system

Abstract

The system according to this embodiment aims to integrate and analyze various internal data sources to conduct a comprehensive and unbiased evaluation. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, an evaluation unit, and a provision unit. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit. The evaluation unit performs an evaluation based on the analysis results obtained by the analysis unit. The provision unit provides the evaluation results obtained by the evaluation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the integration and analysis of various data sources within the company to conduct a comprehensive and fair evaluation have not been sufficiently carried out, and there is room for improvement.

[0005] [[ID=�9]]The system according to an embodiment aims to integrate and analyze various data sources within the company and conduct a comprehensive and fair evaluation.

Means for Solving the Problems

[0006] The system according to an embodiment includes a collection unit, an analysis unit, an evaluation unit, and a provision unit. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit. The evaluation unit conducts an evaluation based on the analysis results obtained by the analysis unit. The provision unit provides the evaluation results obtained by the evaluation unit. [Effects of the Invention]

[0007] The system according to this embodiment can integrate and analyze various internal data sources to perform a comprehensive and unbiased evaluation. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. 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).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The 360-degree evaluation system according to an embodiment of the present invention is an innovative system that combines generative AI and multimodal AI. This system integrates and analyzes diverse internal data sources to achieve comprehensive and fair evaluations that go beyond the limitations of conventional personnel evaluations. Specifically, it consists of the following steps: First, an AI agent integrates and analyzes diverse internal data sources in real time. Next, the generative AI and multimodal AI work together to continuously evaluate daily communication and task performance. This evaluation has the function of detecting and mitigating unconscious bias. It also predicts future performance and potential challenges, supporting proactive talent development. Furthermore, the AI ​​automatically generates multifaceted evaluation indicators and analyzes 360-degree feedback. This eliminates subjectivity in evaluations and improves the efficiency of the evaluation process. Objective evaluations are possible even under remote work conditions without difficulty. For example, evaluation accuracy can be improved by utilizing user behavior data. The AI ​​agent continuously learns and self-improves in response to environmental changes. It also comprehensively analyzes text, voice, and image data, automating everything from goal setting to execution. This creates a workplace environment where all employees are fairly evaluated and their contributions are properly recognized. It democratizes evaluation, improves engagement, maximizes performance, and fosters innovation. Thus, the 360-degree evaluation system enables comprehensive and fair employee evaluation.

[0029] The 360-degree evaluation system according to the embodiment comprises a collection unit, an analysis unit, an evaluation unit, and a provision unit. The collection unit collects data. The collection unit collects data from various data sources within the company, for example. The collection unit can collect text data, numerical data, image data, etc. The collection unit can use sensors, databases, APIs, etc., as means of data collection. The collection unit can set the data collection frequency and collect data periodically, for example. The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the data using AI, for example. The analysis unit can use machine learning algorithms, deep learning algorithms, etc., as analysis algorithms. The analysis unit can perform tasks such as pattern detection, anomaly detection, and prediction for data analysis purposes, for example. The evaluation unit performs evaluations based on the analysis results obtained by the analysis unit. The evaluation unit performs evaluations using AI, for example. The evaluation unit can use performance indicators, behavioral indicators, feedback indicators, etc., as evaluation criteria. The evaluation unit can use scoring, ranking, clustering, etc., as evaluation methods. The provisioning unit provides the evaluation results obtained by the evaluation unit. The provisioning unit provides the evaluation results using, for example, AI. The provisioning unit can use, for example, a dashboard, reports, notifications, etc., as a means of provision. The provisioning unit can set, for example, the timing of provision to be real time, periodic, event-driven, etc. As a result, the 360-degree evaluation system according to the embodiment can efficiently collect, analyze, evaluate, and provide data.

[0030] The data collection unit collects data. For example, the data collection unit collects data from various internal data sources. Specifically, it can collect data from internal HR databases, business systems, email servers, chat tools, project management tools, etc. The data collection unit can collect text data, numerical data, image data, etc. Text data includes employee work reports, feedback comments, and email content. Numerical data includes performance indicators, attendance data, and project progress. Image data includes employee profile pictures and meeting screenshots. The data collection unit can use sensors, databases, APIs, etc., as data collection methods. Sensors include environmental sensors in the office and sensors in the attendance management system. Databases include internal SQL databases and NoSQL databases. APIs include APIs for retrieving data from external cloud services and internal microservices. The data collection unit can set the data collection frequency and collect data regularly. Collection frequencies can be set to real-time, hourly, daily, or weekly. This allows the data collection unit to efficiently collect necessary data from various internal data sources and build a data infrastructure for the entire system.

[0031] The analysis department analyzes the data collected by the data collection department. For example, the analysis department uses AI to analyze data. Specifically, it can analyze text data using natural language processing (NLP) technology to perform sentiment analysis and topic modeling. For numerical data, it can perform statistical analysis and regression analysis to detect performance trends and outliers. For image data, it can perform face recognition and object detection using image recognition technology. The analysis department can use various analytical algorithms, such as machine learning algorithms and deep learning algorithms. Machine learning algorithms include decision trees, random forests, and support vector machines (SVMs). Deep learning algorithms include convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer models. For example, the analysis department can perform tasks such as pattern detection, anomaly detection, and prediction. Pattern detection allows for understanding employee behavior patterns and trends in work performance. Anomaly detection allows for early detection of unusual behavior or performance declines. Prediction allows for forecasting future performance and employee turnover risk. This allows the analysis department to analyze the collected data from multiple perspectives and provide insights into the entire system.

[0032] The evaluation department conducts evaluations based on the analysis results obtained by the analysis department. The evaluation department uses AI, for example, to perform evaluations. Specifically, it can use machine learning models to score employee performance and create rankings. The evaluation department can use performance indicators, behavioral indicators, and feedback indicators as evaluation criteria, for example. Performance indicators include the degree of achievement of performance targets, project completion rates, and sales figures. Behavioral indicators include attendance rates, frequency of meeting participation, and frequency of communication within the team. Feedback indicators include feedback comments from supervisors and colleagues, and evaluations from customers. The evaluation department can use scoring, ranking, and clustering as evaluation methods, for example. Scoring allows for the quantification of employee performance based on each indicator and the calculation of an overall score. Ranking allows for the ranking of employees based on their scores, enabling the identification of high-performing employees. Clustering allows for the classification of employees into specific groups, grouping employees with common characteristics. This enables the evaluation department to conduct objective and fair evaluations based on the analysis results and appropriately assess employee performance.

[0033] The service provider will provide the evaluation results obtained by the evaluation provider. The service provider will provide evaluation results using, for example, AI. Specifically, it will provide a dashboard to visually display evaluation results in an easy-to-understand manner and display evaluation information that is updated in real time. The service provider can use dashboards, reports, notifications, etc., as means of delivery. As a dashboard, it can display evaluation scores, rankings, and performance trends for each employee in graphs and charts. As a report, it can provide regularly generated evaluation reports in PDF or Excel format, allowing for detailed review of evaluation results. As a notification, it can notify evaluation results and important feedback via email or chat tools, enabling rapid information sharing. The service provider can set the timing of delivery, for example, to be real-time, periodic, or event-driven. In real-time, evaluation results can be provided immediately via dashboards and notifications as soon as they are updated. In periodic, evaluation reports can be generated and provided at regular intervals, such as weekly or monthly. In event-driven mode, evaluation results can be provided in response to specific events (for example, project completion or end of quarter). This allows the service provider to provide evaluation results quickly and effectively, providing employees and managers with information to take appropriate action.

[0034] The bias reduction unit can detect and mitigate unconscious bias. For example, the bias reduction unit can use AI to detect unconscious bias. The bias reduction unit can detect specific types of bias, such as gender bias and age bias. The bias reduction unit can mitigate bias using, for example, a bias reduction algorithm. The bias reduction unit can use, for example, an index to evaluate the degree of bias reduction as a method for measuring the effectiveness of the reduction. This allows for improved fairness in evaluation by detecting and mitigating unconscious bias.

[0035] The prediction unit can predict future performance and potential challenges. For example, the prediction unit can use AI to predict future performance. For example, the prediction unit can use regression models, time series models, deep learning models, etc., as prediction models. For example, the prediction unit can use sales, customer satisfaction, productivity, etc., as performance indicators to be predicted. For example, the prediction unit can use risk assessment algorithms to predict potential challenges. For example, the prediction unit can use anomaly detection algorithms as a method for identifying challenges. This allows for proactive talent development support by predicting future performance and potential challenges.

