409] After the user receives the compliment, the smart glasses collect new performance data and send it to the server, such as project progress and deliverables.

[1410] Input: User's new performance data

[1411] Output: New performance data sent to the server

[1412] Step 7:

[1413] The server analyzes the new performance data, evaluates the effectiveness of the compliments, and updates the compliment generation algorithm based on the evaluation results.

[1414] Input: New performance data

[1415] Data processing / data calculation: analysis of performance data and evaluation of effects

[1416] Output: Updated compliment generation algorithm

[1417] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1418] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1419] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1420] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1421] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1422] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1423] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1424] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1425] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1426] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1427] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1428] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1429] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1430] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1431] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1432] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1433] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1434] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1435] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1436] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1437] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1438] The following is further disclosed regarding the above embodiment.

[1439] (Claim 1)

[1440] a means of collecting historical data about individuals;

[1441] a means of analyzing the collected data to identify individual strengths and efforts;

[1442] A means of generating personalized praise based on identified strengths and efforts;

[1443] a means for presenting the generated compliment to the individual;

[1444] a means of collecting individual performance data following the presentation of the praise;

[1445] a means for analyzing the collected performance data to evaluate the effectiveness of the compliments and update the compliment generation algorithm;

[1446] A system including:

[1447] (Claim 2)

[1448] 10. The system of claim 1, wherein the individual's historical data includes project completion reports, end-of-period evaluations, and feedback.

[1449] (Claim 3)

[1450] 2. The system of claim 1, wherein the means for identifying an individual's strengths and efforts uses natural language processing technology.

[1451] "Example 1"

[1452] (Claim 1)

[1453] a means of collecting historical data about individuals;

[1454] a means of analyzing the collected data to identify individual strengths and efforts;

[1455] A means of generating personalized praise based on identified strengths and efforts;

[1456] a means for presenting the generated compliment to the individual;

[1457] a means of collecting individual performance data following the presentation of the praise;

[1458] a means for analyzing the collected performance data to evaluate the effectiveness of the compliments and update the compliment generation algorithm;

[1459] means including a set of programs for performing a plurality of data processing phases;

[1460] means for using a communication protocol necessary for sending and receiving data;

[1461] A means for generating compliments that correspond to specific strengths or efforts using generative AI technology; and

[1462] a means for inputting a prompt sentence into a generative AI model;

[1463] A system including:

[1464] (Claim 2)

[1465] 10. The system of claim 1, wherein the individual's past data includes performance reports, evaluation results, and feedback comments.

[1466] (Claim 3)

[1467] 2. The system of claim 1, wherein the means for identifying an individual's strengths and efforts uses natural language processing technology.

[1468] "Application Example 1"

[1469] (Claim 1)

[1470] a means of collecting historical data about individuals;

[1471] a means of analyzing the collected data to identify individual strengths and efforts;

[1472] A means of generating personalized praise based on identified strengths and efforts;

[1473] a means for presenting the generated compliment to the individual;

[1474] a means of collecting individual performance data following the presentation of the praise;

[1475] a means for analyzing the collected performance data to evaluate the effectiveness of the compliments and update the compliment generation algorithm;

[1476] means for generating personalized compliments in a content delivery service to enhance a user's viewing experience based on viewing data;

[1477] A system including:

[1478] (Claim 2)

[1479] 10. The system of claim 1, wherein the individual's historical data includes project completion reports, end-of-term evaluations, feedback, and viewing history.

[1480] (Claim 3)

[1481] 2. The system of claim 1, wherein the means for identifying individual strengths and efforts uses natural language processing techniques and generative AI models.

[1482] "Example 2: Combining Emotion Engines"

[1483] (Claim 1)

[1484] a means of collecting historical data about individuals;

[1485] a means of analyzing the collected data to identify individual strengths and efforts;

[1486] A means of generating personalized praise based on identified strengths and efforts;

[1487] a means for presenting the generated compliment to the individual;

[1488] a means of collecting individual performance data following the presentation of the praise;

[1489] a means for analyzing the collected performance data to evaluate the effectiveness of the compliments and update the compliment generation algorithm;

[1490] means for recognizing a user's emotion;

[1491] A means for adjusting the compliment based on the emotion recognition results;

[1492] A system including:

[1493] (Claim 2)

[1494] 10. The system of claim 1, wherein the individual's historical data includes project completion reports, end-of-period evaluations, and feedback.

[1495] (Claim 3)

[1496] 2. The system of claim 1, wherein the means for identifying an individual's strengths and efforts uses natural language processing technology.

[1497] "Application example 2 when combining emotion engines"

[1498] (Claim 1)

[1499] a means of collecting historical data about individuals;

[1500] a means of analyzing the collected data to identify individual strengths and efforts;

[1501] A means of generating personalized praise based on identified strengths and efforts;

[1502] a means for presenting the generated compliment to the individual;

[1503] a means of collecting individual performance data following the presentation of the praise;

[1504] a means for analyzing the collected performance data to evaluate the effectiveness of the compliments and update the compliment generation algorithm;

[1505] means for recognizing the emotional state of an individual via an external device that collects audio and video data;

[1506] a means for adjusting compliments based on the perceived emotional state;

[1507] means for displaying the adjusted compliment on an external device;

[1508] A system including:

[1509] (Claim 2)

[1510] 10. The system of claim 1, wherein the individual's historical data includes project completion reports, end-of-period evaluations, and feedback.

[1511] (Claim 3)

[1512] 2. The system of claim 1, wherein the means for identifying an individual's strengths and efforts uses natural language processing technology. [Explanation of symbols]

[1513] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting historical data about individuals; a means of analyzing the collected data to identify individual strengths and efforts; A means of generating personalized praise based on identified strengths and efforts; a means for presenting the generated compliment to the individual; a means of collecting individual performance data following the presentation of the praise; a means for analyzing the collected performance data to evaluate the effectiveness of the compliments and update the compliment generation algorithm; A system including:

2. 10. The system of claim 1, wherein the individual's historical data includes project completion reports, end-of-year evaluations, and feedback.

3. 10. The system of claim 1, wherein the means for identifying individual strengths and efforts utilizes natural language processing techniques.

Images