system

Abstract

We provide the system. [Solution] A means of collecting multiple business data using data communication means, A method for analyzing collected business data to infer emotional states, A means of predicting job satisfaction based on inferred emotional states and related work information, A means of generating feedback based on predicted job satisfaction, A means for transmitting the generated feedback to individual user terminals, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes 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 conventional engagement surveys, it has been difficult to accurately grasp the job satisfaction of employees, and only superficial feedback has been obtained, failing to sufficiently contribute to the improvement of employees' work and the support of their mental health. Also, it has been pointed out that the surveys are becoming monotonous and formal, imposing a burden on employees. Therefore, there is a need for more accurate satisfaction measurement and the provision of practical feedback.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system characterized by collecting multiple business data using data communication means and analyzing that data to infer the emotional state of employees. Furthermore, a process is introduced to predict job satisfaction based on the inferred emotional state and to generate and provide feedback according to the result. This makes it possible to quickly provide specific and useful feedback tailored to the individual circumstances of each employee.

[0006] "Data communication means" refers to a system element that uses communication technologies and protocols to collect multiple business data sets.

[0007] "Business data" refers to information related to employees' daily work activities, and specifically includes message data and workload data.

[0008] "Analysis" is a technical process of analyzing collected data to extract specific information.

[0009] "Emotional state" refers to the classification of emotions that indicate an employee's mental health and psychological response.

[0010] "Prediction" is a method of inferring future states or outcomes based on information obtained through analysis.

[0011] "Feedback" is information that provides employees with specific areas for improvement and guidelines for action based on predicted results.

[0012] "User terminals" refer to electronic devices such as computers and mobile devices used by individual employees. [Brief explanation of the drawing]

[0013] [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. <00…080> [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention provides a system that effectively analyzes and predicts employees' emotional states and job satisfaction based on their work data. The following describes embodiments of this system.

[0035] This system is primarily composed of servers, which are connected to multiple terminals via a network. The servers collect business data from employee terminals using data communication methods. This business data includes emails and chat messages sent and received during business communication, which are periodically transferred to the server.

[0036] The server analyzes the collected message data to infer the emotional state of employees. This process employs algorithms that use natural language processing (NLP) and machine learning models to identify emotions within the text. Specifically, emotional labels such as positive, negative, and neutral are automatically assigned.

[0037] Next, the server combines customer emotional states with work information to predict job satisfaction. This prediction is made using statistical modeling or machine learning models, taking into account past data and work patterns.

[0038] Based on predicted job satisfaction, the server generates feedback for employees. This feedback includes specific advice for improving their mood and suggestions for increasing work efficiency. The generated feedback is sent to the customer's terminal, allowing the user to use it to improve their own work.

[0039] For example, if user A frequently expresses negative emotions in their daily work, the server analyzes this information and performs further analysis. If the prediction phase determines that user A is under a high workload, it provides specific advice as feedback, such as "review your workload and take measures to manage stress." In this way, the system contributes to improving employee satisfaction and corporate productivity.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server automatically collects work data from employee terminals via the network. This data includes emails and chat messages, and text information related to work activities is continuously accumulated.

[0043] Step 2:

[0044] The server preprocesses the collected data, removing personal and confidential information. Additionally, text data is formatted and converted into a state suitable for analysis.

[0045] Step 3:

[0046] The server uses natural language processing techniques to analyze sentiment from pre-processed text data. Specifically, it performs word vectorization and tokenization, and assigns sentiment labels such as positive, negative, and neutral to each text.

[0047] Step 4:

[0048] Based on the analysis results, the server aggregates and analyzes each employee's emotional state and integrates it with related data such as job content and workload.

[0049] Step 5:

[0050] The server uses integrated data as input to predict employee job satisfaction using statistical models and machine learning algorithms. The predictive models also take into account comparisons with historical data and trend analysis.

[0051] Step 6:

[0052] The server generates personalized feedback for each employee based on their predicted job satisfaction results. This feedback includes specific advice for improving their mood.

