system

Abstract

We provide the system. [Solution] An information processing device provides a means for anonymizing and collecting data related to the work of individual workers, A method for analyzing collected anonymized data and evaluating the contribution of workers using natural language processing technology, A means of automatically generating feedback reports based on evaluation results and providing them anonymously to workers, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Solve the problem that among workers, due to poor communication skills and difficulty in self-promotion, their actual contributions may not be correctly evaluated and they may be forced into an unfair career path. Such problems often lead to the failure to properly recognize individual contributions, resulting in a decline in work motivation and feelings of inequality. Therefore, there is a need to provide a system for fairly evaluating workers' performance without relying on communication skills.

Means for Solving the Problems

[0005] This invention provides a means for collecting anonymized data related to workers' work using an information processing device. This anonymized data is analyzed using natural language processing technology to comprehensively evaluate the worker's contribution. Based on this evaluation, the system has a function to anonymously provide the worker with an automatically generated feedback report. Furthermore, this system provides an interface for workers to receive advice in an interactive format based on the feedback report, thereby enabling a fair evaluation of individual contributions and appropriate recognition of actual results.

[0006] "Information processing equipment" is a term that refers to all electronic devices used for collecting, processing, analyzing, and outputting data.

[0007] "Worker" refers to an individual employed by an organization or project to perform specific tasks or duties.

[0008] "Anonymization" is a technology that refers to the process of removing or transforming information that could identify a specific individual, so that the individual cannot be identified.

[0009] "Data" refers to information such as numbers and characters, or collections thereof, that are processed in a computer system.

[0010] "Natural language processing technology" refers to artificial intelligence technology that enables computers to understand, interpret, and generate human language.

[0011] "Contribution" is a measure that indicates the degree of influence or contribution an individual or team has to a particular goal or project.

[0012] "Evaluation" refers to the process of quantifying or qualitatively judging the quality and results of workers and their work based on specific criteria.

[0013] A "feedback report" is a document created based on evaluation results, which includes an evaluation of specific tasks and suggestions for improvement.

[0014] The "dialogue format" refers to the process of obtaining or transmitting information using an interactive method in which the user communicates with the system mutually.

[0015] An "interface" refers to a screen or its function that enables the exchange of information between the system and the user.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the language used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the 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.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0030] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] The present invention is an anonymous evaluation system for fairly and objectively evaluating the performance of workers, and a specific embodiment thereof is shown below. This system uses an information processing device to collect various data related to the work of workers in an anonymized form and uses that data to perform evaluations.

[0038] Data collection and anonymization

[0039] The server automatically collects data related to workers' work. This includes the progress of tasks assigned to workers, deadline compliance rates, and review results of documents related to tasks. The collected data is anonymized so that individuals cannot be identified. This anonymization process creates a dataset in which individual workers cannot be identified.

[0040] Data analysis and evaluation

[0041] The server analyzes anonymized data using natural language processing techniques. This analysis evaluates indicators such as task completion, cooperation, and interaction among workers. Using a Large-Scale Language Model (LLM) enables a more detailed and multifaceted assessment of contributions. The evaluation results are output as a numerical contribution score.

[0042] Feedback generation and provision

[0043] The server automatically generates feedback reports for workers based on the evaluation results. These reports include the evaluated contribution score, strengths and areas for improvement, and specific advice. The generated feedback reports are sent anonymously to each worker.

[0044] Providing interactive advice

[0045] The terminal provides an interactive interface to obtain additional information and specific improvement measures based on feedback received from workers. Users can use this interface to resolve questions and receive advice on the next steps.

[0046] Specific example: Worker A's tasks for Project X include completing tasks on time and conducting detailed document reviews. After the server anonymizes and collects this work data, it analyzes it using natural language processing. As a result, worker A receives feedback stating, "You meet deadlines, but more effective collaboration is expected." Through the terminal, worker A can receive specific advice on how to improve their collaboration skills.

[0047] In this way, the entire system fairly evaluates workers' performance and contributes to creating a better working environment.

[0048] The following describes the processing flow.

[0049] Step 1:

[0050] The server collects data on task information, work progress, and deliverable quality from business applications and project management tools used by workers. This data includes information such as project name, assigned tasks, start date, and end date. Data collection is performed automatically using APIs and log analysis.

[0051] Step 2:

[0052] The server anonymizes the collected data, making it impossible to identify specific individuals. Specifically, it removes personal names and specific identifying information, or replaces them with alternative identifiers. This ensures that data is managed securely while protecting privacy.

[0053] Step 3:

[0054] The server uses an anonymized data as input and performs natural language processing using a Large-Scale Language Model (LLM). During this process, various indicators are extracted and analyzed, including task completion, communication between workers, and contribution to the work. As a result of the analysis, an evaluation score is generated for each individual worker.

[0055] Step 4:

[0056] The server automatically generates a feedback report based on the evaluation score. This report includes a specific assessment of performance, strengths, areas for improvement, and future action plans. The report is designed to be provided anonymously to workers.

[0057] Step 5:

[0058] The terminal anonymously distributes the generated feedback report to each worker. By viewing this report, workers can objectively understand how their performance is being evaluated.

[0059] Step 6:

[0060] Based on feedback reports, users can use an interactive advice system to resolve questions and receive additional guidance. Specifically, they input advice via their device and receive suggestions for improvement and skill development automatically generated by AI. This interactive process allows users to grasp concrete directions for improving their work.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] Ensuring fairness and objectivity in employee performance evaluations is difficult. Furthermore, traditional evaluation systems fail to adequately reflect the individual characteristics and contributions of employees, resulting in ineffective use of feedback. Additionally, there are insufficient mechanisms to effectively link evaluation results to employee growth.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes a device for anonymizing and collecting information related to the activities of multiple workers; means for analyzing the collected anonymized information and evaluating the workers' contributions using natural language processing technology; means for quantifying contribution scores based on the evaluation results, automatically generating feedback documents, and providing them anonymously to the workers; and means for inputting prompt sentences into a generating AI model to perform detailed analysis. This enables fair and detailed performance evaluation and makes it possible to provide feedback that promotes worker growth.

[0066] "Anonymization" is the process of hashing or encoding personal names or IDs so that individual workers cannot be identified.

[0067] "Collection" is the process of automatically gathering information related to the activities of workers.

[0068] "Natural language processing technology" is a technology that mechanically understands, interprets, and generates human language, and is used to evaluate the contribution of workers.

[0069] A "contribution score" is an evaluation index that quantifies the activities and results of workers.

[0070] A "feedback document" is a report provided anonymously to the worker, including their contribution score, evaluation criteria, and suggestions for improvement.

[0071] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs natural language analysis and generation based on prompt sentences.

[0072] A "prompt statement" is a sentence containing specific questions or commands that are input to an AI model to perform analysis or generation.

[0073] A "user interface" refers to an interactive screen or input device used by workers to receive advice on feedback documents.

[0074] This invention is an evaluation system for fairly and objectively evaluating the work activities of multiple workers. The following describes embodiments for carrying out this invention.

[0075] Data collection and anonymization

[0076] The server automatically collects information such as workers' task progress, deadline compliance rates, and review results for related documents. Project management tools and document management systems are used for this collection. To anonymize the collected information, the server hashes individual worker information, converting it into an unidentifiable format. This creates a secure and anonymized dataset.

[0077] Data analysis and evaluation

[0078] The server analyzes anonymized data using a generative AI model. Specifically, by passing the prompt "Evaluate the task completion and collaboration levels in Project X" to the AI ​​model, it performs a detailed and multifaceted evaluation using natural language processing techniques. As a result, scores for the workers' task completion and collaboration levels are calculated.

[0079] Generating and providing feedback

[0080] The server automatically generates a feedback document based on the analysis results. This document includes the worker's contribution score, specific evaluation criteria, and improvement suggestions. The generated document is sent anonymously to the worker's terminal.

[0081] Use of interactive interfaces

[0082] The terminal provides workers with an interactive interface that allows them to request further advice based on feedback documents. Through this interface, users can input questions such as, "How can I improve teamwork?" and receive specific advice.

[0083] This system allows for a deeper understanding of employee performance evaluations and enables the provision of effective feedback and support.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The server collects data related to the workers' tasks. Specifically, it obtains task progress information, deadline compliance rates, and review results from project management tools and document management systems as input. To anonymize this information, it hashes the individual worker identifier and outputs it. This output is an anonymized dataset in which individual workers cannot be identified.

[0087] Step 2:

[0088] The server then moves on to the process of analyzing the anonymized data. The anonymized data is sent to a large-scale language model using the prompt "Evaluate the task completion and collaboration levels in Project X." This data processing utilizes natural language processing techniques to produce a multifaceted evaluation of the workers' contributions and collaborative relationships. This output consists of specific numerical values ​​such as task completion and collaboration scores.

[0089] Step 3:

[0090] The server generates a feedback document based on the analysis results. Using the analysis results as input, it automatically creates feedback including contribution scores, evaluation criteria, and improvement suggestions. This output is an anonymous feedback document provided to the worker. The generated document is sent to the worker's terminal.

[0091] Step 4:

[0092] The terminal receives feedback documents and provides the worker with an interactive interface. Through this interface, the user performs specific actions to request additional advice based on the feedback. It receives questions such as "How can I improve teamwork?" as input and outputs responses from a generative AI model. This output allows the user to obtain specific improvement suggestions and advice.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] Traditional performance evaluation systems struggle to fairly and quickly assess the contributions of individual workers. Furthermore, there are limited means to immediately utilize evaluation results in the real world, hindering efficient improvement.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes a medium for collecting anonymized work-related data generated in the work environment, a medium for analyzing data collected during work via smart devices and evaluating the worker's contribution using natural language processing technology, and a medium for displaying the evaluation results in real time and providing feedback to the worker using augmented reality technology. This makes it possible to fairly and quickly evaluate the performance of workers and use the results to improve work in real time.

[0098] An "information processing system" is a set of electronic devices and software used to process business-related data.

[0099] "Anonymization" is a process that protects privacy by processing data so that individual workers cannot be identified.

[0100] A "smart device" is an electronic device with advanced information processing capabilities, including wearable technology.

[0101] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0102] "Contribution" is a measure that expresses the specific results and impact that an employee has had on their work using numerical values ​​and evaluations.

[0103] Augmented reality technology is a technology that displays digital information overlaid on the physical environment in the real world.

[0104] "Real-time" refers to a time frame in which events occur and are processed almost simultaneously.

[0105] "Feedback" refers to information about areas for improvement and advice provided to employees based on their evaluation results.

[0106] The system implementing this invention primarily utilizes a server, smart devices, and augmented reality (AR) technology. The server collects data generated in the work environment in an anonymized form. Specifically, OCR technology and an AI camera are used to transmit workers' actions and conversations as text data to the server. The server uses Google® Cloud Data Loss Prevention to remove personally identifiable information and achieve anonymization.

[0107] Next, the server uses OpenAI's GPT to perform natural language processing and analyze the data. This analysis evaluates the workers' contributions and generates output in the form of numerical data and feedback. The evaluation results are output as text that extracts specific contribution points and areas for improvement.

[0108] Smart devices, primarily smart glasses, are used to display evaluation results to workers in real time via augmented reality technology. Workers can then use the feedback displayed on the glasses to immediately improve their work.

[0109] For example, in the case of staff handling customer service at a virtual store, their customer service performance is evaluated in real time, and they can instantly view feedback on their glasses indicating that "improvements in the efficiency of customer service time can be expected." This system enables the formation of a smooth business improvement cycle, leading to improved performance.

[0110] The following are examples of prompt messages to use when inputting data into a generative AI model.

[0111] The following is employee work data. Based on this, please generate anonymized evaluations and feedback for performance improvement.

[0112] Business data: Task progress, customer interaction logs, work summary...

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The server acquires data generated by workers during their work from smart devices. As input, task progress and voice data are sent as text information via OCR technology and AI cameras. The server receives this information and outputs it as a dataset.

[0116] Step 2:

[0117] The server anonymizes the acquired dataset. Using the dataset obtained in Step 1 as input, it removes personal information using Google Cloud Data Loss Prevention. It outputs an anonymized dataset, ensuring that individual workers cannot be identified.

[0118] Step 3:

[0119] The server applies natural language processing techniques to analyze the anonymized dataset. The data from Step 2 is passed to OpenAI's GPT as input, where task completion and interaction levels are evaluated. A contribution score and feedback basis are output from the analyzed data.

[0120] Step 4:

[0121] The server generates a feedback report based on the analysis results. Using the contribution score and analysis data obtained in step 3 as input, it creates a text containing evaluation points and improvement suggestions. The server then outputs the automatically generated feedback report.

[0122] Step 5:

[0123] The device (smart glasses) displays the feedback report sent from the server to the user. It receives the feedback generated in step 4 as input and displays the evaluation results and improvement advice on the glasses' display in real time. This allows the user to immediately review the outputted feedback and utilize it in their work.

[0124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0125] This invention combines an emotion engine with a system that collects anonymized data related to workers' work, analyzes that data to evaluate their contribution, and provides a mechanism to deliver more personalized feedback.

[0126] Data collection and anonymization

[0127] The server automatically collects workers' work information. This data is automatically extracted from work progress, results, and tools used. After collection, it undergoes an anonymization process to ensure that individuals cannot be identified.