[0036] The Data Utilization Department can utilize user behavior data. For example, the Data Utilization Department can analyze user behavior data using AI. Specific types of user behavior data that the Data Utilization Department can use include website click data and app usage data. For example, data collection methods include log data collection, sensor usage, and API utilization. The Data Utilization Department can, for example, use algorithms to improve evaluation accuracy based on user behavior data. This allows for improved evaluation accuracy through the utilization of user behavior data.

[0037] The learning unit can continuously learn and improve itself. For example, the learning unit can continuously learn using AI. The learning unit can use various learning algorithms, such as online learning algorithms and reinforcement learning algorithms. The learning unit can set the frequency of learning data updates to real-time, periodic, event-driven, etc. The learning unit can build a feedback loop for self-improvement and optimize the algorithm based on the learning results. This allows the system's accuracy to improve through continuous learning and self-improvement.

[0038] The integrated analysis unit can comprehensively analyze text, audio, and image data. For example, the integrated analysis unit can analyze text data using AI. For example, the integrated analysis unit can analyze text data using natural language processing algorithms. For example, the integrated analysis unit can analyze audio data using speech recognition algorithms. For example, the integrated analysis unit can analyze image data using image recognition algorithms. For example, the integrated analysis unit can use data fusion technology as a method of data integration. This allows for improved evaluation accuracy by comprehensively analyzing text, audio, and image data.

[0039] The data collection unit can integrate data from different departments within the company, thereby improving the accuracy of data collection. For example, the unit can link the databases of each department to collect data in an integrated manner. For example, the unit can standardize data formats across departments to ensure data integrity. For example, the unit can establish inter-departmental data sharing protocols to achieve efficient data collection. This allows for improved data collection accuracy by integrating data from different departments within the company.

[0040] The data collection unit can prioritize the collection of data related to specific projects or tasks during data collection. For example, the data collection unit can prioritize the collection of relevant data according to the progress of a project. For example, the data collection unit can prioritize the collection of necessary data based on the importance of a task. For example, the data collection unit can adjust the timing of data collection to match project deadlines. This allows for the efficient collection of necessary data by prioritizing the collection of data related to specific projects or tasks.

[0041] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, the data collection unit can prioritize the collection of relevant data based on the user's current location. For example, the data collection unit can collect highly relevant data by referring to the user's travel history. For example, the data collection unit can prioritize the collection of necessary data based on the user's geographical activity range. As a result, by prioritizing the collection of highly relevant data while considering the user's geographical location information, necessary data can be collected efficiently.

[0042] The data collection unit can analyze users' social media activity and collect relevant data during data collection. For example, the data collection unit can analyze the content of users' social media posts and collect relevant data. For example, the data collection unit can collect necessary data by considering users' social media friendships. For example, the data collection unit can adjust the timing of data collection based on the frequency of users' social media activity. This allows for the efficient collection of relevant data by analyzing users' social media activity.

[0043] The analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit can perform a detailed analysis on high-importance data, and a simplified analysis on low-importance data. The analysis unit can also allocate analysis resources according to the importance of the data. This allows for efficient analysis by adjusting the level of detail based on the importance of the data.

[0044] The analysis unit can apply different analysis algorithms depending on the data category during analysis. For example, the analysis unit can apply a natural language processing algorithm to text data. For example, the analysis unit can apply an image recognition algorithm to image data. For example, the analysis unit can apply a speech recognition algorithm to audio data. By applying different analysis algorithms depending on the data category, the accuracy of the analysis can be improved.

[0045] The analysis department can prioritize analyses based on when the data was submitted. For example, the analysis department can prioritize analyzing the most recent data. For example, the analysis department can postpone analyzing older data. For example, the analysis department can allocate analysis resources according to the submission date. This allows for prioritizing the analysis of the most recent data by determining the analysis priority based on the data submission date.

[0046] The analysis unit can adjust the order of analysis based on the relevance of the data. For example, the analysis unit can prioritize analyzing highly relevant data. For example, the analysis unit can postpone analyzing less relevant data. For example, the analysis unit can allocate analysis resources according to the relevance of the data. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the data.

[0047] The evaluation unit can improve the accuracy of its evaluations by considering the interrelationships between data. For example, the evaluation unit can analyze the correlations between data and reflect them in the evaluation. For example, the evaluation unit can set evaluation criteria by considering the interdependence of data. For example, the evaluation unit can weight the evaluation based on the interrelationships of data. In this way, the accuracy of the evaluation can be improved by considering the interrelationships of data.

[0048] The evaluation department can consider the attribute information of data submitters when conducting evaluations. For example, the evaluation department can adjust evaluation criteria based on the submitter's position and job responsibilities. For example, the evaluation department can consider the submitter's years of experience and skill level when conducting evaluations. For example, the evaluation department can refer to the submitter's past evaluation history when conducting evaluations. This allows for more appropriate evaluations by considering the attribute information of data submitters.

[0049] The evaluation unit can perform evaluations while considering the geographical distribution of the data. For example, the evaluation unit can integrate geographically dispersed data and reflect it in the evaluation. For example, the evaluation unit can set evaluation criteria while considering the characteristics of each region. For example, the evaluation unit can weight the evaluation based on geographical distribution. This makes it possible to perform more appropriate evaluations by considering the geographical distribution of the data.

[0050] The evaluation unit can improve the accuracy of its evaluation by referring to relevant literature during the evaluation process. For example, the evaluation unit can refer to relevant literature and set evaluation criteria. For example, the evaluation unit can reflect the findings of relevant literature in its evaluation. For example, the evaluation unit can weight the evaluation based on relevant literature. In this way, the accuracy of the evaluation can be improved by referring to relevant literature for the data.

[0051] The information provider can adjust the level of detail provided based on the importance of the information at the time of provision. For example, the provider can provide detailed explanations for highly important information. For example, the provider can provide simplified explanations for less important information. For example, the provider can allocate resources for provision according to the importance of the information. This allows for efficient information provision by adjusting the level of detail based on the importance of the information.

[0052] The information provider can apply different information provision algorithms depending on the information category at the time of provision. For example, the provider can apply a natural language generation algorithm to text information. For example, the provider can apply an image generation algorithm to image information. For example, the provider can apply a speech generation algorithm to speech information. By applying different information provision algorithms depending on the information category, the accuracy of the provision can be improved.

[0053] The information provider can determine the priority of information provision based on when the information was submitted. For example, the provider can prioritize providing the most recent information. For example, the provider can postpone providing older information. For example, the provider can allocate resources for provision according to the submission date. This allows for the provision of the most recent information by prioritizing information provision based on when it was submitted.

[0054] The information provider can adjust the order of information delivery based on its relevance. For example, the provider can prioritize providing highly relevant information. For example, the provider can postpone providing less relevant information. For example, the provider can allocate resources for delivery according to the relevance of the information. This allows for efficient information delivery by adjusting the order of delivery based on the relevance of the information.

[0055] The bias reduction unit can improve the accuracy of bias reduction by considering the interrelationships between data. For example, the bias reduction unit can analyze the correlations between data and reflect them in the bias reduction. For example, the bias reduction unit can set the bias reduction method by considering the interdependence of data. For example, the bias reduction unit can weight the bias reduction based on the interrelationships of data. In this way, the accuracy of bias reduction can be improved by considering the interrelationships of data.

[0056] The bias reduction unit can perform bias reduction while considering the attribute information of the data submitter. For example, the bias reduction unit can adjust the bias reduction method based on the submitter's position and job description. For example, the bias reduction unit can perform bias reduction while considering the submitter's years of experience and skill level. For example, the bias reduction unit can perform bias reduction while referring to the submitter's past evaluation history. This makes it possible to perform more appropriate bias reduction by considering the attribute information of the data submitter.

[0057] The bias reduction unit can perform bias reduction while considering the geographical distribution of the data. For example, the bias reduction unit can integrate geographically dispersed data and reflect this in the bias reduction. For example, the bias reduction unit can set bias reduction methods while considering the characteristics of each region. For example, the bias reduction unit can weight bias reduction based on geographical distribution. This makes it possible to perform more appropriate bias reduction by considering the geographical distribution of the data.

[0058] The prediction unit can optimize its prediction algorithm by referring to past data during the prediction process. For example, the prediction unit adjusts the prediction algorithm based on past data. For example, the prediction unit can analyze trends in past data and reflect them in the prediction. For example, the prediction unit can improve the accuracy of the prediction by referring to past data. Thus, the accuracy of the prediction can be improved by referring to past data.