[0053] Step 7:

[0054] The server sends the generated feedback to the employee's device. Users can then review it and take action to improve their work processes or manage their emotions.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In today's work environment, accurately understanding employees' emotional states and how those states affect job satisfaction is challenging. Providing accurate feedback based on this understanding is crucial for improving employee motivation and work efficiency. Traditional methods have failed to adequately analyze the relationship between emotional states and work performance, making it difficult for improvement suggestions to yield tangible results. Therefore, a new approach is needed to address this challenge.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for acquiring multiple pieces of information data using data communication means, means for analyzing the acquired information data to infer an emotional state, and means for predicting activity satisfaction based on the inferred emotional state and related information. This makes it possible to accurately analyze the emotional state of employees and provide feedback based on that analysis to improve job satisfaction.

[0060] "Data communication means" refers to a method or technology for transferring information data between a server and a user device.

[0061] "Information data" refers to all data generated in the course of business operations, including emails and chat messages related to employees' work, and data on workload.

[0062] "Emotional state" refers to emotional states such as positive, negative, and neutral, derived from text analyzed using natural language processing technology.

[0063] "Activity satisfaction" is an indicator of employee satisfaction with their work, and is predicted based on emotional states and work-related information.

[0064] "Feedback" refers to advice and improvement suggestions provided to employees based on their predicted level of satisfaction with their activities.

[0065] A "generative AI model" is a machine learning model that helps analyze data and provide insights, and is used to infer employee sentiment and generate feedback.

[0066] This invention provides a system for efficiently analyzing and predicting employees' emotional states and activity satisfaction during their work. This system mainly consists of a server and multiple terminals.

[0067] The server is responsible for acquiring information data from each terminal using data communication methods. This information data includes emails and chat messages used by employees for work. By having the server regularly receive this information data, it is possible to accurately reflect the work situation.

[0068] The server utilizes natural language processing and machine learning technologies in analyzing information data. Specifically, a generative AI model infers emotional states from text data. This model assigns emotional labels such as positive, negative, and neutral to the information data. For example, the message "I'm glad this project was completed successfully" is analyzed as having a positive emotion.

[0069] Next, the server predicts activity satisfaction based on the inferred emotional state. Here, past work data and emotional patterns are combined and evaluated using statistical modeling and machine learning. Through this analysis, the server generates specific feedback that contributes to improving organizational productivity.

[0070] The generated feedback is sent to the employee's device. Based on this feedback, the user can identify areas for improvement in their work and take appropriate action.

[0071] As a concrete example, consider a case where a user frequently exhibits negative emotions during work. The server, based on this pattern, infers that the user is in a high-load work environment and provides specific feedback such as, "Please consider adjusting your workload and managing your stress."

[0072] An example of a prompt used as input to the generative AI model is: "Analyze the user's email and chat history, identify the correlation between the frequency of negative emotions and activity satisfaction, and provide specific advice for improvement."

[0073] Thus, the system of the present invention achieves improved employee satisfaction and increased efficiency throughout the organization.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server periodically receives information data from each terminal using data communication methods. This information data includes emails and chat messages. The input consists of business communication data sent from each terminal, which is output and stored on the server.

[0077] Step 2:

[0078] The server analyzes the received information data using natural language processing (NLP) techniques. This analysis uses a generative AI model to infer emotional states from text. The input is the information data acquired in step 1, and the server uses this to classify the emotions in the data as positive, negative, or neutral, and outputs the data with emotional labels.

[0079] Step 3:

[0080] The server predicts activity satisfaction based on informational data with emotion labels. This step also takes into account past data and emotion patterns. The input consists of emotion-labeled data and historical work data, which the server analyzes using a machine learning model to output a predicted activity satisfaction level.

[0081] Step 4:

[0082] The server generates feedback based on the predicted activity satisfaction. This feedback includes specific suggestions, such as individual advice and suggestions for improvement. The input is the activity satisfaction prediction result from step 3, and the server creates the feedback based on it and outputs it as a text message.

[0083] Step 5:

[0084] The server sends the generated feedback to each employee's terminal. The input is the feedback created in step 4, which the server forwards to the user's terminal and outputs in a format that the user can review and utilize.