[0128] Data analysis and evaluation

[0129] The server analyzes anonymized data using natural language processing techniques to evaluate the workers' contributions. By utilizing large-scale language models (LLMs), the evaluation can be multifaceted, including indicators such as the workers' task completion rate, level of cooperation, and creative contribution.

[0130] Feedback generation and provision

[0131] The server automatically generates a feedback report based on the evaluation results. The feedback includes a quantitative assessment of contribution, areas for improvement, and specific action plans. The evaluation results are provided anonymously to each worker.

[0132] Emotional evaluation by an emotional engine

[0133] The terminal collects emotional data in real time from the worker's responses to the feedback they receive. The server analyzes this data using an emotion engine to measure the worker's stress, motivation, and enthusiasm.

[0134] Personalized feedback provided

[0135] The server adjusts the content of the feedback based on the results of the emotion engine. In particular, when the worker is experiencing anxiety or stress, it can add positive supplementary feedback or content that encourages counseling.

[0136] Interactive Advice and Emotional Interface

[0137] Users can view feedback and ask questions through an emotion-based interactive interface. The emotion interface provides appropriate advice and information for self-improvement based on the user's emotional state.

[0138] Specific example: When worker B receives a feedback report, the emotion engine detects a stress response. In this case, the server adjusts the feedback and adds the message, "We will provide increased support next time." Through the terminal, worker B receives an option to access counseling services and can receive support tailored to their emotional state.

[0139] In this way, a feedback system that takes workers' feelings into account helps to create a better work environment.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] The server automatically collects task information, progress data, and performance data from the work applications and project management tools used by workers. This includes task start and end dates, completion status, and log data of the tools used.

[0143] Step 2:

[0144] The server anonymizes the collected data. This process removes personally identifiable information and assigns alternative identifiers to identify individual workers, ensuring data security while protecting privacy.

[0145] Step 3:

[0146] The server analyzes the anonymized data using natural language processing techniques. Here, a large-scale language model (LLM) is used to extract indicators that evaluate each worker's task completion, cooperation, and contribution, and calculate a contribution score.

[0147] Step 4:

[0148] The server automatically generates feedback reports based on contribution scores. These reports include the worker's strengths and areas for improvement, as well as specific action plans, all based on their score. The feedback is provided anonymously, with measures taken to prevent the recipient from being identified.

[0149] Step 5:

[0150] The terminal anonymously distributes the generated feedback reports to each worker. It also provides an interface for recording their reactions to the reports in real time.

[0151] Step 6:

[0152] The user reviews the feedback report on their device. The user's emotional responses (e.g., facial expressions, speech) are recorded as emotional data by the emotion engine. The emotion engine automatically categorizes the user's emotional state into states such as stress, relief, and motivation.

[0153] Step 7:

[0154] The server receives the analysis results from the emotion engine and adjusts the feedback content according to the emotional state. For example, if the user is feeling stressed, it adds emotional support by supplementing the feedback with advice on how to relax and words of encouragement.

[0155] Step 8:

[0156] The terminal then presents the adjusted feedback to the user. Furthermore, the user can ask additional questions about the feedback through interactive advice, and the system provides appropriate guidance. This allows the user to deepen their understanding of how to improve their work based on the feedback and suggestions.

[0157] (Example 2)

[0158] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0159] Traditional employee evaluation systems tend to focus heavily on the quantitative assessment of employees' work performance, relying solely on numerical evaluations and failing to provide feedback that considers employees' emotional states or stress levels. Furthermore, the lack of personalized feedback makes it insufficient for improving employee motivation. This results in monotonous feedback for employees, making it difficult to provide concrete pathways for improvement.

[0160] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0161] In this invention, the server includes means for anonymizing and collecting information related to the work of individual workers; means for analyzing the collected anonymized information and evaluating the worker's contribution using natural language processing technology; means for automatically generating a report based on the evaluation results and providing it anonymously to the worker; means for collecting emotional data from the worker's feedback responses via a terminal; means for analyzing the collected emotional data and evaluating the worker's emotional state; and means for adjusting the content of the feedback based on the emotional state. As a result, the feedback received by the worker will take their emotional state into consideration, and it will be possible to provide specific and constructive action plans tailored to individual circumstances.

[0162] An "information processing device" is a computer system used for collecting, analyzing, storing, and outputting data.

[0163] "Anonymization" is a technology used to protect privacy by removing or transforming information that could identify an individual.

[0164] "Natural language processing technology" is a technology that uses computers to analyze and understand the language that humans use.

[0165] "Contribution level" is an indicator used to evaluate the degree of results and cooperation that workers demonstrate in their work.

[0166] A "report" is a document created based on the analysis results, containing information including evaluation details and areas for improvement.

[0167] A "terminal" is a device used by a user to input and output information.

[0168] "Emotional data" refers to information that indicates the user's emotions and sensory state, and is collected through feedback and conversations.

[0169] "Feedback" refers to information used to communicate evaluations, suggestions, and improvement measures regarding an employee's work.

[0170] An embodiment of the present invention is a feedback system that combines worker performance evaluation with emotional data analysis. This system consists of an information processing device that provides personalized feedback to each worker.

[0171] First, the server automatically collects information related to the worker's work. Specifically, it utilizes a high-speed database system to extract data from sources such as email, project management tools, and work time records. The information is anonymized, thus protecting individual privacy. This anonymization process uses hash functions such as SHA-256.

[0172] Next, the server analyzes the data using natural language processing techniques to evaluate the workers' contributions. Large-scale language models such as BERT and GPT are employed for the analysis. This allows for a multifaceted evaluation of task completion, collaboration, and creative contribution.

[0173] Subsequently, a report is automatically generated based on the evaluation results. The report includes quantitative evaluations, specific improvement suggestions, and a next action plan. The report is provided to the user anonymously.

[0174] The terminal collects the worker's response to the report in real time and sends it to the server as sentiment data. This sentiment data is analyzed by an emotion engine and used to evaluate the worker's stress and motivation levels.

[0175] Ultimately, the server adjusts the feedback based on the evaluation of emotional data, providing situation-appropriate advice and support. This enables personalized feedback that takes into account the worker's emotional state.

[0176] For example, if a worker receives feedback and a stress response is detected, the server adjusts the feedback to include a message such as, "We will provide increased support next time." It also offers counseling service options via the terminal, providing support tailored to the worker's emotional state.

[0177] An example of a prompt message for a generative AI model is, "Based on worker evaluation data, please generate feedback content that takes into account individual emotional states."

[0178] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0179] Step 1:

[0180] The server collects workers' work information. Inputs include email content, project management tool records, and work time data. This information is sent to the server sequentially and anonymized. Specifically, personally identifiable data is removed from the information, and it is anonymized using the SHA-256 hash function. The anonymized work information is then stored in a database as output.

[0181] Step 2:

[0182] The server analyzes anonymized work information using natural language processing technology. The input is the anonymized information obtained in step 1. The server inputs this information into a generative AI model (e.g., BERT, GPT) and outputs it as an evaluation index that quantifies the worker's task completion level, cooperation level, and creative contribution level. Specifically, it analyzes the text data for each task and expresses the results and level of cooperation numerically.

[0183] Step 3:

[0184] The server automatically generates a report based on the evaluation results. The evaluation metrics from Step 2 are used as input. Based on this information, the server generates a report that includes contributions, areas for improvement, and action plans. For example, the report is output as a PDF file and provided anonymously to the worker.

[0185] Step 4:

[0186] The terminal collects the worker's reaction to receiving the report. The input is the user's emotional feedback. The terminal uses a camera, microphone, and input devices to observe the worker's facial expressions, tone of voice, and typing speed in real time, and outputs this as emotional data. This also includes eye gaze and facial expression analysis while the worker is reading the report.

[0187] Step 5:

[0188] The server analyzes the collected emotional data using an emotion engine. It uses the emotional data from step 4 as input. The server evaluates the worker's stress level and motivation and outputs the results. Specifically, it uses an API to perform emotion analysis, and if particularly strong stress or anxiety is detected, it generates supplementary feedback regarding that situation.

[0189] Step 6:

[0190] The server adjusts the feedback based on the sentiment analysis results. The sentiment evaluation results from Step 5 are the input. The server rewrites the feedback, including positive messages and steps for improvement, according to the worker's current emotions. As output, the updated report is provided to the worker again.

[0191] Step 7:

[0192] Users can use the interactive interface provided on their device to review feedback and ask questions. Appropriate advice is output in response to the user's feedback and questions. Specifically, advice and information are provided that takes into account the user's emotional state, supporting workers in deciding on their next course of action.

[0193] (Application Example 2)

[0194] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0195] In the work environment for employees, it is crucial to appropriately evaluate individual contributions to work and provide effective feedback. Traditional evaluation systems struggle to provide personalized feedback that takes into account employees' emotional states. This can lead to decreased employee motivation and excessive stress, negatively impacting company productivity. Therefore, to create a better work environment, a system is needed that evaluates work contributions while providing feedback tailored to individual emotional states.

[0196] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0197] In this invention, the server includes means for anonymizing and collecting data related to the work of individual workers; means for analyzing the collected anonymized data and evaluating the worker's contribution using natural language processing technology; means for automatically generating a feedback report based on the evaluation results and providing it anonymously to the worker; means for monitoring the worker's emotional response to the feedback in real time, analyzing it with an emotion engine, and providing personalized feedback; and means for creating and presenting support and improvement suggestions based on emotions. This makes it possible to provide feedback that takes into account the worker's emotional state, thereby supporting improvements in the work environment and increased productivity.

[0198] An "information processing device" is a device that includes hardware and software for collecting, analyzing, and evaluating data.

[0199] "Data related to the work of individual workers" refers to data related to the progress, results, and tools and equipment used by the workers in their tasks.

[0200] "Anonymization" is the process of removing personally identifiable information from collected data in order to protect individual privacy.

[0201] "Natural language processing technology" is a technology that enables computers to understand and process human language, and is used for the analysis and evaluation of text data.

[0202] "Evaluating contribution" means quantifying the extent to which an employee contributes to the work based on a variety of indicators.

[0203] A "feedback report" is a report created based on the evaluation results and provided to the worker.

[0204] The "emotional engine" is a system that analyzes workers' emotional responses and numerically evaluates their emotional state.

[0205] "Personalized feedback" refers to feedback that is customized according to the worker's emotional state and individual circumstances.

[0206] "Emotion-based support" refers to providing appropriate advice and support based on the emotional state of the worker.

[0207] The system for implementing this invention is configured around an information processing device. This system collects anonymized data related to the worker's tasks and evaluates their contribution using natural language processing technology. It then generates a feedback report based on the evaluation results and provides it to the worker anonymously. After providing the feedback, the terminal acquires the worker's emotional response in real time, and the server analyzes this data using an emotion engine, enabling the provision of personalized feedback.

[0208] The server utilizes high-performance computers and employs statistical analysis software and sensor data aggregation systems for collecting and anonymizing business data. It also leverages large-scale language models (LLMs) and natural language processing libraries for data analysis. The server's role is to provide a multifaceted evaluation of work contributions and automatically generate feedback reports.

[0209] Furthermore, the emotion engine analyzes the worker's stress and motivation, and adjusts the feedback based on the analysis results. The terminal is equipped with sensors to acquire the worker's emotional data, allowing for real-time measurement of the worker's emotional state. Based on the emotional state, the server provides feedback, including encouraging messages and counseling suggestions.

[0210] To give a specific example, while a worker is trying out a new work procedure, this system collects data and analyzes it to evaluate the worker's progress and the emotional burden they are experiencing. Based on this evaluation, the server sends support suggestions to reduce the burden via the terminal.

[0211] An example of a prompt message for a generative AI model is: "This worker is having difficulty progressing with a new procedure. Please generate and provide an appropriate encouraging message to help him stay motivated."

[0212] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0213] Step 1:

[0214] The server receives raw data related to workers' tasks via a sensor data aggregation system. This input data includes information about work progress, results, and tools used. The server uses statistical analysis software to anonymize this data and process it into a format that does not identify individuals. As an output of this process, anonymized work data is prepared.

[0215] Step 2:

[0216] The server retrieves anonymized data and performs natural language processing using a Large-Scale Language Model (LLM). The input data is transformed into metrics related to the worker's contribution (e.g., task completion, cooperation). The server uses these metrics to derive a multifaceted evaluation of the worker's contribution. This result becomes an element of the evaluation report.

[0217] Step 3:

[0218] The server automatically generates a feedback report based on the contribution evaluation results. This report includes specific evaluation points and improvement suggestions for the worker. The input evaluation data is generated using a generation algorithm and is ready to be provided anonymously to the worker.

[0219] Step 4:

[0220] The terminal monitors the emotional responses of workers who receive feedback reports in real time. Sensors detect the worker's facial expressions and body movements, and transmit the acquired emotional data to a server.

[0221] Step 5:

[0222] The server inputs the received emotional data into an emotion engine for analysis. The input is used to measure the worker's stress and motivation. The output is a quantitative evaluation of the worker's emotional state.

[0223] Step 6:

[0224] The server adjusts the feedback report based on the results of the emotion engine and creates emotion-based support and improvement suggestions. These meanings are input as prompts into the generative AI model, which generates specific encouraging messages and personalized feedback.

[0225] Step 7:

[0226] The device provides final feedback to the worker and offers counseling and support options tailored to the worker's emotional state. Through this, the user is ready to receive personalized support.