[0059] The prediction unit can optimize its prediction algorithm by considering real-time data during prediction. For example, the prediction unit adjusts the prediction algorithm based on real-time data. For example, the prediction unit can analyze trends in real-time data and reflect them in the prediction. For example, the prediction unit can improve the accuracy of the prediction by referring to real-time data. Thus, by considering real-time data, the accuracy of the prediction can be improved.

[0060] The prediction unit can weight the prediction data based on the data submission date during the prediction process. For example, the prediction unit can prioritize the inclusion of the most recent data in the prediction. For example, the prediction unit can postpone the inclusion of older data. For example, the prediction unit can weight the prediction data according to the submission date. By weighting the prediction data based on the data submission date, the latest data can be prioritized for inclusion in the prediction.

[0061] The data utilization unit can improve the accuracy of data utilization by considering the interrelationships between data. For example, the data utilization unit can analyze the correlations between data and reflect them in data utilization. For example, the data utilization unit can set data utilization methods by considering the interdependence of data. For example, the data utilization unit can weight data utilization based on the interrelationships between data. In this way, the accuracy of data utilization can be improved by considering the interrelationships between data.

[0062] The Data Utilization Department can utilize data while considering the attribute information of the data submitter. For example, the Data Utilization Department can adjust the data utilization method based on the submitter's position and job description. For example, the Data Utilization Department can utilize data while considering the submitter's years of experience and skill level. For example, the Data Utilization Department can utilize data while referring to the submitter's past evaluation history. By considering the attribute information of the data submitter, more appropriate data utilization becomes possible.

[0063] The data utilization unit can perform data utilization while considering the geographical distribution of the data. For example, the data utilization unit can integrate geographically dispersed data and reflect it in data utilization. For example, the data utilization unit can set data utilization methods while considering the characteristics of each region. For example, the data utilization unit can weight data utilization based on geographical distribution. As a result, more appropriate data utilization becomes possible by considering the geographical distribution of the data.

[0064] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit adjusts the learning algorithm based on past learning data. For example, the learning unit can analyze trends in past learning data and reflect them in the learning process. For example, the learning unit can improve the accuracy of learning by referring to past learning data. Thus, the accuracy of learning can be improved by referring to past learning data.

[0065] The learning unit can optimize the learning algorithm by considering real-time data during training. For example, the learning unit adjusts the learning algorithm based on real-time data. For example, the learning unit can analyze trends in real-time data and reflect them in the learning process. For example, the learning unit can improve the accuracy of learning by referring to real-time data. Thus, by considering real-time data, the accuracy of learning can be improved.

[0066] The learning unit can weight the training data based on when the data was submitted. For example, the learning unit can prioritize incorporating the most recent data into the training. For example, the learning unit can postpone incorporating older data. For example, the learning unit can weight the training data according to the submission date. This allows the learning unit to prioritize incorporating the most recent data into the training by weighting the training data based on the submission date.

[0067] The integrated analysis unit can improve the accuracy of integrated analysis by considering the interrelationships between data. For example, the integrated analysis unit can analyze the correlations between data and reflect them in the integrated analysis. For example, the integrated analysis unit can set the integrated analysis method by considering the interdependence of data. For example, the integrated analysis unit can weight the integrated analysis based on the interrelationships of data. In this way, the accuracy of integrated analysis can be improved by considering the interrelationships of data.

[0068] The Integrated Analysis Department can perform integrated analysis while considering the attribute information of data submitters. For example, the Integrated Analysis Department can adjust the integrated analysis method based on the submitter's position and job description. For example, the Integrated Analysis Department can perform integrated analysis while considering the submitter's years of experience and skill level. For example, the Integrated Analysis Department can perform integrated analysis while referring to the submitter's past evaluation history. This makes it possible to perform more appropriate integrated analysis by considering the attribute information of data submitters.

[0069] The integrated analysis unit can perform integrated analysis while considering the geographical distribution of the data. For example, the integrated analysis unit can integrate geographically dispersed data and reflect it in the integrated analysis. For example, the integrated analysis unit can set the integrated analysis method considering the characteristics of each region. For example, the integrated analysis unit can weight the integrated analysis based on geographical distribution. This makes it possible to perform more appropriate integrated analysis by considering the geographical distribution of the data.

[0070] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0071] The data collection unit can integrate data from different departments within the company, thereby improving the accuracy of data collection. For example, the unit can link the databases of each department to collect data in an integrated manner. For example, the unit can standardize data formats across departments to ensure data integrity. For example, the unit can establish inter-departmental data sharing protocols to achieve efficient data collection. This allows for improved data collection accuracy by integrating data from different departments within the company.

[0072] The data collection unit can prioritize the collection of data related to specific projects or tasks during data collection. For example, the data collection unit can prioritize the collection of relevant data according to the progress of a project. For example, the data collection unit can prioritize the collection of necessary data based on the importance of a task. For example, the data collection unit can adjust the timing of data collection to match project deadlines. This allows for the efficient collection of necessary data by prioritizing the collection of data related to specific projects or tasks.

[0073] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, the data collection unit can prioritize the collection of relevant data based on the user's current location. For example, the data collection unit can collect highly relevant data by referring to the user's travel history. For example, the data collection unit can prioritize the collection of necessary data based on the user's geographical activity range. As a result, by prioritizing the collection of highly relevant data while considering the user's geographical location information, necessary data can be collected efficiently.

[0074] The data collection unit can analyze users' social media activity and collect relevant data during data collection. For example, the data collection unit can analyze the content of users' social media posts and collect relevant data. For example, the data collection unit can collect necessary data by considering users' social media friendships. For example, the data collection unit can adjust the timing of data collection based on the frequency of users' social media activity. This allows for the efficient collection of relevant data by analyzing users' social media activity.

[0075] The analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit can perform a detailed analysis on high-importance data, and a simplified analysis on low-importance data. The analysis unit can also allocate analysis resources according to the importance of the data. This allows for efficient analysis by adjusting the level of detail based on the importance of the data.

[0076] The analysis unit can apply different analysis algorithms depending on the data category during analysis. For example, the analysis unit can apply a natural language processing algorithm to text data. For example, the analysis unit can apply an image recognition algorithm to image data. For example, the analysis unit can apply a speech recognition algorithm to audio data. By applying different analysis algorithms depending on the data category, the accuracy of the analysis can be improved.

[0077] The following briefly describes the processing flow for example form 1.

[0078] Step 1: The collection unit collects data. The collection unit collects data from various internal data sources, for example. The collection unit can collect text data, numerical data, image data, etc. The collection unit can use sensors, databases, APIs, etc., as means of data collection. The collection unit can set the data collection frequency and collect data regularly, for example. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the data using, for example, AI. The analysis unit can use, for example, machine learning algorithms, deep learning algorithms, etc., as analytical algorithms. The analysis unit can perform tasks such as pattern detection, anomaly detection, and prediction for the purpose of data analysis. Step 3: The evaluation unit performs an evaluation based on the analysis results obtained by the analysis unit. The evaluation unit may use AI for evaluation, for example. The evaluation unit may use performance indicators, behavioral indicators, feedback indicators, etc., as evaluation criteria. The evaluation unit may use scoring, ranking, clustering, etc., as evaluation methods. Step 4: The delivery unit provides the evaluation results obtained by the evaluation unit. The delivery unit provides the evaluation results using, for example, AI. The delivery unit can use, for example, dashboards, reports, notifications, etc., as delivery methods. The delivery unit can set, for example, delivery timing such as real time, periodic, event-driven, etc.

[0079] (Example of form 2) The 360-degree evaluation system according to an embodiment of the present invention is an innovative system that combines generative AI and multimodal AI. This system integrates and analyzes diverse internal data sources to achieve comprehensive and fair evaluations that go beyond the limitations of conventional personnel evaluations. Specifically, it consists of the following steps: First, an AI agent integrates and analyzes diverse internal data sources in real time. Next, the generative AI and multimodal AI work together to continuously evaluate daily communication and task performance. This evaluation has the function of detecting and mitigating unconscious bias. It also predicts future performance and potential challenges, supporting proactive talent development. Furthermore, the AI ​​automatically generates multifaceted evaluation indicators and analyzes 360-degree feedback. This eliminates subjectivity in evaluations and improves the efficiency of the evaluation process. Objective evaluations are possible even under remote work conditions without difficulty. For example, evaluation accuracy can be improved by utilizing user behavior data. The AI ​​agent continuously learns and self-improves in response to environmental changes. It also comprehensively analyzes text, voice, and image data, automating everything from goal setting to execution. This creates a workplace environment where all employees are fairly evaluated and their contributions are properly recognized. It democratizes evaluation, improves engagement, maximizes performance, and fosters innovation. Thus, the 360-degree evaluation system enables comprehensive and fair employee evaluation.