[0227] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0228] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0229] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0233] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0234] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0235] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0236] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0237] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0238] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0239] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0240] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0241] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0242] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0243] The present invention is an anonymous evaluation system for fairly and objectively evaluating the performance of workers, and a specific embodiment thereof is shown below. This system uses an information processing device to collect various data related to the work of workers in an anonymized form and uses that data to perform evaluations.

[0244] Data collection and anonymization

[0245] The server automatically collects data related to workers' work. This includes the progress of tasks assigned to workers, deadline compliance rates, and review results of documents related to tasks. The collected data is anonymized so that individuals cannot be identified. This anonymization process creates a dataset in which individual workers cannot be identified.

[0246] Data analysis and evaluation

[0247] The server analyzes anonymized data using natural language processing techniques. This analysis evaluates indicators such as task completion, cooperation, and interaction among workers. Using a Large-Scale Language Model (LLM) enables a more detailed and multifaceted assessment of contributions. The evaluation results are output as a numerical contribution score.

[0248] Feedback generation and provision

[0249] The server automatically generates feedback reports for workers based on the evaluation results. These reports include the evaluated contribution score, strengths and areas for improvement, and specific advice. The generated feedback reports are sent anonymously to each worker.

[0250] Providing interactive advice

[0251] The terminal provides an interactive interface to obtain additional information and specific improvement measures based on feedback received from workers. Users can use this interface to resolve questions and receive advice on the next steps.

[0252] Specific example: Worker A's tasks for Project X include completing tasks on time and conducting detailed document reviews. After the server anonymizes and collects this work data, it analyzes it using natural language processing. As a result, worker A receives feedback stating, "You meet deadlines, but more effective collaboration is expected." Through the terminal, worker A can receive specific advice on how to improve their collaboration skills.

[0253] In this way, the entire system fairly evaluates workers' performance and contributes to creating a better working environment.

[0254] The following describes the processing flow.

[0255] Step 1:

[0256] The server collects data on task information, work progress, and deliverable quality from business applications and project management tools used by workers. This data includes information such as project name, assigned tasks, start date, and end date. Data collection is performed automatically using APIs and log analysis.

[0257] Step 2:

[0258] The server anonymizes the collected data, making it impossible to identify specific individuals. Specifically, it removes personal names and specific identifying information, or replaces them with alternative identifiers. This ensures that data is managed securely while protecting privacy.

[0259] Step 3:

[0260] The server uses an anonymized data as input and performs natural language processing using a Large-Scale Language Model (LLM). During this process, various indicators are extracted and analyzed, including task completion, communication between workers, and contribution to the work. As a result of the analysis, an evaluation score is generated for each individual worker.

[0261] Step 4:

[0262] The server automatically generates a feedback report based on the evaluation score. This report includes a specific assessment of performance, strengths, areas for improvement, and future action plans. The report is designed to be provided anonymously to workers.

[0263] Step 5:

[0264] The terminal anonymously distributes the generated feedback report to each worker. By viewing this report, workers can objectively understand how their performance is being evaluated.

[0265] Step 6:

[0266] Based on feedback reports, users can use an interactive advice system to resolve questions and receive additional guidance. Specifically, they input advice via their device and receive suggestions for improvement and skill development automatically generated by AI. This interactive process allows users to grasp concrete directions for improving their work.

[0267] (Example 1)

[0268] Next, we will describe Example 1. 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."

[0269] Ensuring fairness and objectivity in employee performance evaluations is difficult. Furthermore, traditional evaluation systems fail to adequately reflect the individual characteristics and contributions of employees, resulting in ineffective use of feedback. Additionally, there are insufficient mechanisms to effectively link evaluation results to employee growth.

[0270] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0271] In this invention, the server includes a device for anonymizing and collecting information related to the activities of multiple workers; means for analyzing the collected anonymized information and evaluating the workers' contributions using natural language processing technology; means for quantifying contribution scores based on the evaluation results, automatically generating feedback documents, and providing them anonymously to the workers; and means for inputting prompt sentences into a generating AI model to perform detailed analysis. This enables fair and detailed performance evaluation and makes it possible to provide feedback that promotes worker growth.

[0272] "Anonymization" is the process of hashing or encoding personal names or IDs so that individual workers cannot be identified.

[0273] "Collection" is the process of automatically gathering information related to the activities of workers.

[0274] "Natural language processing technology" is a technology that mechanically understands, interprets, and generates human language, and is used to evaluate the contribution of workers.

[0275] A "contribution score" is an evaluation index that quantifies the activities and results of workers.

[0276] A "feedback document" is a report provided anonymously to the worker, including their contribution score, evaluation criteria, and suggestions for improvement.

[0277] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs natural language analysis and generation based on prompt sentences.

[0278] A "prompt statement" is a sentence containing specific questions or commands that are input to an AI model to perform analysis or generation.

[0279] A "user interface" refers to an interactive screen or input device used by workers to receive advice on feedback documents.

[0280] The present invention is an evaluation system for fairly and objectively evaluating activities related to the work of multiple workers. The following shows the embodiments for implementing the present invention.

[0281] Data collection and anonymization

[0282] The server automatically collects information such as the task progress of workers, deadline compliance rate, and review results of related documents. For this collection, project management tools and document management systems are used. The server hashes the individual information of the workers and converts it into an unidentifiable form in order to anonymize the collected information. As a result, a secure and anonymized dataset is created.

[0283] Data analysis and evaluation

[0284] The server analyzes the anonymized data using a generative AI model. Specifically, by passing an input of "Please evaluate the task achievement and cooperation degree in Project X" as a prompt sentence to the AI model, a detailed and multi-faceted evaluation is performed using natural language processing technology. As a result, scores for the task achievement and cooperation relationship of the workers are calculated.

[0285] Feedback generation and provision

[0286] The server automatically generates a feedback document based on the analysis results. This document includes the contribution score of the worker, specific evaluation criteria, and improvement suggestions. The generated document is sent to the worker's terminal while remaining anonymous.

[0287] Use of the interactive interface

[0288] The terminal provides an interactive interface that can request further advice from the worker based on the feedback document. The user can input a question such as "Please teach me how to improve teamwork" through this interface and obtain specific advice.

[0289] This system allows for a deeper understanding of employee performance evaluations and enables the provision of effective feedback and support.

[0290] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0291] Step 1:

[0292] The server collects data related to the workers' tasks. Specifically, it obtains task progress information, deadline compliance rates, and review results from project management tools and document management systems as input. To anonymize this information, it hashes the individual worker identifier and outputs it. This output is an anonymized dataset in which individual workers cannot be identified.

[0293] Step 2:

[0294] The server then moves on to the process of analyzing the anonymized data. The anonymized data is sent to a large-scale language model using the prompt "Evaluate the task completion and collaboration levels in Project X." This data processing utilizes natural language processing techniques to produce a multifaceted evaluation of the workers' contributions and collaborative relationships. This output consists of specific numerical values ​​such as task completion and collaboration scores.

[0295] Step 3:

[0296] The server generates a feedback document based on the analysis results. Using the analysis results as input, it automatically creates feedback including contribution scores, evaluation criteria, and improvement suggestions. This output is an anonymous feedback document provided to the worker. The generated document is sent to the worker's terminal.

[0297] Step 4:

[0298] The terminal receives feedback documents and provides the worker with an interactive interface. Through this interface, the user performs specific actions to request additional advice based on the feedback. It receives questions such as "How can I improve teamwork?" as input and outputs responses from a generative AI model. This output allows the user to obtain specific improvement suggestions and advice.

[0299] (Application Example 1)

[0300] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0301] Traditional performance evaluation systems struggle to fairly and quickly assess the contributions of individual workers. Furthermore, there are limited means to immediately utilize evaluation results in the real world, hindering efficient improvement.

[0302] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0303] In this invention, the server includes a medium for collecting anonymized work-related data generated in the work environment, a medium for analyzing data collected during work via smart devices and evaluating the worker's contribution using natural language processing technology, and a medium for displaying the evaluation results in real time and providing feedback to the worker using augmented reality technology. This makes it possible to fairly and quickly evaluate the performance of workers and use the results to improve work in real time.

[0304] An "information processing system" is a set of electronic devices and software used to process business-related data.

[0305] "Anonymization" is a process that protects privacy by processing data so that individual workers cannot be identified.

[0306] A "smart device" is an electronic device with advanced information processing capabilities, including wearable technology.

[0307] "Natural language processing technology" is a technology for computers to understand and analyze human language.

[0308] "Degree of contribution" is a measure that represents the specific achievements and impacts made by workers to their work in numerical values or evaluations.

[0309] "Augmented reality technology" is a technology that overlays digital information on the physical environment and displays it in the real world.

[0310] "Real-time" is a time frame in which events occur and are processed almost simultaneously.

[0311] "Feedback" is information regarding improvement points and advice provided to workers based on evaluation results.

[0312] The system for implementing this invention mainly uses a server, smart devices, and augmented reality (AR) technology. The server anonymizes and collects data generated in the work environment. Specifically, OCR technology and an AI camera are used to transmit the actions and conversations of workers to the server as text data. The server uses Google Cloud Data Loss Prevention to remove personal identification information and achieve anonymization.

[0313] Next, the server utilizes GPT of OpenAI to perform natural language processing and analyze the data. Through this analysis, the degree of contribution of workers is evaluated, and outputs are generated as numerical values and feedback. The evaluation results are output as specific contribution points and text extracting points to be improved.

[0314] Smart devices, primarily smart glasses, are used to display evaluation results to workers in real time via augmented reality technology. Workers can then use the feedback displayed on the glasses to immediately improve their work.

[0315] For example, in the case of staff handling customer service at a virtual store, their customer service performance is evaluated in real time, and they can instantly view feedback on their glasses indicating that "improvements in the efficiency of customer service time can be expected." This system enables the formation of a smooth business improvement cycle, leading to improved performance.

[0316] The following are examples of prompt messages to use when inputting data into a generative AI model.

[0317] The following is employee work data. Based on this, please generate anonymized evaluations and feedback for performance improvement.

[0318] Business data: Task progress, customer interaction logs, work summary...

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] The server acquires data generated by workers during their work from smart devices. As input, task progress and voice data are sent as text information via OCR technology and AI cameras. The server receives this information and outputs it as a dataset.

[0322] Step 2:

[0323] The server anonymizes the acquired dataset. Using the dataset obtained in Step 1 as input, it removes personal information using Google Cloud Data Loss Prevention. It outputs an anonymized dataset, ensuring that individual workers cannot be identified.

[0324] Step 3:

[0325] The server applies natural language processing techniques to analyze the anonymized dataset. The data from Step 2 is passed to OpenAI's GPT as input, where task completion and interaction levels are evaluated. A contribution score and feedback basis are output from the analyzed data.

[0326] Step 4:

[0327] The server generates a feedback report based on the analysis results. Using the contribution score and analysis data obtained in step 3 as input, it creates a text containing evaluation points and improvement suggestions. The server then outputs the automatically generated feedback report.

[0328] Step 5:

[0329] The device (smart glasses) displays the feedback report sent from the server to the user. It receives the feedback generated in step 4 as input and displays the evaluation results and improvement advice on the glasses' display in real time. This allows the user to immediately review the outputted feedback and utilize it in their work.

[0330] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0331] This invention combines an emotion engine with a system that collects anonymized data related to workers' work, analyzes that data to evaluate their contribution, and provides a mechanism to deliver more personalized feedback.

[0332] Data collection and anonymization

[0333] The server automatically collects workers' work information. This data is automatically extracted from work progress, results, and tools used. After collection, it undergoes an anonymization process to ensure that individuals cannot be identified.

[0334] Data analysis and evaluation

[0335] The server analyzes anonymized data using natural language processing techniques to evaluate the workers' contributions. By utilizing large-scale language models (LLMs), the evaluation can be multifaceted, including indicators such as the workers' task completion rate, level of cooperation, and creative contribution.

[0336] Feedback generation and provision

[0337] The server automatically generates a feedback report based on the evaluation results. The feedback includes a quantitative assessment of contribution, areas for improvement, and specific action plans. The evaluation results are provided anonymously to each worker.

[0338] Emotional evaluation by an emotional engine

[0339] The terminal collects emotional data in real time from the worker's responses to the feedback they receive. The server analyzes this data using an emotion engine to measure the worker's stress, motivation, and enthusiasm.

[0340] Personalized feedback provided

[0341] The server adjusts the content of the feedback based on the results of the emotion engine. In particular, when the worker is experiencing anxiety or stress, it can add positive supplementary feedback or content that encourages counseling.

[0342] Interactive Advice and Emotional Interface

[0343] Users can view feedback and ask questions through an emotion-based interactive interface. The emotion interface provides appropriate advice and information for self-improvement based on the user's emotional state.

[0344] Specific example: When worker B receives a feedback report, the emotion engine detects a stress response. In this case, the server adjusts the feedback and adds the message, "We will provide increased support next time." Through the terminal, worker B receives an option to access counseling services and can receive support tailored to their emotional state.

[0345] In this way, a feedback system that takes workers' feelings into account helps to create a better work environment.

[0346] The following describes the processing flow.

[0347] Step 1:

[0348] The server automatically collects task information, progress data, and performance data from the work applications and project management tools used by workers. This includes task start and end dates, completion status, and log data of the tools used.

[0349] Step 2:

[0350] The server anonymizes the collected data. This process removes personally identifiable information and assigns alternative identifiers to identify individual workers, ensuring data security while protecting privacy.

[0351] Step 3:

[0352] The server analyzes the anonymized data using natural language processing techniques. Here, a large-scale language model (LLM) is used to extract indicators that evaluate each worker's task completion, cooperation, and contribution, and calculate a contribution score.

[0353] Step 4:

[0354] The server automatically generates feedback reports based on contribution scores. These reports include the worker's strengths and areas for improvement, as well as specific action plans, all based on their score. The feedback is provided anonymously, with measures taken to prevent the recipient from being identified.

[0355] Step 5:

[0356] The terminal anonymously distributes the generated feedback reports to each worker. It also provides an interface for recording their reactions to the reports in real time.

[0357] Step 6:

[0358] The user reviews the feedback report on their device. The user's emotional responses (e.g., facial expressions, speech) are recorded as emotional data by the emotion engine. The emotion engine automatically categorizes the user's emotional state into states such as stress, relief, and motivation.

[0359] Step 7:

[0360] The server receives the analysis results from the emotion engine and adjusts the feedback content according to the emotional state. For example, if the user is feeling stressed, it adds emotional support by supplementing the feedback with advice on how to relax and words of encouragement.

[0361] Step 8:

[0362] The terminal then presents the adjusted feedback to the user. Furthermore, the user can ask additional questions about the feedback through interactive advice, and the system provides appropriate guidance. This allows the user to deepen their understanding of how to improve their work based on the feedback and suggestions.

[0363] (Example 2)

[0364] Next, we will describe Example 2. 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".

[0365] Traditional employee evaluation systems tend to focus heavily on the quantitative assessment of employees' work performance, relying solely on numerical evaluations and failing to provide feedback that considers employees' emotional states or stress levels. Furthermore, the lack of personalized feedback makes it insufficient for improving employee motivation. This results in monotonous feedback for employees, making it difficult to provide concrete pathways for improvement.

[0366] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0367] In this invention, the server includes means for anonymizing and collecting information related to the work of individual workers; means for analyzing the collected anonymized information and evaluating the worker's contribution using natural language processing technology; means for automatically generating a report based on the evaluation results and providing it anonymously to the worker; means for collecting emotional data from the worker's feedback responses via a terminal; means for analyzing the collected emotional data and evaluating the worker's emotional state; and means for adjusting the content of the feedback based on the emotional state. As a result, the feedback received by the worker will take their emotional state into consideration, and it will be possible to provide specific and constructive action plans tailored to individual circumstances.

[0368] An "information processing device" is a computer system used for collecting, analyzing, storing, and outputting data.

[0369] "Anonymization" is a technology used to protect privacy by removing or transforming information that could identify an individual.

[0370] "Natural language processing technology" is a technology that uses computers to analyze and understand the language that humans use.

[0371] "Contribution level" is an indicator used to evaluate the degree of results and cooperation that workers demonstrate in their work.

[0372] A "report" is a document created based on the analysis results, containing information including evaluation details and areas for improvement.

[0373] A "terminal" is a device used by a user to input and output information.

[0374] "Emotional data" refers to information that indicates the user's emotions and sensory state, and is collected through feedback and conversations.

[0375] "Feedback" refers to information used to communicate evaluations, suggestions, and improvement measures regarding an employee's work.

[0376] An embodiment of the present invention is a feedback system that combines worker performance evaluation with emotional data analysis. This system consists of an information processing device that provides personalized feedback to each worker.

[0377] First, the server automatically collects information related to the worker's work. Specifically, it utilizes a high-speed database system to extract data from sources such as email, project management tools, and work time records. The information is anonymized, thus protecting individual privacy. This anonymization process uses hash functions such as SHA-256.

[0378] Next, the server analyzes the data using natural language processing techniques to evaluate the workers' contributions. Large-scale language models such as BERT and GPT are employed for the analysis. This allows for a multifaceted evaluation of task completion, collaboration, and creative contribution.

[0379] Subsequently, a report is automatically generated based on the evaluation results. The report includes quantitative evaluations, specific improvement suggestions, and a next action plan. The report is provided to the user anonymously.

[0380] The terminal collects the worker's response to the report in real time and sends it to the server as sentiment data. This sentiment data is analyzed by an emotion engine and used to evaluate the worker's stress and motivation levels.

[0381] Ultimately, the server adjusts the feedback based on the evaluation of emotional data, providing situation-appropriate advice and support. This enables personalized feedback that takes into account the worker's emotional state.

[0382] For example, if a worker receives feedback and a stress response is detected, the server adjusts the feedback to include a message such as, "We will provide increased support next time." It also offers counseling service options via the terminal, providing support tailored to the worker's emotional state.

[0383] An example of a prompt message for a generative AI model is, "Based on worker evaluation data, please generate feedback content that takes into account individual emotional states."

[0384] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0385] Step 1:

[0386] The server collects workers' work information. Inputs include email content, project management tool records, and work time data. This information is sent to the server sequentially and anonymized. Specifically, personally identifiable data is removed from the information, and it is anonymized using the SHA-256 hash function. The anonymized work information is then stored in a database as output.

[0387] Step 2:

[0388] The server analyzes anonymized work information using natural language processing technology. The input is the anonymized information obtained in step 1. The server inputs this information into a generative AI model (e.g., BERT, GPT) and outputs it as an evaluation index that quantifies the worker's task completion level, cooperation level, and creative contribution level. Specifically, it analyzes the text data for each task and expresses the results and level of cooperation numerically.

[0389] Step 3:

[0390] The server automatically generates a report based on the evaluation results. The evaluation metrics from Step 2 are used as input. Based on this information, the server generates a report that includes contributions, areas for improvement, and action plans. For example, the report is output as a PDF file and provided anonymously to the worker.

[0391] Step 4:

[0392] The terminal collects the worker's reaction to receiving the report. The input is the user's emotional feedback. The terminal uses a camera, microphone, and input devices to observe the worker's facial expressions, tone of voice, and typing speed in real time, and outputs this as emotional data. This also includes eye gaze and facial expression analysis while the worker is reading the report.

[0393] Step 5:

[0394] The server analyzes the collected emotional data using an emotion engine. It uses the emotional data from step 4 as input. The server evaluates the worker's stress level and motivation and outputs the results. Specifically, it uses an API to perform emotion analysis, and if particularly strong stress or anxiety is detected, it generates supplementary feedback regarding that situation.

[0395] Step 6:

[0396] The server adjusts the feedback based on the sentiment analysis results. The sentiment evaluation results from Step 5 are the input. The server rewrites the feedback, including positive messages and steps for improvement, according to the worker's current emotions. As output, the updated report is provided to the worker again.

[0397] Step 7:

[0398] Users can use the interactive interface provided on their device to review feedback and ask questions. Appropriate advice is output in response to the user's feedback and questions. Specifically, advice and information are provided that takes into account the user's emotional state, supporting workers in deciding on their next course of action.

[0399] (Application Example 2)

[0400] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0401] In the work environment for employees, it is crucial to appropriately evaluate individual contributions to work and provide effective feedback. Traditional evaluation systems struggle to provide personalized feedback that takes into account employees' emotional states. This can lead to decreased employee motivation and excessive stress, negatively impacting company productivity. Therefore, to create a better work environment, a system is needed that evaluates work contributions while providing feedback tailored to individual emotional states.

[0402] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0403] In this invention, the server includes means for anonymizing and collecting data related to the work of individual workers; means for analyzing the collected anonymized data and evaluating the worker's contribution using natural language processing technology; means for automatically generating a feedback report based on the evaluation results and providing it anonymously to the worker; means for monitoring the worker's emotional response to the feedback in real time, analyzing it with an emotion engine, and providing personalized feedback; and means for creating and presenting support and improvement suggestions based on emotions. This makes it possible to provide feedback that takes into account the worker's emotional state, thereby supporting improvements in the work environment and increased productivity.

[0404] An "information processing device" is a device that includes hardware and software for collecting, analyzing, and evaluating data.

[0405] "Data related to the work of individual workers" refers to data related to the progress, results, and tools and equipment used by the workers in their tasks.

[0406] "Anonymization" is the process of removing personally identifiable information from collected data in order to protect individual privacy.

[0407] "Natural language processing technology" is a technology that enables computers to understand and process human language, and is used for the analysis and evaluation of text data.

[0408] "Evaluating contribution" means quantifying the extent to which an employee contributes to the work based on a variety of indicators.

[0409] A "feedback report" is a report created based on the evaluation results and provided to the worker.

[0410] The "emotional engine" is a system that analyzes workers' emotional responses and numerically evaluates their emotional state.

[0411] "Personalized feedback" refers to feedback that is customized according to the worker's emotional state and individual circumstances.

[0412] "Emotion-based support" refers to providing appropriate advice and support based on the emotional state of the worker.

[0413] The system for implementing this invention is configured around an information processing device. This system collects anonymized data related to the worker's tasks and evaluates their contribution using natural language processing technology. It then generates a feedback report based on the evaluation results and provides it to the worker anonymously. After providing the feedback, the terminal acquires the worker's emotional response in real time, and the server analyzes this data using an emotion engine, enabling the provision of personalized feedback.

[0414] The server utilizes high-performance computers and employs statistical analysis software and sensor data aggregation systems for collecting and anonymizing business data. It also leverages large-scale language models (LLMs) and natural language processing libraries for data analysis. The server's role is to provide a multifaceted evaluation of work contributions and automatically generate feedback reports.

[0415] Furthermore, the emotion engine analyzes the worker's stress and motivation, and adjusts the feedback based on the analysis results. The terminal is equipped with sensors to acquire the worker's emotional data, allowing for real-time measurement of the worker's emotional state. Based on the emotional state, the server provides feedback, including encouraging messages and counseling suggestions.

[0416] To give a specific example, while a worker is trying out a new work procedure, this system collects data and analyzes it to evaluate the worker's progress and the emotional burden they are experiencing. Based on this evaluation, the server sends support suggestions to reduce the burden via the terminal.

[0417] An example of a prompt message for a generative AI model is: "This worker is having difficulty progressing with a new procedure. Please generate and provide an appropriate encouraging message to help him stay motivated."

[0418] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0419] Step 1:

[0420] The server receives raw data related to workers' tasks via a sensor data aggregation system. This input data includes information about work progress, results, and tools used. The server uses statistical analysis software to anonymize this data and process it into a format that does not identify individuals. As an output of this process, anonymized work data is prepared.

[0421] Step 2:

[0422] The server retrieves anonymized data and performs natural language processing using a Large-Scale Language Model (LLM). The input data is transformed into metrics related to the worker's contribution (e.g., task completion, cooperation). The server uses these metrics to derive a multifaceted evaluation of the worker's contribution. This result becomes an element of the evaluation report.

[0423] Step 3:

[0424] The server automatically generates a feedback report based on the contribution evaluation results. This report includes specific evaluation points and improvement suggestions for the worker. The input evaluation data is generated using a generation algorithm and is ready to be provided anonymously to the worker.

[0425] Step 4:

[0426] The terminal monitors the emotional responses of workers who receive feedback reports in real time. Sensors detect the worker's facial expressions and body movements, and transmit the acquired emotional data to a server.

[0427] Step 5:

[0428] The server inputs the received emotional data into an emotion engine for analysis. The input is used to measure the worker's stress and motivation. The output is a quantitative evaluation of the worker's emotional state.

[0429] Step 6:

[0430] The server adjusts the feedback report based on the results of the emotion engine and creates emotion-based support and improvement suggestions. These meanings are input as prompts into the generative AI model, which generates specific encouraging messages and personalized feedback.

[0431] Step 7:

[0432] The device provides final feedback to the worker and offers counseling and support options tailored to the worker's emotional state. Through this, the user is ready to receive personalized support.

[0433] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0434] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0435] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0436] [Third Embodiment]

[0437] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0438] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0439] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0440] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0441] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0442] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0443] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0444] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0445] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0446] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0447] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0448] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0449] The present invention is an anonymous evaluation system for fairly and objectively evaluating the performance of workers, and a specific embodiment thereof is shown below. This system uses an information processing device to collect various data related to the work of workers in an anonymized form and uses that data to perform evaluations.

[0450] Data collection and anonymization

[0451] The server automatically collects data related to workers' work. This includes the progress of tasks assigned to workers, deadline compliance rates, and review results of documents related to tasks. The collected data is anonymized so that individuals cannot be identified. This anonymization process creates a dataset in which individual workers cannot be identified.

[0452] Data analysis and evaluation

[0453] The server analyzes anonymized data using natural language processing techniques. This analysis evaluates indicators such as task completion, cooperation, and interaction among workers. Using a Large-Scale Language Model (LLM) enables a more detailed and multifaceted assessment of contributions. The evaluation results are output as a numerical contribution score.

[0454] Feedback generation and provision

[0455] The server automatically generates feedback reports for workers based on the evaluation results. These reports include the evaluated contribution score, strengths and areas for improvement, and specific advice. The generated feedback reports are sent anonymously to each worker.

[0456] Providing interactive advice

[0457] The terminal provides an interactive interface to obtain additional information and specific improvement measures based on feedback received from workers. Users can use this interface to resolve questions and receive advice on the next steps.