[0080] The 360-degree evaluation system according to the embodiment comprises a collection unit, an analysis unit, an evaluation unit, and a provision unit. The collection unit collects data. The collection unit collects data from various data sources within the company, for example. The collection unit can collect text data, numerical data, image data, etc. The collection unit can use sensors, databases, APIs, etc., as means of data collection. The collection unit can set the data collection frequency and collect data periodically, for example. The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the data using AI, for example. The analysis unit can use machine learning algorithms, deep learning algorithms, etc., as analysis algorithms. The analysis unit can perform tasks such as pattern detection, anomaly detection, and prediction for data analysis purposes, for example. The evaluation unit performs evaluations based on the analysis results obtained by the analysis unit. The evaluation unit performs evaluations using AI, for example. The evaluation unit can use performance indicators, behavioral indicators, feedback indicators, etc., as evaluation criteria. The evaluation unit can use scoring, ranking, clustering, etc., as evaluation methods. The provisioning unit provides the evaluation results obtained by the evaluation unit. The provisioning unit provides the evaluation results using, for example, AI. The provisioning unit can use, for example, a dashboard, reports, notifications, etc., as a means of provision. The provisioning unit can set, for example, the timing of provision to be real time, periodic, event-driven, etc. As a result, the 360-degree evaluation system according to the embodiment can efficiently collect, analyze, evaluate, and provide data.

[0081] The data collection unit collects data. For example, the data collection unit collects data from various internal data sources. Specifically, it can collect data from internal HR databases, business systems, email servers, chat tools, project management tools, etc. The data collection unit can collect text data, numerical data, image data, etc. Text data includes employee work reports, feedback comments, and email content. Numerical data includes performance indicators, attendance data, and project progress. Image data includes employee profile pictures and meeting screenshots. The data collection unit can use sensors, databases, APIs, etc., as data collection methods. Sensors include environmental sensors in the office and sensors in the attendance management system. Databases include internal SQL databases and NoSQL databases. APIs include APIs for retrieving data from external cloud services and internal microservices. The data collection unit can set the data collection frequency and collect data regularly. Collection frequencies can be set to real-time, hourly, daily, or weekly. This allows the data collection unit to efficiently collect necessary data from various internal data sources and build a data infrastructure for the entire system.

[0082] The analysis department analyzes the data collected by the data collection department. For example, the analysis department uses AI to analyze data. Specifically, it can analyze text data using natural language processing (NLP) technology to perform sentiment analysis and topic modeling. For numerical data, it can perform statistical analysis and regression analysis to detect performance trends and outliers. For image data, it can perform face recognition and object detection using image recognition technology. The analysis department can use various analytical algorithms, such as machine learning algorithms and deep learning algorithms. Machine learning algorithms include decision trees, random forests, and support vector machines (SVMs). Deep learning algorithms include convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer models. For example, the analysis department can perform tasks such as pattern detection, anomaly detection, and prediction. Pattern detection allows for understanding employee behavior patterns and trends in work performance. Anomaly detection allows for early detection of unusual behavior or performance declines. Prediction allows for forecasting future performance and employee turnover risk. This allows the analysis department to analyze the collected data from multiple perspectives and provide insights into the entire system.

[0083] The evaluation department conducts evaluations based on the analysis results obtained by the analysis department. The evaluation department uses AI, for example, to perform evaluations. Specifically, it can use machine learning models to score employee performance and create rankings. The evaluation department can use performance indicators, behavioral indicators, and feedback indicators as evaluation criteria, for example. Performance indicators include the degree of achievement of performance targets, project completion rates, and sales figures. Behavioral indicators include attendance rates, frequency of meeting participation, and frequency of communication within the team. Feedback indicators include feedback comments from supervisors and colleagues, and evaluations from customers. The evaluation department can use scoring, ranking, and clustering as evaluation methods, for example. Scoring allows for the quantification of employee performance based on each indicator and the calculation of an overall score. Ranking allows for the ranking of employees based on their scores, enabling the identification of high-performing employees. Clustering allows for the classification of employees into specific groups, grouping employees with common characteristics. This enables the evaluation department to conduct objective and fair evaluations based on the analysis results and appropriately assess employee performance.

[0084] The service provider will provide the evaluation results obtained by the evaluation provider. The service provider will provide evaluation results using, for example, AI. Specifically, it will provide a dashboard to visually display evaluation results in an easy-to-understand manner and display evaluation information that is updated in real time. The service provider can use dashboards, reports, notifications, etc., as means of delivery. As a dashboard, it can display evaluation scores, rankings, and performance trends for each employee in graphs and charts. As a report, it can provide regularly generated evaluation reports in PDF or Excel format, allowing for detailed review of evaluation results. As a notification, it can notify evaluation results and important feedback via email or chat tools, enabling rapid information sharing. The service provider can set the timing of delivery, for example, to be real-time, periodic, or event-driven. In real-time, evaluation results can be provided immediately via dashboards and notifications as soon as they are updated. In periodic, evaluation reports can be generated and provided at regular intervals, such as weekly or monthly. In event-driven mode, evaluation results can be provided in response to specific events (for example, project completion or end of quarter). This allows the service provider to provide evaluation results quickly and effectively, providing employees and managers with information to take appropriate action.

[0085] The bias reduction unit can detect and mitigate unconscious bias. For example, the bias reduction unit can use AI to detect unconscious bias. The bias reduction unit can detect specific types of bias, such as gender bias and age bias. The bias reduction unit can mitigate bias using, for example, a bias reduction algorithm. The bias reduction unit can use, for example, an index to evaluate the degree of bias reduction as a method for measuring the effectiveness of the reduction. This allows for improved fairness in evaluation by detecting and mitigating unconscious bias.

[0086] The prediction unit can predict future performance and potential challenges. For example, the prediction unit can use AI to predict future performance. For example, the prediction unit can use regression models, time series models, deep learning models, etc., as prediction models. For example, the prediction unit can use sales, customer satisfaction, productivity, etc., as performance indicators to be predicted. For example, the prediction unit can use risk assessment algorithms to predict potential challenges. For example, the prediction unit can use anomaly detection algorithms as a method for identifying challenges. This allows for proactive talent development support by predicting future performance and potential challenges.

[0087] The Data Utilization Department can utilize user behavior data. For example, the Data Utilization Department can analyze user behavior data using AI. Specific types of user behavior data that the Data Utilization Department can use include website click data and app usage data. For example, data collection methods include log data collection, sensor usage, and API utilization. The Data Utilization Department can, for example, use algorithms to improve evaluation accuracy based on user behavior data. This allows for improved evaluation accuracy through the utilization of user behavior data.

[0088] The learning unit can continuously learn and improve itself. For example, the learning unit can continuously learn using AI. The learning unit can use various learning algorithms, such as online learning algorithms and reinforcement learning algorithms. The learning unit can set the frequency of learning data updates to real-time, periodic, event-driven, etc. The learning unit can build a feedback loop for self-improvement and optimize the algorithm based on the learning results. This allows the system's accuracy to improve through continuous learning and self-improvement.

[0089] The integrated analysis unit can comprehensively analyze text, audio, and image data. For example, the integrated analysis unit can analyze text data using AI. For example, the integrated analysis unit can analyze text data using natural language processing algorithms. For example, the integrated analysis unit can analyze audio data using speech recognition algorithms. For example, the integrated analysis unit can analyze image data using image recognition algorithms. For example, the integrated analysis unit can use data fusion technology as a method of data integration. This allows for improved evaluation accuracy by comprehensively analyzing text, audio, and image data.

[0090] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, the data collection unit estimates the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the data collection unit can reduce the frequency of data collection to lessen the user's burden. For example, if the user is relaxed, the data collection unit can increase the frequency of data collection to collect more detailed data. For example, if the user is concentrating, the data collection unit can adjust the timing of data collection to avoid interrupting their work. This reduces the user's burden by adjusting the timing of data collection based on their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0091] The data collection unit can integrate data from different departments within the company, thereby improving the accuracy of data collection. For example, the unit can link the databases of each department to collect data in an integrated manner. For example, the unit can standardize data formats across departments to ensure data integrity. For example, the unit can establish inter-departmental data sharing protocols to achieve efficient data collection. This allows for improved data collection accuracy by integrating data from different departments within the company.