[0458] Specific example: Worker A's tasks for Project X include completing tasks on time and conducting detailed document reviews. After the server anonymizes and collects this work data, it analyzes it using natural language processing. As a result, worker A receives feedback stating, "You meet deadlines, but more effective collaboration is expected." Through the terminal, worker A can receive specific advice on how to improve their collaboration skills.

[0459] In this way, the entire system fairly evaluates workers' performance and contributes to creating a better working environment.

[0460] The following describes the processing flow.

[0461] Step 1:

[0462] The server collects data on task information, work progress, and deliverable quality from business applications and project management tools used by workers. This data includes information such as project name, assigned tasks, start date, and end date. Data collection is performed automatically using APIs and log analysis.

[0463] Step 2:

[0464] The server anonymizes the collected data, making it impossible to identify specific individuals. Specifically, it removes personal names and specific identifying information, or replaces them with alternative identifiers. This ensures that data is managed securely while protecting privacy.

[0465] Step 3:

[0466] The server uses an anonymized data as input and performs natural language processing using a Large-Scale Language Model (LLM). During this process, various indicators are extracted and analyzed, including task completion, communication between workers, and contribution to the work. As a result of the analysis, an evaluation score is generated for each individual worker.

[0467] Step 4:

[0468] The server automatically generates a feedback report based on the evaluation score. This report includes a specific assessment of performance, strengths, areas for improvement, and future action plans. The report is designed to be provided anonymously to workers.

[0469] Step 5:

[0470] The terminal anonymously distributes the generated feedback report to each worker. By viewing this report, workers can objectively understand how their performance is being evaluated.

[0471] Step 6:

[0472] Based on feedback reports, users can use an interactive advice system to resolve questions and receive additional guidance. Specifically, they input advice via their device and receive suggestions for improvement and skill development automatically generated by AI. This interactive process allows users to grasp concrete directions for improving their work.

[0473] (Example 1)

[0474] Next, we will describe Example 1. 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."

[0475] Ensuring fairness and objectivity in employee performance evaluations is difficult. Furthermore, traditional evaluation systems fail to adequately reflect the individual characteristics and contributions of employees, resulting in ineffective use of feedback. Additionally, there are insufficient mechanisms to effectively link evaluation results to employee growth.

[0476] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0477] In this invention, the server includes a device for anonymizing and collecting information related to the activities of multiple workers; means for analyzing the collected anonymized information and evaluating the workers' contributions using natural language processing technology; means for quantifying contribution scores based on the evaluation results, automatically generating feedback documents, and providing them anonymously to the workers; and means for inputting prompt sentences into a generating AI model to perform detailed analysis. This enables fair and detailed performance evaluation and makes it possible to provide feedback that promotes worker growth.

[0478] "Anonymization" is the process of hashing or encoding personal names or IDs so that individual workers cannot be identified.

[0479] "Collection" is the process of automatically gathering information related to the activities of workers.

[0480] "Natural language processing technology" is a technology that mechanically understands, interprets, and generates human language, and is used to evaluate the contribution of workers.

[0481] A "contribution score" is an evaluation index that quantifies the activities and results of workers.

[0482] A "feedback document" is a report provided anonymously to the worker, including their contribution score, evaluation criteria, and suggestions for improvement.

[0483] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs natural language analysis and generation based on prompt sentences.

[0484] A "prompt statement" is a sentence containing specific questions or commands that are input to an AI model to perform analysis or generation.

[0485] A "user interface" refers to an interactive screen or input device used by workers to receive advice on feedback documents.

[0486] This invention is an evaluation system for fairly and objectively evaluating the work activities of multiple workers. The following describes embodiments for carrying out this invention.

[0487] Data collection and anonymization

[0488] The server automatically collects information such as workers' task progress, deadline compliance rates, and review results for related documents. Project management tools and document management systems are used for this collection. To anonymize the collected information, the server hashes individual worker information, converting it into an unidentifiable format. This creates a secure and anonymized dataset.

[0489] Data analysis and evaluation

[0490] The server analyzes anonymized data using a generative AI model. Specifically, by passing the prompt "Evaluate the task completion and collaboration levels in Project X" to the AI ​​model, it performs a detailed and multifaceted evaluation using natural language processing techniques. As a result, scores for the workers' task completion and collaboration levels are calculated.

[0491] Generating and providing feedback

[0492] The server automatically generates a feedback document based on the analysis results. This document includes the worker's contribution score, specific evaluation criteria, and improvement suggestions. The generated document is sent anonymously to the worker's terminal.

[0493] Use of interactive interfaces

[0494] The terminal provides workers with an interactive interface that allows them to request further advice based on feedback documents. Through this interface, users can input questions such as, "How can I improve teamwork?" and receive specific advice.

[0495] This system allows for a deeper understanding of employee performance evaluations and enables the provision of effective feedback and support.

[0496] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0497] Step 1:

[0498] The server collects data related to the workers' tasks. Specifically, it obtains task progress information, deadline compliance rates, and review results from project management tools and document management systems as input. To anonymize this information, it hashes the individual worker identifier and outputs it. This output is an anonymized dataset in which individual workers cannot be identified.

[0499] Step 2:

[0500] The server then moves on to the process of analyzing the anonymized data. The anonymized data is sent to a large-scale language model using the prompt "Evaluate the task completion and collaboration levels in Project X." This data processing utilizes natural language processing techniques to produce a multifaceted evaluation of the workers' contributions and collaborative relationships. This output consists of specific numerical values ​​such as task completion and collaboration scores.

[0501] Step 3:

[0502] The server generates a feedback document based on the analysis results. Using the analysis results as input, it automatically creates feedback including contribution scores, evaluation criteria, and improvement suggestions. This output is an anonymous feedback document provided to the worker. The generated document is sent to the worker's terminal.

[0503] Step 4:

[0504] The terminal receives feedback documents and provides the worker with an interactive interface. Through this interface, the user performs specific actions to request additional advice based on the feedback. It receives questions such as "How can I improve teamwork?" as input and outputs responses from a generative AI model. This output allows the user to obtain specific improvement suggestions and advice.

[0505] (Application Example 1)

[0506] Next, we will explain Application Example 1. In the following explanation, 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."

[0507] Traditional performance evaluation systems struggle to fairly and quickly assess the contributions of individual workers. Furthermore, there are limited means to immediately utilize evaluation results in the real world, hindering efficient improvement.

[0508] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0509] In this invention, the server includes a medium for collecting anonymized work-related data generated in the work environment, a medium for analyzing data collected during work via smart devices and evaluating the worker's contribution using natural language processing technology, and a medium for displaying the evaluation results in real time and providing feedback to the worker using augmented reality technology. This makes it possible to fairly and quickly evaluate the performance of workers and use the results to improve work in real time.

[0510] An "information processing system" is a set of electronic devices and software used to process business-related data.

[0511] "Anonymization" is a process that protects privacy by processing data so that individual workers cannot be identified.

[0512] A "smart device" is an electronic device with advanced information processing capabilities, including wearable technology.

[0513] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0514] "Contribution" is a measure that expresses the specific results and impact that an employee has had on their work using numerical values ​​and evaluations.

[0515] Augmented reality technology is a technology that displays digital information overlaid on the physical environment in the real world.

[0516] "Real-time" refers to a time frame in which events occur and are processed almost simultaneously.

[0517] "Feedback" refers to information about areas for improvement and advice provided to employees based on their evaluation results.

[0518] The system implementing this invention primarily utilizes a server, smart devices, and augmented reality (AR) technology. The server collects data generated in the work environment in an anonymized form. Specifically, OCR technology and an AI camera are used to transmit workers' actions and conversations as text data to the server. The server uses Google Cloud Data Loss Prevention to remove personally identifiable information and achieve anonymization.

[0519] Next, the server uses OpenAI's GPT to perform natural language processing and analyze the data. This analysis evaluates the workers' contributions and generates output in the form of numerical data and feedback. The evaluation results are output as text that extracts specific contribution points and areas for improvement.

[0520] Smart devices, primarily smart glasses, are used to display evaluation results to workers in real time via augmented reality technology. Workers can then use the feedback displayed on the glasses to immediately improve their work.

[0521] For example, in the case of staff handling customer service at a virtual store, their customer service performance is evaluated in real time, and they can instantly view feedback on their glasses indicating that "improvements in the efficiency of customer service time can be expected." This system enables the formation of a smooth business improvement cycle, leading to improved performance.

[0522] The following are examples of prompt messages to use when inputting data into a generative AI model.

[0523] The following is employee work data. Based on this, please generate anonymized evaluations and feedback for performance improvement.

[0524] Business data: Task progress, customer interaction logs, work summary...

[0525] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0526] Step 1:

[0527] The server acquires data generated by workers during their work from smart devices. As input, task progress and voice data are sent as text information via OCR technology and AI cameras. The server receives this information and outputs it as a dataset.

[0528] Step 2:

[0529] The server anonymizes the acquired dataset. Using the dataset obtained in Step 1 as input, it removes personal information using Google Cloud Data Loss Prevention. It outputs an anonymized dataset, ensuring that individual workers cannot be identified.

[0530] Step 3:

[0531] The server applies natural language processing techniques to analyze the anonymized dataset. The data from Step 2 is passed to OpenAI's GPT as input, where task completion and interaction levels are evaluated. A contribution score and feedback basis are output from the analyzed data.

[0532] Step 4:

[0533] The server generates a feedback report based on the analysis results. Using the contribution score and analysis data obtained in step 3 as input, it creates a text containing evaluation points and improvement suggestions. The server then outputs the automatically generated feedback report.

[0534] Step 5:

[0535] The device (smart glasses) displays the feedback report sent from the server to the user. It receives the feedback generated in step 4 as input and displays the evaluation results and improvement advice on the glasses' display in real time. This allows the user to immediately review the outputted feedback and utilize it in their work.

[0536] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0537] This invention combines an emotion engine with a system that collects anonymized data related to workers' work, analyzes that data to evaluate their contribution, and provides a mechanism to deliver more personalized feedback.

[0538] Data collection and anonymization

[0539] The server automatically collects workers' work information. This data is automatically extracted from work progress, results, and tools used. After collection, it undergoes an anonymization process to ensure that individuals cannot be identified.

[0540] Data analysis and evaluation

[0541] The server analyzes anonymized data using natural language processing techniques to evaluate the workers' contributions. By utilizing large-scale language models (LLMs), the evaluation can be multifaceted, including indicators such as the workers' task completion rate, level of cooperation, and creative contribution.

[0542] Feedback generation and provision

[0543] The server automatically generates a feedback report based on the evaluation results. The feedback includes a quantitative assessment of contribution, areas for improvement, and specific action plans. The evaluation results are provided anonymously to each worker.

[0544] Emotional evaluation by an emotional engine

[0545] The terminal collects emotional data in real time from the worker's responses to the feedback they receive. The server analyzes this data using an emotion engine to measure the worker's stress, motivation, and enthusiasm.

[0546] Personalized feedback provided

[0547] The server adjusts the content of the feedback based on the results of the emotion engine. In particular, when the worker is experiencing anxiety or stress, it can add positive supplementary feedback or content that encourages counseling.

[0548] Interactive Advice and Emotional Interface

[0549] Users can view feedback and ask questions through an emotion-based interactive interface. The emotion interface provides appropriate advice and information for self-improvement based on the user's emotional state.

[0550] Specific example: When worker B receives a feedback report, the emotion engine detects a stress response. In this case, the server adjusts the feedback and adds the message, "We will provide increased support next time." Through the terminal, worker B receives an option to access counseling services and can receive support tailored to their emotional state.

[0551] In this way, a feedback system that takes workers' feelings into account helps to create a better work environment.

[0552] The following describes the processing flow.

[0553] Step 1:

[0554] The server automatically collects task information, progress data, and performance data from the work applications and project management tools used by workers. This includes task start and end dates, completion status, and log data of the tools used.

[0555] Step 2:

[0556] The server anonymizes the collected data. This process removes personally identifiable information and assigns alternative identifiers to identify individual workers, ensuring data security while protecting privacy.

[0557] Step 3:

[0558] The server analyzes the anonymized data using natural language processing techniques. Here, a large-scale language model (LLM) is used to extract indicators that evaluate each worker's task completion, cooperation, and contribution, and calculate a contribution score.

[0559] Step 4:

[0560] The server automatically generates feedback reports based on contribution scores. These reports include the worker's strengths and areas for improvement, as well as specific action plans, all based on their score. The feedback is provided anonymously, with measures taken to prevent the recipient from being identified.

[0561] Step 5:

[0562] The terminal anonymously distributes the generated feedback reports to each worker. It also provides an interface for recording their reactions to the reports in real time.

[0563] Step 6:

[0564] The user reviews the feedback report on their device. The user's emotional responses (e.g., facial expressions, speech) are recorded as emotional data by the emotion engine. The emotion engine automatically categorizes the user's emotional state into states such as stress, relief, and motivation.

[0565] Step 7:

[0566] The server receives the analysis results from the emotion engine and adjusts the feedback content according to the emotional state. For example, if the user is feeling stressed, it adds emotional support by supplementing the feedback with advice on how to relax and words of encouragement.

[0567] Step 8:

[0568] The terminal then presents the adjusted feedback to the user. Furthermore, the user can ask additional questions about the feedback through interactive advice, and the system provides appropriate guidance. This allows the user to deepen their understanding of how to improve their work based on the feedback and suggestions.