[0092] The data collection unit can prioritize the collection of data related to specific projects or tasks during data collection. For example, the data collection unit can prioritize the collection of relevant data according to the progress of a project. For example, the data collection unit can prioritize the collection of necessary data based on the importance of a task. For example, the data collection unit can adjust the timing of data collection to match project deadlines. This allows for the efficient collection of necessary data by prioritizing the collection of data related to specific projects or tasks.

[0093] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated emotions. For example, the data collection unit might use an emotion estimation algorithm to estimate the user's emotions. For example, if the user is stressed, the data collection unit might postpone the collection of less important data. For example, if the user is relaxed, the data collection unit might prioritize the collection of detailed data. For example, if the user is focused, the data collection unit might prioritize the collection of data relevant to the task. This allows for the priority collection of important data by determining the priority of data to collect based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0094] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, the data collection unit can prioritize the collection of relevant data based on the user's current location. For example, the data collection unit can collect highly relevant data by referring to the user's travel history. For example, the data collection unit can prioritize the collection of necessary data based on the user's geographical activity range. As a result, by prioritizing the collection of highly relevant data while considering the user's geographical location information, necessary data can be collected efficiently.

[0095] The data collection unit can analyze users' social media activity and collect relevant data during data collection. For example, the data collection unit can analyze the content of users' social media posts and collect relevant data. For example, the data collection unit can collect necessary data by considering users' social media friendships. For example, the data collection unit can adjust the timing of data collection based on the frequency of users' social media activity. This allows for the efficient collection of relevant data by analyzing users' social media activity.

[0096] The analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated emotions. For example, the analysis unit can estimate the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the analysis unit can apply a simple analysis method. For example, if the user is relaxed, the analysis unit can apply a detailed analysis method. For example, if the user is focused, the analysis unit can apply a complex analysis method. This reduces the user's burden by adjusting the analysis method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0097] The analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit can perform a detailed analysis on high-importance data, and a simplified analysis on low-importance data. The analysis unit can also allocate analysis resources according to the importance of the data. This allows for efficient analysis by adjusting the level of detail based on the importance of the data.

[0098] The analysis unit can apply different analysis algorithms depending on the data category during analysis. For example, the analysis unit can apply a natural language processing algorithm to text data. For example, the analysis unit can apply an image recognition algorithm to image data. For example, the analysis unit can apply a speech recognition algorithm to audio data. By applying different analysis algorithms depending on the data category, the accuracy of the analysis can be improved.

[0099] The analysis unit can estimate the user's emotions and determine the priority of analyses based on the estimated emotions. For example, the analysis unit might use an emotion estimation algorithm to estimate the user's emotions. For example, if the user is stressed, the analysis unit can postpone less important analyses. For example, if the user is relaxed, the analysis unit can prioritize detailed analyses. For example, if the user is focused, the analysis unit can prioritize analyses related to the task at hand. This allows for prioritizing important analyses by determining the priority of analyses based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0100] The analysis department can prioritize analyses based on when the data was submitted. For example, the analysis department can prioritize analyzing the most recent data. For example, the analysis department can postpone analyzing older data. For example, the analysis department can allocate analysis resources according to the submission date. This allows for prioritizing the analysis of the most recent data by determining the analysis priority based on the data submission date.

[0101] The analysis unit can adjust the order of analysis based on the relevance of the data. For example, the analysis unit can prioritize analyzing highly relevant data. For example, the analysis unit can postpone analyzing less relevant data. For example, the analysis unit can allocate analysis resources according to the relevance of the data. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the data.

[0102] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated emotions. For example, the evaluation unit estimates the user's emotions using an emotion estimation algorithm. For example, the evaluation unit can relax the evaluation criteria if the user is stressed. For example, the evaluation unit can tighten the evaluation criteria if the user is relaxed. For example, the evaluation unit can set detailed evaluation criteria if the user is focused. This allows for more appropriate evaluations by adjusting the evaluation criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0103] The evaluation unit can improve the accuracy of its evaluations by considering the interrelationships between data. For example, the evaluation unit can analyze the correlations between data and reflect them in the evaluation. For example, the evaluation unit can set evaluation criteria by considering the interdependence of data. For example, the evaluation unit can weight the evaluation based on the interrelationships of data. In this way, the accuracy of the evaluation can be improved by considering the interrelationships of data.

[0104] The evaluation department can consider the attribute information of data submitters when conducting evaluations. For example, the evaluation department can adjust evaluation criteria based on the submitter's position and job responsibilities. For example, the evaluation department can consider the submitter's years of experience and skill level when conducting evaluations. For example, the evaluation department can refer to the submitter's past evaluation history when conducting evaluations. This allows for more appropriate evaluations by considering the attribute information of data submitters.

[0105] The evaluation unit can estimate the user's emotions and adjust the order in which evaluation results are displayed based on the estimated emotions. For example, the evaluation unit estimates the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the evaluation unit can display positive evaluation results first. For example, if the user is relaxed, the evaluation unit can display detailed evaluation results in a sequential manner. For example, if the user is focused, the evaluation unit can prioritize displaying important evaluation results. This reduces the user's burden by adjusting the order in which evaluation results are displayed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0106] The evaluation unit can perform evaluations while considering the geographical distribution of the data. For example, the evaluation unit can integrate geographically dispersed data and reflect it in the evaluation. For example, the evaluation unit can set evaluation criteria while considering the characteristics of each region. For example, the evaluation unit can weight the evaluation based on geographical distribution. This makes it possible to perform more appropriate evaluations by considering the geographical distribution of the data.

[0107] The evaluation unit can improve the accuracy of its evaluation by referring to relevant literature during the evaluation process. For example, the evaluation unit can refer to relevant literature and set evaluation criteria. For example, the evaluation unit can reflect the findings of relevant literature in its evaluation. For example, the evaluation unit can weight the evaluation based on relevant literature. In this way, the accuracy of the evaluation can be improved by referring to relevant literature for the data.

[0108] The service provider can estimate the user's emotions and adjust the presentation of the information provided based on the estimated emotions. For example, the service provider can estimate the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the service provider can provide simple and easily understandable information. For example, if the user is relaxed, the service provider can provide detailed information. For example, if the user is focused, the service provider can highlight important information. This reduces the user's burden by adjusting the presentation of information based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0109] The information provider can adjust the level of detail provided based on the importance of the information at the time of provision. For example, the provider can provide detailed explanations for highly important information. For example, the provider can provide simplified explanations for less important information. For example, the provider can allocate resources for provision according to the importance of the information. This allows for efficient information provision by adjusting the level of detail based on the importance of the information.

[0110] The information provider can apply different information provision algorithms depending on the information category at the time of provision. For example, the provider can apply a natural language generation algorithm to text information. For example, the provider can apply an image generation algorithm to image information. For example, the provider can apply a speech generation algorithm to speech information. By applying different information provision algorithms depending on the information category, the accuracy of the provision can be improved.

[0111] The service provider can estimate the user's emotions and prioritize the information it provides based on those emotions. For example, the service provider might use an emotion estimation algorithm to estimate the user's emotions. For instance, if the user is stressed, the service provider might postpone providing less important information. For instance, if the user is relaxed, the service provider might prioritize providing detailed information. For instance, if the user is focused, the service provider might prioritize providing work-related information. This allows for the prioritization of important information by determining the priority of information based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0112] The information provider can determine the priority of information provision based on when the information was submitted. For example, the provider can prioritize providing the most recent information. For example, the provider can postpone providing older information. For example, the provider can allocate resources for provision according to the submission date. This allows for the provision of the most recent information by prioritizing information provision based on when it was submitted.

[0113] The information provider can adjust the order of information delivery based on its relevance. For example, the provider can prioritize providing highly relevant information. For example, the provider can postpone providing less relevant information. For example, the provider can allocate resources for delivery according to the relevance of the information. This allows for efficient information delivery by adjusting the order of delivery based on the relevance of the information.

[0114] The bias reduction unit can estimate the user's emotions and adjust the bias reduction method based on the estimated user emotions. For example, the bias reduction unit estimates the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the bias reduction unit can simplify the bias reduction method. For example, if the user is relaxed, the bias reduction unit can apply a more detailed bias reduction method. For example, if the user is focused, the bias reduction unit can apply a more complex bias reduction method. This reduces the user's burden by adjusting the bias reduction method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0115] The bias reduction unit can improve the accuracy of bias reduction by considering the interrelationships between data. For example, the bias reduction unit can analyze the correlations between data and reflect them in the bias reduction. For example, the bias reduction unit can set the bias reduction method by considering the interdependence of data. For example, the bias reduction unit can weight the bias reduction based on the interrelationships of data. In this way, the accuracy of bias reduction can be improved by considering the interrelationships of data.

[0116] The bias reduction unit can perform bias reduction while considering the attribute information of the data submitter. For example, the bias reduction unit can adjust the bias reduction method based on the submitter's position and job description. For example, the bias reduction unit can perform bias reduction while considering the submitter's years of experience and skill level. For example, the bias reduction unit can perform bias reduction while referring to the submitter's past evaluation history. This makes it possible to perform more appropriate bias reduction by considering the attribute information of the data submitter.

[0117] The bias reduction unit can estimate the user's emotions and determine the priority of bias reduction based on the estimated user emotions. For example, the bias reduction unit estimates the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the bias reduction unit can postpone less important bias reductions. For example, if the user is relaxed, the bias reduction unit can prioritize detailed bias reductions. For example, if the user is focused, the bias reduction unit can prioritize work-related bias reductions. This allows for prioritizing important bias reductions by determining the priority of bias reductions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0118] The bias reduction unit can perform bias reduction while considering the geographical distribution of the data. For example, the bias reduction unit can integrate geographically dispersed data and reflect this in the bias reduction. For example, the bias reduction unit can set bias reduction methods while considering the characteristics of each region. For example, the bias reduction unit can weight bias reduction based on geographical distribution. This makes it possible to perform more appropriate bias reduction by considering the geographical distribution of the data.

[0119] The prediction unit can estimate the user's emotions and adjust its prediction method based on the estimated emotions. For example, the prediction unit estimates the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the prediction unit can apply a simple prediction method. For example, if the user is relaxed, the prediction unit can apply a more detailed prediction method. For example, if the user is focused, the prediction unit can apply a more complex prediction method. This allows for a reduction in user burden by adjusting the prediction method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0120] The prediction unit can optimize its prediction algorithm by referring to past data during the prediction process. For example, the prediction unit adjusts the prediction algorithm based on past data. For example, the prediction unit can analyze trends in past data and reflect them in the prediction. For example, the prediction unit can improve the accuracy of the prediction by referring to past data. Thus, the accuracy of the prediction can be improved by referring to past data.

[0121] The prediction unit can optimize its prediction algorithm by considering real-time data during prediction. For example, the prediction unit adjusts the prediction algorithm based on real-time data. For example, the prediction unit can analyze trends in real-time data and reflect them in the prediction. For example, the prediction unit can improve the accuracy of the prediction by referring to real-time data. Thus, by considering real-time data, the accuracy of the prediction can be improved.

[0122] The prediction unit can estimate the user's emotions and determine the priority of predictions based on the estimated emotions. For example, the prediction unit estimates the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the prediction unit can postpone less important predictions. For example, if the user is relaxed, the prediction unit can prioritize detailed predictions. For example, if the user is focused, the prediction unit can prioritize predictions related to the task at hand. This allows for prioritizing important predictions by determining the priority of predictions based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0123] The prediction unit can weight the prediction data based on the data submission date during the prediction process. For example, the prediction unit can prioritize the inclusion of the most recent data in the prediction. For example, the prediction unit can postpone the inclusion of older data. For example, the prediction unit can weight the prediction data according to the submission date. By weighting the prediction data based on the data submission date, the latest data can be prioritized for inclusion in the prediction.

[0124] The data utilization unit can estimate the user's emotions and adjust the data utilization method based on the estimated user emotions. For example, the data utilization unit estimates the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the data utilization unit can apply a simple data utilization method. For example, if the user is relaxed, the data utilization unit can apply a detailed data utilization method. For example, if the user is focused, the data utilization unit can apply a complex data utilization method. This reduces the user's burden by adjusting the data utilization method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0125] The data utilization unit can improve the accuracy of data utilization by considering the interrelationships between data. For example, the data utilization unit can analyze the correlations between data and reflect them in data utilization. For example, the data utilization unit can set data utilization methods by considering the interdependence of data. For example, the data utilization unit can weight data utilization based on the interrelationships between data. In this way, the accuracy of data utilization can be improved by considering the interrelationships between data.

[0126] The Data Utilization Department can utilize data while considering the attribute information of the data submitter. For example, the Data Utilization Department can adjust the data utilization method based on the submitter's position and job description. For example, the Data Utilization Department can utilize data while considering the submitter's years of experience and skill level. For example, the Data Utilization Department can utilize data while referring to the submitter's past evaluation history. By considering the attribute information of the data submitter, more appropriate data utilization becomes possible.

[0127] The data utilization unit can estimate the user's emotions and determine the priority of data utilization based on the estimated user emotions. For example, the data utilization unit estimates the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the data utilization unit can postpone less important data utilization. For example, if the user is relaxed, the data utilization unit can prioritize detailed data utilization. For example, if the user is focused, the data utilization unit can prioritize data utilization related to the task. This allows for prioritizing important data utilization by determining the priority of data utilization based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0128] The data utilization unit can perform data utilization while considering the geographical distribution of the data. For example, the data utilization unit can integrate geographically dispersed data and reflect it in data utilization. For example, the data utilization unit can set data utilization methods while considering the characteristics of each region. For example, the data utilization unit can weight data utilization based on geographical distribution. As a result, more appropriate data utilization becomes possible by considering the geographical distribution of the data.

[0129] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, the learning unit can estimate the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the learning unit can select simple training data. For example, if the user is relaxed, the learning unit can select detailed training data. For example, if the user is focused, the learning unit can select complex training data. This reduces the user's burden by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0130] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit adjusts the learning algorithm based on past learning data. For example, the learning unit can analyze trends in past learning data and reflect them in the learning process. For example, the learning unit can improve the accuracy of learning by referring to past learning data. Thus, the accuracy of learning can be improved by referring to past learning data.

[0131] The learning unit can optimize the learning algorithm by considering real-time data during training. For example, the learning unit adjusts the learning algorithm based on real-time data. For example, the learning unit can analyze trends in real-time data and reflect them in the learning process. For example, the learning unit can improve the accuracy of learning by referring to real-time data. Thus, by considering real-time data, the accuracy of learning can be improved.

[0132] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, the learning unit estimates the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the learning unit can reduce the learning frequency. For example, if the user is relaxed, the learning unit can increase the learning frequency. For example, if the user is concentrating, the learning unit can adjust the learning frequency. This reduces the user's burden by adjusting the learning frequency based on their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0133] The learning unit can weight the training data based on when the data was submitted. For example, the learning unit can prioritize incorporating the most recent data into the training. For example, the learning unit can postpone incorporating older data. For example, the learning unit can weight the training data according to the submission date. This allows the learning unit to prioritize incorporating the most recent data into the training by weighting the training data based on the submission date.

[0134] The integrated analysis unit can estimate the user's emotions and adjust the integrated analysis method based on the estimated user emotions. For example, the integrated analysis unit estimates the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the integrated analysis unit can apply a simple integrated analysis method. For example, if the user is relaxed, the integrated analysis unit can apply a detailed integrated analysis method. For example, if the user is focused, the integrated analysis unit can apply a complex integrated analysis method. This reduces the user's burden by adjusting the integrated analysis method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0135] The integrated analysis unit can improve the accuracy of integrated analysis by considering the interrelationships between data. For example, the integrated analysis unit can analyze the correlations between data and reflect them in the integrated analysis. For example, the integrated analysis unit can set the integrated analysis method by considering the interdependence of data. For example, the integrated analysis unit can weight the integrated analysis based on the interrelationships of data. In this way, the accuracy of integrated analysis can be improved by considering the interrelationships of data.

[0136] The Integrated Analysis Department can perform integrated analysis while considering the attribute information of data submitters. For example, the Integrated Analysis Department can adjust the integrated analysis method based on the submitter's position and job description. For example, the Integrated Analysis Department can perform integrated analysis while considering the submitter's years of experience and skill level. For example, the Integrated Analysis Department can perform integrated analysis while referring to the submitter's past evaluation history. This makes it possible to perform more appropriate integrated analysis by considering the attribute information of data submitters.