[0569] (Example 2)

[0570] Next, we will describe Example 2. 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."

[0571] Traditional employee evaluation systems tend to focus heavily on the quantitative assessment of employees' work performance, relying solely on numerical evaluations and failing to provide feedback that considers employees' emotional states or stress levels. Furthermore, the lack of personalized feedback makes it insufficient for improving employee motivation. This results in monotonous feedback for employees, making it difficult to provide concrete pathways for improvement.

[0572] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0573] In this invention, the server includes means for anonymizing and collecting information related to the work of individual workers; means for analyzing the collected anonymized information and evaluating the worker's contribution using natural language processing technology; means for automatically generating a report based on the evaluation results and providing it anonymously to the worker; means for collecting emotional data from the worker's feedback responses via a terminal; means for analyzing the collected emotional data and evaluating the worker's emotional state; and means for adjusting the content of the feedback based on the emotional state. As a result, the feedback received by the worker will take their emotional state into consideration, and it will be possible to provide specific and constructive action plans tailored to individual circumstances.

[0574] An "information processing device" is a computer system used for collecting, analyzing, storing, and outputting data.

[0575] "Anonymization" is a technology used to protect privacy by removing or transforming information that could identify an individual.

[0576] "Natural language processing technology" is a technology that uses computers to analyze and understand the language that humans use.

[0577] "Contribution level" is an indicator used to evaluate the degree of results and cooperation that workers demonstrate in their work.

[0578] A "report" is a document created based on the analysis results, containing information including evaluation details and areas for improvement.

[0579] A "terminal" is a device used by a user to input and output information.

[0580] "Emotional data" refers to information that indicates the user's emotions and sensory state, and is collected through feedback and conversations.

[0581] "Feedback" refers to information used to communicate evaluations, suggestions, and improvement measures regarding an employee's work.

[0582] An embodiment of the present invention is a feedback system that combines worker performance evaluation with emotional data analysis. This system consists of an information processing device that provides personalized feedback to each worker.

[0583] First, the server automatically collects information related to the worker's work. Specifically, it utilizes a high-speed database system to extract data from sources such as email, project management tools, and work time records. The information is anonymized, thus protecting individual privacy. This anonymization process uses hash functions such as SHA-256.

[0584] Next, the server analyzes the data using natural language processing techniques to evaluate the workers' contributions. Large-scale language models such as BERT and GPT are employed for the analysis. This allows for a multifaceted evaluation of task completion, collaboration, and creative contribution.

[0585] Subsequently, a report is automatically generated based on the evaluation results. The report includes quantitative evaluations, specific improvement suggestions, and a next action plan. The report is provided to the user anonymously.

[0586] The terminal collects the worker's response to the report in real time and sends it to the server as sentiment data. This sentiment data is analyzed by an emotion engine and used to evaluate the worker's stress and motivation levels.

[0587] Ultimately, the server adjusts the feedback based on the evaluation of emotional data, providing situation-appropriate advice and support. This enables personalized feedback that takes into account the worker's emotional state.

[0588] For example, if a worker receives feedback and a stress response is detected, the server adjusts the feedback to include a message such as, "We will provide increased support next time." It also offers counseling service options via the terminal, providing support tailored to the worker's emotional state.

[0589] An example of a prompt message for a generative AI model is, "Based on worker evaluation data, please generate feedback content that takes into account individual emotional states."

[0590] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0591] Step 1:

[0592] The server collects workers' work information. Inputs include email content, project management tool records, and work time data. This information is sent to the server sequentially and anonymized. Specifically, personally identifiable data is removed from the information, and it is anonymized using the SHA-256 hash function. The anonymized work information is then stored in a database as output.

[0593] Step 2:

[0594] The server analyzes anonymized work information using natural language processing technology. The input is the anonymized information obtained in step 1. The server inputs this information into a generative AI model (e.g., BERT, GPT) and outputs it as an evaluation index that quantifies the worker's task completion level, cooperation level, and creative contribution level. Specifically, it analyzes the text data for each task and expresses the results and level of cooperation numerically.

[0595] Step 3:

[0596] The server automatically generates a report based on the evaluation results. The evaluation metrics from Step 2 are used as input. Based on this information, the server generates a report that includes contributions, areas for improvement, and action plans. For example, the report is output as a PDF file and provided anonymously to the worker.

[0597] Step 4:

[0598] The terminal collects the worker's reaction to receiving the report. The input is the user's emotional feedback. The terminal uses a camera, microphone, and input devices to observe the worker's facial expressions, tone of voice, and typing speed in real time, and outputs this as emotional data. This also includes eye gaze and facial expression analysis while the worker is reading the report.

[0599] Step 5:

[0600] The server analyzes the collected emotional data using an emotion engine. It uses the emotional data from step 4 as input. The server evaluates the worker's stress level and motivation and outputs the results. Specifically, it uses an API to perform emotion analysis, and if particularly strong stress or anxiety is detected, it generates supplementary feedback regarding that situation.

[0601] Step 6:

[0602] The server adjusts the feedback based on the sentiment analysis results. The sentiment evaluation results from Step 5 are the input. The server rewrites the feedback, including positive messages and steps for improvement, according to the worker's current emotions. As output, the updated report is provided to the worker again.

[0603] Step 7:

[0604] Users can use the interactive interface provided on their device to review feedback and ask questions. Appropriate advice is output in response to the user's feedback and questions. Specifically, advice and information are provided that takes into account the user's emotional state, supporting workers in deciding on their next course of action.

[0605] (Application Example 2)

[0606] Next, we will explain application example 2. In the following explanation, 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."

[0607] In the work environment for employees, it is crucial to appropriately evaluate individual contributions to work and provide effective feedback. Traditional evaluation systems struggle to provide personalized feedback that takes into account employees' emotional states. This can lead to decreased employee motivation and excessive stress, negatively impacting company productivity. Therefore, to create a better work environment, a system is needed that evaluates work contributions while providing feedback tailored to individual emotional states.

[0608] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0609] In this invention, the server includes means for anonymizing and collecting data related to the work of individual workers; means for analyzing the collected anonymized data and evaluating the worker's contribution using natural language processing technology; means for automatically generating a feedback report based on the evaluation results and providing it anonymously to the worker; means for monitoring the worker's emotional response to the feedback in real time, analyzing it with an emotion engine, and providing personalized feedback; and means for creating and presenting support and improvement suggestions based on emotions. This makes it possible to provide feedback that takes into account the worker's emotional state, thereby supporting improvements in the work environment and increased productivity.

[0610] An "information processing device" is a device that includes hardware and software for collecting, analyzing, and evaluating data.

[0611] "Data related to the work of individual workers" refers to data related to the progress, results, and tools and equipment used by the workers in their tasks.

[0612] "Anonymization" is the process of removing personally identifiable information from collected data in order to protect individual privacy.

[0613] "Natural language processing technology" is a technology that enables computers to understand and process human language, and is used for the analysis and evaluation of text data.

[0614] "Evaluating contribution" means quantifying the extent to which an employee contributes to the work based on a variety of indicators.

[0615] A "feedback report" is a report created based on the evaluation results and provided to the worker.

[0616] The "emotional engine" is a system that analyzes workers' emotional responses and numerically evaluates their emotional state.

[0617] "Personalized feedback" refers to feedback that is customized according to the worker's emotional state and individual circumstances.

[0618] "Emotion-based support" refers to providing appropriate advice and support based on the emotional state of the worker.

[0619] The system for implementing this invention is configured around an information processing device. This system collects anonymized data related to the worker's tasks and evaluates their contribution using natural language processing technology. It then generates a feedback report based on the evaluation results and provides it to the worker anonymously. After providing the feedback, the terminal acquires the worker's emotional response in real time, and the server analyzes this data using an emotion engine, enabling the provision of personalized feedback.

[0620] The server utilizes high-performance computers and employs statistical analysis software and sensor data aggregation systems for collecting and anonymizing business data. It also leverages large-scale language models (LLMs) and natural language processing libraries for data analysis. The server's role is to provide a multifaceted evaluation of work contributions and automatically generate feedback reports.

[0621] Furthermore, the emotion engine analyzes the worker's stress and motivation, and adjusts the feedback based on the analysis results. The terminal is equipped with sensors to acquire the worker's emotional data, allowing for real-time measurement of the worker's emotional state. Based on the emotional state, the server provides feedback, including encouraging messages and counseling suggestions.

[0622] To give a specific example, while a worker is trying out a new work procedure, this system collects data and analyzes it to evaluate the worker's progress and the emotional burden they are experiencing. Based on this evaluation, the server sends support suggestions to reduce the burden via the terminal.

[0623] An example of a prompt message for a generative AI model is: "This worker is having difficulty progressing with a new procedure. Please generate and provide an appropriate encouraging message to help him stay motivated."

[0624] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0625] Step 1:

[0626] The server receives raw data related to workers' tasks via a sensor data aggregation system. This input data includes information about work progress, results, and tools used. The server uses statistical analysis software to anonymize this data and process it into a format that does not identify individuals. As an output of this process, anonymized work data is prepared.

[0627] Step 2:

[0628] The server retrieves anonymized data and performs natural language processing using a Large-Scale Language Model (LLM). The input data is transformed into metrics related to the worker's contribution (e.g., task completion, cooperation). The server uses these metrics to derive a multifaceted evaluation of the worker's contribution. This result becomes an element of the evaluation report.

[0629] Step 3:

[0630] The server automatically generates a feedback report based on the contribution evaluation results. This report includes specific evaluation points and improvement suggestions for the worker. The input evaluation data is generated using a generation algorithm and is ready to be provided anonymously to the worker.

[0631] Step 4:

[0632] The terminal monitors the emotional responses of workers who receive feedback reports in real time. Sensors detect the worker's facial expressions and body movements, and transmit the acquired emotional data to a server.

[0633] Step 5:

[0634] The server inputs the received emotional data into an emotion engine for analysis. The input is used to measure the worker's stress and motivation. The output is a quantitative evaluation of the worker's emotional state.

[0635] Step 6:

[0636] The server adjusts the feedback report based on the results of the emotion engine and creates emotion-based support and improvement suggestions. These meanings are input as prompts into the generative AI model, which generates specific encouraging messages and personalized feedback.

[0637] Step 7:

[0638] The device provides final feedback to the worker and offers counseling and support options tailored to the worker's emotional state. Through this, the user is ready to receive personalized support.

[0639] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0640] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0641] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0642] [Fourth Embodiment]

[0643] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0644] As shown in Figure 7, the 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.

[0645] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0646] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0647] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0648] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0649] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0650] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0651] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0652] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0653] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0654] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0655] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0656] The present invention is an anonymous evaluation system for fairly and objectively evaluating the performance of workers, and a specific embodiment thereof is shown below. This system uses an information processing device to collect various data related to the work of workers in an anonymized form and uses that data to perform evaluations.

[0657] Data collection and anonymization

[0658] The server automatically collects data related to workers' work. This includes the progress of tasks assigned to workers, deadline compliance rates, and review results of documents related to tasks. The collected data is anonymized so that individuals cannot be identified. This anonymization process creates a dataset in which individual workers cannot be identified.

[0659] Data analysis and evaluation

[0660] The server analyzes anonymized data using natural language processing techniques. This analysis evaluates indicators such as task completion, cooperation, and interaction among workers. Using a Large-Scale Language Model (LLM) enables a more detailed and multifaceted assessment of contributions. The evaluation results are output as a numerical contribution score.

[0661] Feedback generation and provision

[0662] The server automatically generates feedback reports for workers based on the evaluation results. These reports include the evaluated contribution score, strengths and areas for improvement, and specific advice. The generated feedback reports are sent anonymously to each worker.

[0663] Providing interactive advice

[0664] The terminal provides an interactive interface to obtain additional information and specific improvement measures based on feedback received from workers. Users can use this interface to resolve questions and receive advice on the next steps.

[0665] Specific example: Worker A's tasks for Project X include completing tasks on time and conducting detailed document reviews. After the server anonymizes and collects this work data, it analyzes it using natural language processing. As a result, worker A receives feedback stating, "You meet deadlines, but more effective collaboration is expected." Through the terminal, worker A can receive specific advice on how to improve their collaboration skills.

[0666] In this way, the entire system fairly evaluates workers' performance and contributes to creating a better working environment.

[0667] The following describes the processing flow.

[0668] Step 1:

[0669] The server collects data on task information, work progress, and deliverable quality from business applications and project management tools used by workers. This data includes information such as project name, assigned tasks, start date, and end date. Data collection is performed automatically using APIs and log analysis.

[0670] Step 2:

[0671] The server anonymizes the collected data, making it impossible to identify specific individuals. Specifically, it removes personal names and specific identifying information, or replaces them with alternative identifiers. This ensures that data is managed securely while protecting privacy.

[0672] Step 3:

[0673] The server uses an anonymized data as input and performs natural language processing using a Large-Scale Language Model (LLM). During this process, various indicators are extracted and analyzed, including task completion, communication between workers, and contribution to the work. As a result of the analysis, an evaluation score is generated for each individual worker.

[0674] Step 4:

[0675] The server automatically generates a feedback report based on the evaluation score. This report includes a specific assessment of performance, strengths, areas for improvement, and future action plans. The report is designed to be provided anonymously to workers.