[0137] The integrated analysis unit can estimate the user's emotions and determine the priority of integrated analyses based on the estimated user emotions. For example, the integrated analysis unit estimates the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the integrated analysis unit can postpone less important integrated analyses. For example, if the user is relaxed, the integrated analysis unit can prioritize detailed integrated analyses. For example, if the user is focused, the integrated analysis unit can prioritize work-related integrated analyses. This allows for prioritizing important integrated analyses based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0138] The integrated analysis unit can perform integrated analysis while considering the geographical distribution of the data. For example, the integrated analysis unit can integrate geographically dispersed data and reflect it in the integrated analysis. For example, the integrated analysis unit can set the integrated analysis method considering the characteristics of each region. For example, the integrated analysis unit can weight the integrated analysis based on geographical distribution. This makes it possible to perform more appropriate integrated analysis by considering the geographical distribution of the data.

[0139] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0140] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, the data collection unit estimates the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the data collection unit can reduce the frequency of data collection to alleviate the user's burden. For example, if the user is relaxed, the data collection unit can increase the frequency of data collection to collect more detailed data. For example, if the user is concentrating, the data collection unit can adjust the timing of data collection to avoid interrupting their work. In this way, the user's burden can be reduced by adjusting the timing of data collection based on the user's emotions.

[0141] The data collection unit can integrate data from different departments within the company, thereby improving the accuracy of data collection. For example, the unit can link the databases of each department to collect data in an integrated manner. For example, the unit can standardize data formats across departments to ensure data integrity. For example, the unit can establish inter-departmental data sharing protocols to achieve efficient data collection. This allows for improved data collection accuracy by integrating data from different departments within the company.

[0142] The data collection unit can prioritize the collection of data related to specific projects or tasks during data collection. For example, the data collection unit can prioritize the collection of relevant data according to the progress of a project. For example, the data collection unit can prioritize the collection of necessary data based on the importance of a task. For example, the data collection unit can adjust the timing of data collection to match project deadlines. This allows for the efficient collection of necessary data by prioritizing the collection of data related to specific projects or tasks.

[0143] The data collection unit can estimate the user's emotions and prioritize the data to collect based on those emotions. For example, the data collection unit might use an emotion estimation algorithm to estimate the user's emotions. For example, if the user is stressed, the data collection unit can postpone the collection of less important data. For example, if the user is relaxed, the data collection unit can prioritize the collection of detailed data. For example, if the user is focused, the data collection unit can prioritize the collection of data relevant to the task. This allows for the priority collection of important data by prioritizing the data to be collected based on the user's emotions.

[0144] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, the data collection unit can prioritize the collection of relevant data based on the user's current location. For example, the data collection unit can collect highly relevant data by referring to the user's travel history. For example, the data collection unit can prioritize the collection of necessary data based on the user's geographical activity range. As a result, by prioritizing the collection of highly relevant data while considering the user's geographical location information, necessary data can be collected efficiently.

[0145] The data collection unit can analyze users' social media activity and collect relevant data during data collection. For example, the data collection unit can analyze the content of users' social media posts and collect relevant data. For example, the data collection unit can collect necessary data by considering users' social media friendships. For example, the data collection unit can adjust the timing of data collection based on the frequency of users' social media activity. This allows for the efficient collection of relevant data by analyzing users' social media activity.

[0146] The analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated emotions. For example, the analysis unit can estimate the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the analysis unit can apply a simple analysis method. For example, if the user is relaxed, the analysis unit can apply a detailed analysis method. For example, if the user is focused, the analysis unit can apply a complex analysis method. In this way, the user's burden can be reduced by adjusting the analysis method based on the user's emotions.

[0147] The analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit can perform a detailed analysis on high-importance data, and a simplified analysis on low-importance data. The analysis unit can also allocate analysis resources according to the importance of the data. This allows for efficient analysis by adjusting the level of detail based on the importance of the data.

[0148] The analysis unit can apply different analysis algorithms depending on the data category during analysis. For example, the analysis unit can apply a natural language processing algorithm to text data. For example, the analysis unit can apply an image recognition algorithm to image data. For example, the analysis unit can apply a speech recognition algorithm to audio data. By applying different analysis algorithms depending on the data category, the accuracy of the analysis can be improved.

[0149] The analysis unit can estimate the user's emotions and determine the priority of analyses based on those estimated emotions. For example, the analysis unit can estimate the user's emotions using an emotion estimation algorithm. For example, if the user is stressed, the analysis unit can postpone less important analyses. For example, if the user is relaxed, the analysis unit can prioritize detailed analyses. For example, if the user is focused, the analysis unit can prioritize analyses related to the task at hand. In this way, by determining the priority of analyses based on the user's emotions, important analyses can be prioritized.

[0150] The following briefly describes the processing flow for example form 2.

[0151] Step 1: The collection unit collects data. The collection unit collects data from various internal data sources, for example. The collection unit can collect text data, numerical data, image data, etc. The collection unit can use sensors, databases, APIs, etc., as means of data collection. The collection unit can set the data collection frequency and collect data regularly, for example. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the data using, for example, AI. The analysis unit can use, for example, machine learning algorithms, deep learning algorithms, etc., as analytical algorithms. The analysis unit can perform tasks such as pattern detection, anomaly detection, and prediction for the purpose of data analysis. Step 3: The evaluation unit performs an evaluation based on the analysis results obtained by the analysis unit. The evaluation unit may use AI for evaluation, for example. The evaluation unit may use performance indicators, behavioral indicators, feedback indicators, etc., as evaluation criteria. The evaluation unit may use scoring, ranking, clustering, etc., as evaluation methods. Step 4: The delivery unit provides the evaluation results obtained by the evaluation unit. The delivery unit provides the evaluation results using, for example, AI. The delivery unit can use, for example, dashboards, reports, notifications, etc., as delivery methods. The delivery unit can set, for example, delivery timing such as real time, periodic, event-driven, etc.

[0152] 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.

[0153] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0154] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0155] Each of the multiple elements described above, including the data collection unit, analysis unit, evaluation unit, provision unit, bias reduction unit, prediction unit, data utilization unit, learning unit, and integrated analysis unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data collection unit collects data using the sensors and database of the smart device 14 and analyzes it using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data using AI. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and performs an evaluation based on the analysis results. The provision unit is implemented, for example, by the control unit 46A of the smart device 14 and provides the evaluation results as a dashboard or report. The bias reduction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and detects and reduces unconscious bias. The prediction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and predicts future performance and potential challenges. The data utilization unit is implemented, for example, by the control unit 46A of the smart device 14, and improves evaluation accuracy by utilizing user behavior data. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and continuously learns and improves itself. The integrated analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and comprehensively analyzes text, voice, and image data. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0156] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0157] 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.

[0158] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0159] 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.

[0160] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0161] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0162] 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.

[0163] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0164] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0165] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0166] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0167] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0168] 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.

[0169] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0170] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0171] Each of the multiple elements described above, including the data collection unit, analysis unit, evaluation unit, provision unit, bias reduction unit, prediction unit, data utilization unit, learning unit, and integrated analysis unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit collects data using the sensors and database of the smart glasses 214 and analyzes it using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data using AI. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and performs an evaluation based on the analysis results. The provision unit is implemented, for example, by the control unit 46A of the smart glasses 214 and provides the evaluation results as a dashboard or report. The bias reduction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and detects and reduces unconscious bias. The prediction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and predicts future performance and potential challenges. The data utilization unit is implemented, for example, by the control unit 46A of the smart glasses 214, and improves evaluation accuracy by utilizing user behavior data. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and continuously learns and improves itself. The integrated analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and comprehensively analyzes text, voice, and image data. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0172] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0173] 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.

[0174] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0175] 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.

[0176] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0177] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0178] 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.

[0179] 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.

[0180] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0181] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0182] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0183] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0184] 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.