[0676] Step 5:

[0677] The terminal anonymously distributes the generated feedback report to each worker. By viewing this report, workers can objectively understand how their performance is being evaluated.

[0678] Step 6:

[0679] Based on feedback reports, users can use an interactive advice system to resolve questions and receive additional guidance. Specifically, they input advice via their device and receive suggestions for improvement and skill development automatically generated by AI. This interactive process allows users to grasp concrete directions for improving their work.

[0680] (Example 1)

[0681] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0682] Ensuring fairness and objectivity in employee performance evaluations is difficult. Furthermore, traditional evaluation systems fail to adequately reflect the individual characteristics and contributions of employees, resulting in ineffective use of feedback. Additionally, there are insufficient mechanisms to effectively link evaluation results to employee growth.

[0683] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0684] In this invention, the server includes a device for anonymizing and collecting information related to the activities of multiple workers; means for analyzing the collected anonymized information and evaluating the workers' contributions using natural language processing technology; means for quantifying contribution scores based on the evaluation results, automatically generating feedback documents, and providing them anonymously to the workers; and means for inputting prompt sentences into a generating AI model to perform detailed analysis. This enables fair and detailed performance evaluation and makes it possible to provide feedback that promotes worker growth.

[0685] "Anonymization" is the process of hashing or encoding personal names or IDs so that individual workers cannot be identified.

[0686] "Collection" is the process of automatically gathering information related to the activities of workers.

[0687] "Natural language processing technology" is a technology that mechanically understands, interprets, and generates human language, and is used to evaluate the contribution of workers.

[0688] A "contribution score" is an evaluation index that quantifies the activities and results of workers.

[0689] A "feedback document" is a report provided anonymously to the worker, including their contribution score, evaluation criteria, and suggestions for improvement.

[0690] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs natural language analysis and generation based on prompt sentences.

[0691] A "prompt statement" is a sentence containing specific questions or commands that are input to an AI model to perform analysis or generation.

[0692] A "user interface" refers to an interactive screen or input device used by workers to receive advice on feedback documents.

[0693] This invention is an evaluation system for fairly and objectively evaluating the work activities of multiple workers. The following describes embodiments for carrying out this invention.

[0694] Data collection and anonymization

[0695] The server automatically collects information such as workers' task progress, deadline compliance rates, and review results for related documents. Project management tools and document management systems are used for this collection. To anonymize the collected information, the server hashes individual worker information, converting it into an unidentifiable format. This creates a secure and anonymized dataset.

[0696] Data analysis and evaluation

[0697] The server analyzes anonymized data using a generative AI model. Specifically, by passing the prompt "Evaluate the task completion and collaboration levels in Project X" to the AI ​​model, it performs a detailed and multifaceted evaluation using natural language processing techniques. As a result, scores for the workers' task completion and collaboration levels are calculated.

[0698] Generating and providing feedback

[0699] The server automatically generates a feedback document based on the analysis results. This document includes the worker's contribution score, specific evaluation criteria, and improvement suggestions. The generated document is sent anonymously to the worker's terminal.

[0700] Use of interactive interfaces

[0701] The terminal provides workers with an interactive interface that allows them to request further advice based on feedback documents. Through this interface, users can input questions such as, "How can I improve teamwork?" and receive specific advice.

[0702] This system allows for a deeper understanding of employee performance evaluations and enables the provision of effective feedback and support.

[0703] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0704] Step 1:

[0705] The server collects data related to the workers' tasks. Specifically, it obtains task progress information, deadline compliance rates, and review results from project management tools and document management systems as input. To anonymize this information, it hashes the individual worker identifier and outputs it. This output is an anonymized dataset in which individual workers cannot be identified.

[0706] Step 2:

[0707] The server then moves on to the process of analyzing the anonymized data. The anonymized data is sent to a large-scale language model using the prompt "Evaluate the task completion and collaboration levels in Project X." This data processing utilizes natural language processing techniques to produce a multifaceted evaluation of the workers' contributions and collaborative relationships. This output consists of specific numerical values ​​such as task completion and collaboration scores.

[0708] Step 3:

[0709] The server generates a feedback document based on the analysis results. Using the analysis results as input, it automatically creates feedback including contribution scores, evaluation criteria, and improvement suggestions. This output is an anonymous feedback document provided to the worker. The generated document is sent to the worker's terminal.

[0710] Step 4:

[0711] The terminal receives feedback documents and provides the worker with an interactive interface. Through this interface, the user performs specific actions to request additional advice based on the feedback. It receives questions such as "How can I improve teamwork?" as input and outputs responses from a generative AI model. This output allows the user to obtain specific improvement suggestions and advice.

[0712] (Application Example 1)

[0713] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0714] Traditional performance evaluation systems struggle to fairly and quickly assess the contributions of individual workers. Furthermore, there are limited means to immediately utilize evaluation results in the real world, hindering efficient improvement.

[0715] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0716] In this invention, the server includes a medium for collecting anonymized work-related data generated in the work environment, a medium for analyzing data collected during work via smart devices and evaluating the worker's contribution using natural language processing technology, and a medium for displaying the evaluation results in real time and providing feedback to the worker using augmented reality technology. This makes it possible to fairly and quickly evaluate the performance of workers and use the results to improve work in real time.

[0717] An "information processing system" is a set of electronic devices and software used to process business-related data.

[0718] "Anonymization" is a process that protects privacy by processing data so that individual workers cannot be identified.

[0719] A "smart device" is an electronic device with advanced information processing capabilities, including wearable technology.

[0720] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0721] "Contribution" is a measure that expresses the specific results and impact that an employee has had on their work using numerical values ​​and evaluations.

[0722] Augmented reality technology is a technology that displays digital information overlaid on the physical environment in the real world.

[0723] "Real-time" refers to a time frame in which events occur and are processed almost simultaneously.

[0724] "Feedback" refers to information about areas for improvement and advice provided to employees based on their evaluation results.

[0725] The system implementing this invention primarily utilizes a server, smart devices, and augmented reality (AR) technology. The server collects data generated in the work environment in an anonymized form. Specifically, OCR technology and an AI camera are used to transmit workers' actions and conversations as text data to the server. The server uses Google Cloud Data Loss Prevention to remove personally identifiable information and achieve anonymization.

[0726] Next, the server uses OpenAI's GPT to perform natural language processing and analyze the data. This analysis evaluates the workers' contributions and generates output in the form of numerical data and feedback. The evaluation results are output as text that extracts specific contribution points and areas for improvement.

[0727] Smart devices, primarily smart glasses, are used to display evaluation results to workers in real time via augmented reality technology. Workers can then use the feedback displayed on the glasses to immediately improve their work.

[0728] For example, in the case of staff handling customer service at a virtual store, their customer service performance is evaluated in real time, and they can instantly view feedback on their glasses indicating that "improvements in the efficiency of customer service time can be expected." This system enables the formation of a smooth business improvement cycle, leading to improved performance.

[0729] The following are examples of prompt messages to use when inputting data into a generative AI model.

[0730] The following is employee work data. Based on this, please generate anonymized evaluations and feedback for performance improvement.

[0731] Business data: Task progress, customer interaction logs, work summary...

[0732] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0733] Step 1:

[0734] The server acquires data generated by workers during their work from smart devices. As input, task progress and voice data are sent as text information via OCR technology and AI cameras. The server receives this information and outputs it as a dataset.

[0735] Step 2:

[0736] The server anonymizes the acquired dataset. Using the dataset obtained in Step 1 as input, it removes personal information using Google Cloud Data Loss Prevention. It outputs an anonymized dataset, ensuring that individual workers cannot be identified.

[0737] Step 3:

[0738] The server applies natural language processing techniques to analyze the anonymized dataset. The data from Step 2 is passed to OpenAI's GPT as input, where task completion and interaction levels are evaluated. A contribution score and feedback basis are output from the analyzed data.

[0739] Step 4:

[0740] The server generates a feedback report based on the analysis results. Using the contribution score and analysis data obtained in step 3 as input, it creates a text containing evaluation points and improvement suggestions. The server then outputs the automatically generated feedback report.

[0741] Step 5:

[0742] The device (smart glasses) displays the feedback report sent from the server to the user. It receives the feedback generated in step 4 as input and displays the evaluation results and improvement advice on the glasses' display in real time. This allows the user to immediately review the outputted feedback and utilize it in their work.

[0743] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0744] This invention combines an emotion engine with a system that collects anonymized data related to workers' work, analyzes that data to evaluate their contribution, and provides a mechanism to deliver more personalized feedback.

[0745] Data collection and anonymization

[0746] The server automatically collects workers' work information. This data is automatically extracted from work progress, results, and tools used. After collection, it undergoes an anonymization process to ensure that individuals cannot be identified.

[0747] Data analysis and evaluation

[0748] The server analyzes anonymized data using natural language processing techniques to evaluate the workers' contributions. By utilizing large-scale language models (LLMs), the evaluation can be multifaceted, including indicators such as the workers' task completion rate, level of cooperation, and creative contribution.

[0749] Feedback generation and provision

[0750] The server automatically generates a feedback report based on the evaluation results. The feedback includes a quantitative assessment of contribution, areas for improvement, and specific action plans. The evaluation results are provided anonymously to each worker.

[0751] Emotional evaluation by an emotional engine

[0752] The terminal collects emotional data in real time from the worker's responses to the feedback they receive. The server analyzes this data using an emotion engine to measure the worker's stress, motivation, and enthusiasm.

[0753] Personalized feedback provided

[0754] The server adjusts the content of the feedback based on the results of the emotion engine. In particular, when the worker is experiencing anxiety or stress, it can add positive supplementary feedback or content that encourages counseling.

[0755] Interactive Advice and Emotional Interface

[0756] Users can view feedback and ask questions through an emotion-based interactive interface. The emotion interface provides appropriate advice and information for self-improvement based on the user's emotional state.

[0757] Specific example: When worker B receives a feedback report, the emotion engine detects a stress response. In this case, the server adjusts the feedback and adds the message, "We will provide increased support next time." Through the terminal, worker B receives an option to access counseling services and can receive support tailored to their emotional state.

[0758] In this way, a feedback system that takes workers' feelings into account helps to create a better work environment.

[0759] The following describes the processing flow.

[0760] Step 1:

[0761] The server automatically collects task information, progress data, and performance data from the work applications and project management tools used by workers. This includes task start and end dates, completion status, and log data of the tools used.

[0762] Step 2:

[0763] The server anonymizes the collected data. This process removes personally identifiable information and assigns alternative identifiers to identify individual workers, ensuring data security while protecting privacy.

[0764] Step 3:

[0765] The server analyzes the anonymized data using natural language processing techniques. Here, a large-scale language model (LLM) is used to extract indicators that evaluate each worker's task completion, cooperation, and contribution, and calculate a contribution score.

[0766] Step 4:

[0767] The server automatically generates feedback reports based on contribution scores. These reports include the worker's strengths and areas for improvement, as well as specific action plans, all based on their score. The feedback is provided anonymously, with measures taken to prevent the recipient from being identified.

[0768] Step 5:

[0769] The terminal anonymously distributes the generated feedback reports to each worker. It also provides an interface for recording their reactions to the reports in real time.

[0770] Step 6:

[0771] The user reviews the feedback report on their device. The user's emotional responses (e.g., facial expressions, speech) are recorded as emotional data by the emotion engine. The emotion engine automatically categorizes the user's emotional state into states such as stress, relief, and motivation.

[0772] Step 7:

[0773] The server receives the analysis results from the emotion engine and adjusts the feedback content according to the emotional state. For example, if the user is feeling stressed, it adds emotional support by supplementing the feedback with advice on how to relax and words of encouragement.

[0774] Step 8:

[0775] The terminal then presents the adjusted feedback to the user. Furthermore, the user can ask additional questions about the feedback through interactive advice, and the system provides appropriate guidance. This allows the user to deepen their understanding of how to improve their work based on the feedback and suggestions.

[0776] (Example 2)

[0777] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0778] Traditional employee evaluation systems tend to focus heavily on the quantitative assessment of employees' work performance, relying solely on numerical evaluations and failing to provide feedback that considers employees' emotional states or stress levels. Furthermore, the lack of personalized feedback makes it insufficient for improving employee motivation. This results in monotonous feedback for employees, making it difficult to provide concrete pathways for improvement.

[0779] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0780] In this invention, the server includes means for anonymizing and collecting information related to the work of individual workers; means for analyzing the collected anonymized information and evaluating the worker's contribution using natural language processing technology; means for automatically generating a report based on the evaluation results and providing it anonymously to the worker; means for collecting emotional data from the worker's feedback responses via a terminal; means for analyzing the collected emotional data and evaluating the worker's emotional state; and means for adjusting the content of the feedback based on the emotional state. As a result, the feedback received by the worker will take their emotional state into consideration, and it will be possible to provide specific and constructive action plans tailored to individual circumstances.

[0781] An "information processing device" is a computer system used for collecting, analyzing, storing, and outputting data.

[0782] "Anonymization" is a technology used to protect privacy by removing or transforming information that could identify an individual.

[0783] "Natural language processing technology" is a technology that uses computers to analyze and understand the language that humans use.

[0784] "Contribution level" is an indicator used to evaluate the degree of results and cooperation that workers demonstrate in their work.