[0185] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0186] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0187] Each of the multiple elements described above, including the data collection unit, analysis unit, evaluation unit, provision unit, bias reduction unit, prediction unit, data utilization unit, learning unit, and integrated analysis unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data collection unit collects data using the sensors and database of the headset terminal 314 and analyzes it using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data using AI. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and performs an evaluation based on the analysis results. The provision unit is implemented, for example, by the control unit 46A of the headset terminal 314 and provides the evaluation results as a dashboard or report. The bias reduction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and detects and reduces unconscious bias. The prediction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and predicts future performance and potential challenges. The data utilization unit is implemented, for example, by the control unit 46A of the headset terminal 314, and improves evaluation accuracy by utilizing user behavior data. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and continuously learns and improves itself. The integrated analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and comprehensively analyzes text, voice, and image data. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0188] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0189] 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.

[0190] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0191] 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.

[0192] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0193] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0194] 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.

[0195] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0196] 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.

[0197] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0198] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0199] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0200] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0201] 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.

[0202] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0203] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0204] Each of the multiple elements described above, including the collection unit, analysis unit, evaluation unit, provision unit, bias reduction unit, prediction unit, data utilization unit, learning unit, and integrated analysis unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects data using the sensors and database of the robot 414 and analyzes it using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data using AI. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and performs an evaluation based on the analysis results. The provision unit is implemented, for example, by the control unit 46A of the robot 414 and provides the evaluation results as a dashboard or report. The bias reduction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and detects and reduces unconscious bias. The prediction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and predicts future performance and potential challenges. The data utilization unit is implemented, for example, by the control unit 46A of the robot 414, and improves evaluation accuracy by utilizing user behavior data. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and continuously learns and improves itself. The integrated analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and comprehensively analyzes text, voice, and image data. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0205] 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.

[0206] Figure 9 shows the 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.

[0207] 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.

[0208] 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.

[0209] 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, and motorcycles, 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 based, for example, 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.

[0210] 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."

[0211] 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.

[0212] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0221] 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 other things 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.

[0222] 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.

[0223] (Note 1) A data collection unit that collects data, An analysis unit analyzes the data collected by the aforementioned collection unit, An evaluation unit that performs an evaluation based on the analysis results obtained by the aforementioned analysis unit, The system includes a providing unit that provides evaluation results obtained by the evaluation unit. A system characterized by the following features. (Note 2) Equipped with a bias reduction unit that detects and mitigates unconscious bias. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a forecasting unit that predicts future performance and potential challenges. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a data utilization unit that uses user behavior data. The system described in Appendix 1, characterized by the features described herein. (Note 5) It has a learning section for continuous learning and self-improvement. The system described in Appendix 1, characterized by the features described herein. (Note 6) It features an integrated analysis unit that comprehensively analyzes text, audio, and image data. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Integrating data from different departments within the company to improve the accuracy of data collection. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting data, prioritize the collection of data related to specific projects or tasks. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting data, the system prioritizes the collection of highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is During data collection, the system analyzes users' social media activity and collects relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit is It estimates the user's emotions and adjusts the analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit is During analysis, adjust the level of detail based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit is During analysis, different analytical algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit is We estimate the user's emotions and prioritize the analysis based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit is During analysis, prioritize the analysis based on when the data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit is During analysis, adjust the order of analysis based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The evaluation unit described above, It estimates the user's emotions and adjusts the evaluation criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The evaluation unit described above, During evaluation, consider the interrelationships between data to improve the accuracy of the evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 21) The evaluation unit described above, During the evaluation process, the attribute information of the data submitter will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The evaluation unit described above, It estimates the user's emotions and adjusts the order in which evaluation results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The evaluation unit described above, During the evaluation, the geographical distribution of the data will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The evaluation unit described above, During evaluation, we refer to relevant literature to improve the accuracy of the evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, It estimates the user's emotions and adjusts how the information provided is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing information, adjust the level of detail based on its importance. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing information, different delivery algorithms are applied depending on the category of information. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, It estimates the user's emotions and prioritizes the information provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, When providing information, we will determine the priority of provision based on when the information was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When providing information, the order of provision will be adjusted based on the relevance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 31) The bias reduction unit is, We estimate the user's emotions and adjust the bias reduction method based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The bias reduction unit is, When reducing bias, consider the interrelationships between data to improve the accuracy of bias reduction. The system described in Appendix 2, characterized by the features described herein. (Note 33) The bias reduction unit is, When reducing bias, the attribute information of the data submitter is taken into consideration. The system described in Appendix 2, characterized by the features described herein. (Note 34) The bias reduction unit is, The system estimates user emotions and determines bias reduction priorities based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 35) The bias reduction unit is, When reducing bias, the geographical distribution of the data should be taken into consideration. The system described in Appendix 2, characterized by the features described herein. (Note 36) The prediction unit, It estimates the user's emotions and adjusts the prediction method based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 37) The prediction unit, When making predictions, the prediction algorithm is optimized by referring to historical data. The system described in Appendix 3, characterized by the features described herein. (Note 38) The prediction unit, When making predictions, optimize the prediction algorithm by taking real-time data into consideration. The system described in Appendix 3, characterized by the features described herein. (Note 39) The prediction unit, It estimates the user's emotions and determines the priority of predictions based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The prediction unit, During the prediction process, the predicted data is weighted based on when the data was submitted. The system described in Appendix 3, characterized by the features described herein. (Note 41) The aforementioned data utilization unit is We estimate user emotions and adjust how we use the data based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned data utilization unit is When utilizing data, consider the interrelationships between data to improve the accuracy of data utilization. The system described in Appendix 4, characterized by the features described herein. (Note 43) The aforementioned data utilization unit is When utilizing data, perform data utilization while considering the attribute information of the data submitter. The system according to Supplementary Note 4, characterized by this. (Supplementary Note 44) The data utilization unit Estimates the user's emotion and determines the priority order of data utilization based on the estimated user's emotion. The system according to Supplementary Note 4, characterized by this. (Supplementary Note 45) The data utilization unit When utilizing data, perform data utilization while considering the geographical distribution of the data. The system according to Supplementary Note 4, characterized by this. (Supplementary Note 46) The learning unit Estimates the user's emotion and selects learning data based on the estimated user's emotion. The system according to Supplementary Note 5, characterized by this. (Supplementary Note 47) The learning unit When learning, optimize the learning algorithm by referring to past learning data. The system according to Supplementary Note 5, characterized by this. (Supplementary Note 48) The learning unit When learning, optimize the learning algorithm while considering real-time data. The system according to Supplementary Note 5, characterized by this. (Supplementary Note 49) The learning unit Estimates the user's emotion and adjusts the learning frequency based on the estimated user's emotion. The system according to Supplementary Note 5, characterized by this. (Supplementary Note 50) The learning unit When learning, perform weighting of learning data based on the data submission time. The system according to Supplementary Note 5, characterized by this. (Supplementary Note 51) The integrated analysis unit Estimates the user's emotion and adjusts the integrated analysis method based on the estimated user's emotion. The system described in Appendix 6, characterized by the features described herein. (Note 52) The aforementioned integrated analysis unit is When performing integrated analysis, consider the interrelationships between data to improve the accuracy of the integrated analysis. The system described in Appendix 6, characterized by the features described herein. (Note 53) The aforementioned integrated analysis unit is When performing integrated analysis, the attribute information of the data submitters should be taken into consideration. The system described in Appendix 6, characterized by the features described herein. (Note 54) The aforementioned integrated analysis unit is We estimate user sentiment and prioritize integrated analysis based on the estimated user sentiment. The system described in Appendix 6, characterized by the features described herein. (Note 55) The aforementioned integrated analysis unit is When performing integrated analysis, consider the geographical distribution of the data. The system described in Appendix 6, characterized by the features described herein. [Explanation of symbols]

[0224] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A data collection unit that collects data, An analysis unit analyzes the data collected by the aforementioned collection unit, An evaluation unit that performs an evaluation based on the analysis results obtained by the aforementioned analysis unit, The system includes a providing unit that provides evaluation results obtained by the evaluation unit. A system characterized by the following features.

2. It is equipped with a bias reduction unit that detects and mitigates unconscious bias. The system according to feature 1.

3. It includes a forecasting unit that predicts future performance and potential challenges. The system according to feature 1.

4. It includes a data utilization unit that uses user behavior data. The system according to feature 1.

5. It has a learning section for continuous learning and self-improvement. The system according to feature 1.

6. It features an integrated analysis unit that comprehensively analyzes text, audio, and image data. The system according to feature 1.

7. The aforementioned collection unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is Integrating data from different departments within the company to improve the accuracy of data collection. The system according to feature 1.

9. The aforementioned collection unit is When collecting data, prioritize the collection of data related to specific projects or tasks. The system according to feature 1.

Images