[0785] A "report" is a document created based on the analysis results, containing information including evaluation details and areas for improvement.

[0786] A "terminal" is a device used by a user to input and output information.

[0787] "Emotional data" refers to information that indicates the user's emotions and sensory state, and is collected through feedback and conversations.

[0788] "Feedback" refers to information used to communicate evaluations, suggestions, and improvement measures regarding an employee's work.

[0789] An embodiment of the present invention is a feedback system that combines worker performance evaluation with emotional data analysis. This system consists of an information processing device that provides personalized feedback to each worker.

[0790] First, the server automatically collects information related to the worker's work. Specifically, it utilizes a high-speed database system to extract data from sources such as email, project management tools, and work time records. The information is anonymized, thus protecting individual privacy. This anonymization process uses hash functions such as SHA-256.

[0791] Next, the server analyzes the data using natural language processing techniques to evaluate the workers' contributions. Large-scale language models such as BERT and GPT are employed for the analysis. This allows for a multifaceted evaluation of task completion, collaboration, and creative contribution.

[0792] Subsequently, a report is automatically generated based on the evaluation results. The report includes quantitative evaluations, specific improvement suggestions, and a next action plan. The report is provided to the user anonymously.

[0793] The terminal collects the worker's response to the report in real time and sends it to the server as sentiment data. This sentiment data is analyzed by an emotion engine and used to evaluate the worker's stress and motivation levels.

[0794] Ultimately, the server adjusts the feedback based on the evaluation of emotional data, providing situation-appropriate advice and support. This enables personalized feedback that takes into account the worker's emotional state.

[0795] For example, if a worker receives feedback and a stress response is detected, the server adjusts the feedback to include a message such as, "We will provide increased support next time." It also offers counseling service options via the terminal, providing support tailored to the worker's emotional state.

[0796] An example of a prompt message for a generative AI model is, "Based on worker evaluation data, please generate feedback content that takes into account individual emotional states."

[0797] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0798] Step 1:

[0799] The server collects workers' work information. Inputs include email content, project management tool records, and work time data. This information is sent to the server sequentially and anonymized. Specifically, personally identifiable data is removed from the information, and it is anonymized using the SHA-256 hash function. The anonymized work information is then stored in a database as output.

[0800] Step 2:

[0801] The server analyzes anonymized work information using natural language processing technology. The input is the anonymized information obtained in step 1. The server inputs this information into a generative AI model (e.g., BERT, GPT) and outputs it as an evaluation index that quantifies the worker's task completion level, cooperation level, and creative contribution level. Specifically, it analyzes the text data for each task and expresses the results and level of cooperation numerically.

[0802] Step 3:

[0803] The server automatically generates a report based on the evaluation results. The evaluation metrics from Step 2 are used as input. Based on this information, the server generates a report that includes contributions, areas for improvement, and action plans. For example, the report is output as a PDF file and provided anonymously to the worker.

[0804] Step 4:

[0805] The terminal collects the worker's reaction to receiving the report. The input is the user's emotional feedback. The terminal uses a camera, microphone, and input devices to observe the worker's facial expressions, tone of voice, and typing speed in real time, and outputs this as emotional data. This also includes eye gaze and facial expression analysis while the worker is reading the report.

[0806] Step 5:

[0807] The server analyzes the collected emotional data using an emotion engine. It uses the emotional data from step 4 as input. The server evaluates the worker's stress level and motivation and outputs the results. Specifically, it uses an API to perform emotion analysis, and if particularly strong stress or anxiety is detected, it generates supplementary feedback regarding that situation.

[0808] Step 6:

[0809] The server adjusts the feedback based on the sentiment analysis results. The sentiment evaluation results from Step 5 are the input. The server rewrites the feedback, including positive messages and steps for improvement, according to the worker's current emotions. As output, the updated report is provided to the worker again.

[0810] Step 7:

[0811] Users can use the interactive interface provided on their device to review feedback and ask questions. Appropriate advice is output in response to the user's feedback and questions. Specifically, advice and information are provided that takes into account the user's emotional state, supporting workers in deciding on their next course of action.

[0812] (Application Example 2)

[0813] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0814] In the work environment for employees, it is crucial to appropriately evaluate individual contributions to work and provide effective feedback. Traditional evaluation systems struggle to provide personalized feedback that takes into account employees' emotional states. This can lead to decreased employee motivation and excessive stress, negatively impacting company productivity. Therefore, to create a better work environment, a system is needed that evaluates work contributions while providing feedback tailored to individual emotional states.

[0815] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0816] In this invention, the server includes means for anonymizing and collecting data related to the work of individual workers; means for analyzing the collected anonymized data and evaluating the worker's contribution using natural language processing technology; means for automatically generating a feedback report based on the evaluation results and providing it anonymously to the worker; means for monitoring the worker's emotional response to the feedback in real time, analyzing it with an emotion engine, and providing personalized feedback; and means for creating and presenting support and improvement suggestions based on emotions. This makes it possible to provide feedback that takes into account the worker's emotional state, thereby supporting improvements in the work environment and increased productivity.

[0817] An "information processing device" is a device that includes hardware and software for collecting, analyzing, and evaluating data.

[0818] "Data related to the work of individual workers" refers to data related to the progress, results, and tools and equipment used by the workers in their tasks.

[0819] "Anonymization" is the process of removing personally identifiable information from collected data in order to protect individual privacy.

[0820] "Natural language processing technology" is a technology that enables computers to understand and process human language, and is used for the analysis and evaluation of text data.

[0821] "Evaluating contribution" means quantifying the extent to which an employee contributes to the work based on a variety of indicators.

[0822] A "feedback report" is a report created based on the evaluation results and provided to the worker.

[0823] The "emotional engine" is a system that analyzes workers' emotional responses and numerically evaluates their emotional state.

[0824] "Personalized feedback" refers to feedback that is customized according to the worker's emotional state and individual circumstances.

[0825] "Emotion-based support" refers to providing appropriate advice and support based on the emotional state of the worker.

[0826] The system for implementing this invention is configured around an information processing device. This system collects anonymized data related to the worker's tasks and evaluates their contribution using natural language processing technology. It then generates a feedback report based on the evaluation results and provides it to the worker anonymously. After providing the feedback, the terminal acquires the worker's emotional response in real time, and the server analyzes this data using an emotion engine, enabling the provision of personalized feedback.

[0827] The server utilizes high-performance computers and employs statistical analysis software and sensor data aggregation systems for collecting and anonymizing business data. It also leverages large-scale language models (LLMs) and natural language processing libraries for data analysis. The server's role is to provide a multifaceted evaluation of work contributions and automatically generate feedback reports.

[0828] Furthermore, the emotion engine analyzes the worker's stress and motivation, and adjusts the feedback based on the analysis results. The terminal is equipped with sensors to acquire the worker's emotional data, allowing for real-time measurement of the worker's emotional state. Based on the emotional state, the server provides feedback, including encouraging messages and counseling suggestions.

[0829] To give a specific example, while a worker is trying out a new work procedure, this system collects data and analyzes it to evaluate the worker's progress and the emotional burden they are experiencing. Based on this evaluation, the server sends support suggestions to reduce the burden via the terminal.

[0830] An example of a prompt message for a generative AI model is: "This worker is having difficulty progressing with a new procedure. Please generate and provide an appropriate encouraging message to help him stay motivated."

[0831] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0832] Step 1:

[0833] The server receives raw data related to workers' tasks via a sensor data aggregation system. This input data includes information about work progress, results, and tools used. The server uses statistical analysis software to anonymize this data and process it into a format that does not identify individuals. As an output of this process, anonymized work data is prepared.

[0834] Step 2:

[0835] The server retrieves anonymized data and performs natural language processing using a Large-Scale Language Model (LLM). The input data is transformed into metrics related to the worker's contribution (e.g., task completion, cooperation). The server uses these metrics to derive a multifaceted evaluation of the worker's contribution. This result becomes an element of the evaluation report.

[0836] Step 3:

[0837] The server automatically generates a feedback report based on the contribution evaluation results. This report includes specific evaluation points and improvement suggestions for the worker. The input evaluation data is generated using a generation algorithm and is ready to be provided anonymously to the worker.

[0838] Step 4:

[0839] The terminal monitors the emotional responses of workers who receive feedback reports in real time. Sensors detect the worker's facial expressions and body movements, and transmit the acquired emotional data to a server.

[0840] Step 5:

[0841] The server inputs the received emotional data into an emotion engine for analysis. The input is used to measure the worker's stress and motivation. The output is a quantitative evaluation of the worker's emotional state.

[0842] Step 6:

[0843] The server adjusts the feedback report based on the results of the emotion engine and creates emotion-based support and improvement suggestions. These meanings are input as prompts into the generative AI model, which generates specific encouraging messages and personalized feedback.

[0844] Step 7:

[0845] The device provides final feedback to the worker and offers counseling and support options tailored to the worker's emotional state. Through this, the user is ready to receive personalized support.

[0846] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0847] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0848] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0849] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0850] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0851] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0852] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0853] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0854] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0855] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0856] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0857] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0858] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0859] 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.

[0860] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0861] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0862] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0863] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0864] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0865] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0866] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0867] The following is further disclosed regarding the embodiments described above.

[0868] (Claim 1)

[0869] In an information processing device, a means for anonymizing and collecting data related to the work of individual workers,

[0870] A method for analyzing collected anonymized data and evaluating the contribution of workers using natural language processing technology,

[0871] A means of automatically generating feedback reports based on evaluation results and providing them anonymously to workers,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, wherein the feedback report includes specific evaluation points and improvement suggestions.

[0875] (Claim 3)

[0876] The system according to claim 1, further comprising means for providing an interface for workers to receive advice in an interactive format regarding feedback reports.

[0877] "Example 1"

[0878] (Claim 1)

[0879] A device for anonymizing and collecting information related to the activities of multiple workers,

[0880] A means for analyzing collected anonymized information and evaluating the contribution of workers using natural language processing technology,

[0881] A means of quantifying contribution scores based on evaluation results, automatically generating feedback documents, and providing them anonymously to workers,

[0882] A means of inputting prompt sentences into a generative AI model and performing detailed analysis,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, wherein the feedback document includes specific evaluation criteria and improvement suggestions.

[0886] (Claim 3)

[0887] The system according to claim 1, further comprising means for providing a user interface for an operator to interactively receive advice on a feedback document.

[0888] "Application Example 1"

[0889] (Claim 1)

[0890] In information processing systems, a medium for collecting anonymized work-related data generated in the work environment,

[0891] A system that analyzes data collected during work via smart devices and uses natural language processing technology to evaluate the contribution of workers,

[0892] A medium that utilizes augmented reality technology to display evaluation results in real time and provide feedback to workers,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, wherein the feedback report includes specific evaluation criteria and improvement suggestions and is displayed on a smart device.

[0896] (Claim 3)

[0897] The system according to claim 1, further comprising an interactive medium for workers to receive advice in a dialogue format regarding feedback reports.

[0898] "Example 2 of combining an emotion engine"

[0899] (Claim 1)

[0900] In an information processing device, a means for collecting anonymized information related to the work of individual workers,

[0901] A means of analyzing collected anonymized information and using natural language processing technology to evaluate the contribution of workers,

[0902] A means of automatically generating reports based on evaluation results and providing them anonymously to workers,

[0903] A means of collecting emotional data from workers' feedback responses via a terminal,

[0904] A means of analyzing collected emotional data to evaluate the emotional state of workers,

[0905] A means of adjusting the content of feedback based on emotional state,

[0906] A system that includes this.

[0907] (Claim 2)

[0908] The system according to claim 1, wherein the report provides emotionally sensitive feedback, including specific evaluation points and suggestions for improvement.

[0909] (Claim 3)

[0910] The system according to claim 1, comprising means for providing an interactive interface for workers to receive advice in a dialogue format regarding a report.

[0911] "Application example 2 when combining with an emotional engine"

[0912] (Claim 1)

[0913] In an information processing device, a means for anonymizing and collecting data related to the work of individual workers,

[0914] A method for analyzing collected anonymized data and evaluating the contribution of workers using natural language processing technology,

[0915] A means of automatically generating feedback reports based on evaluation results and providing them anonymously to workers,

[0916] A means of monitoring workers' emotional responses to feedback in real time, analyzing them with an emotion engine, and providing personalized feedback.

[0917] A means of creating and presenting emotionally-based support and improvement proposals,

[0918] A system that includes this.

[0919] (Claim 2)

[0920] The system according to claim 1, wherein the feedback report includes specific evaluation points and improvement suggestions, and further includes supplementary suggestions tailored to the worker's emotional state.

[0921] (Claim 3)

[0922] The system according to claim 1, further comprising an interface for workers to receive advice in a dialogue format in response to feedback reports, and means for suggesting appropriate support according to their emotional state. [Explanation of Symbols]

[0923] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. In an information processing device, a means for anonymizing and collecting data related to the work of individual workers, A method for analyzing collected anonymized data and evaluating the contribution of workers using natural language processing technology, A means of automatically generating feedback reports based on evaluation results and providing them anonymously to workers, A system that includes this.

2. The system according to claim 1, wherein the feedback report includes specific evaluation points and improvement suggestions.

3. The system according to claim 1, further comprising means for providing an interface for workers to receive advice in a dialogue format regarding feedback reports.

Images