[0085] (Application Example 1)

[0086] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] In today's workplace, it is essential to understand employees' emotional states and job satisfaction in real time and provide appropriate feedback. However, traditional methods make it difficult to accurately grasp individual emotional states, and in particular, they fail to provide prompt support to employees whose mental health deteriorates due to workload. Therefore, there is a need for a system that monitors emotional states and provides improvement suggestions in real time in the real world.

[0088] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0089] In this invention, the server includes means for collecting multiple pieces of work information using information transmission technology, means for analyzing the collected work information to infer the emotional state, means for predicting work satisfaction based on the inferred emotional state and related work-related information, and means for presenting the created improvement proposals on a visual display device. This makes it possible to monitor the emotional state of employees in real time and provide feedback.

[0090] "Information transmission technology" refers to methods for efficiently sending and receiving information and data between multiple devices.

[0091] "Business information" refers to all information, including data and messages related to employees' work activities.

[0092] "Emotional status" is an indicator that shows an employee's current emotional response or state.

[0093] "Business-related information" refers to background information necessary for carrying out business operations and data associated with business processes.

[0094] "Job satisfaction" is an indicator that shows the level of satisfaction and fulfillment employees feel when performing their work.

[0095] "Improvement suggestions" refer to proposals aimed at improving work efficiency or emotional state, based on the detected situation.

[0096] An "information processing terminal" refers to a digital device used by users to receive and process information.

[0097] A "visual display device" refers to a hardware device used to present information to users visually.

[0098] The system implementing this invention has the function of providing real-time feedback by collecting employee work information, inferring their emotional state, and predicting their job satisfaction. The server collects work information from information processing terminals used by employees using information transmission technology. The collected information includes message information and workload information. The server utilizes natural language processing to analyze this data and infer the emotional state.

[0099] The server integrates analyzed emotional states with related work-related information and predicts work satisfaction using a machine learning model. This model can utilize frameworks such as TENSORFLOW® and PyTorch. Based on the predicted work satisfaction, the server generates improvement suggestions and presents them to the user in real time through smart glasses, which act as a visual display device.

[0100] For example, if an employee exhibits a high stress level during work and this is analyzed as a negative emotion, the server visually displays a suggestion to "take a deep breath and relax" on the employee's glasses. Because the user receives this suggestion in real time, they can immediately implement stress reduction measures.

[0101] Examples of prompt statements include the following:

[0102] Based on the following text data, predict the emotional state: "I'm a little tired today, but I managed to finish work."

[0103] By using this prompt, the generative AI model can appropriately analyze the emotional state and provide accurate feedback to the user.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The server collects business information from information processing terminals used by employees. This business information includes message information and workload information. It receives text data sent from the terminals as input and stores it in the database.

[0107] Step 2:

[0108] The server analyzes the collected business information. This analysis uses natural language processing algorithms to infer emotional states from text data. The stored text data is used as input, and emotional labels (positive, negative, neutral) are assigned using NLP techniques. The analysis results are then sent to a generating AI model as output.

[0109] Step 3:

[0110] The server integrates emotional states and related information, and uses a machine learning model to predict job satisfaction. The input uses the inferred emotional data and related job information described above. Statistical modeling is applied to obtain the predicted job satisfaction as output.

[0111] Step 4:

[0112] The server generates improvement suggestions based on predicted employee satisfaction. Using the prediction results as input, a generative AI model is applied to generate suggestion texts, outputting specific advice in text format.

[0113] Step 5:

[0114] The server sends the generated improvement suggestions to an information processing terminal and instructs it to display them on a visual display device. The terminal then outputs the suggestions received from the server as a notification to the user's smart glasses, presenting them visually. This system allows the user to receive improvement suggestions in real time.

[0115] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0116] This invention is a system that analyzes business data collected via data communication means, infers the user's emotional state, predicts job satisfaction based on that inference, and provides feedback to the user. In particular, by combining it with an emotion engine, it becomes possible to recognize the user's emotions more accurately and in real time.

[0117] The system primarily consists of servers, with an emotion engine integrated into them. The servers collect various business data from user terminals via the network. This includes email and chat message data, workload data, and visual and audio data captured by cameras and microphones operating on the terminals. Based on this data, the emotion engine analyzes the user's current emotions. Because real-time emotion recognition is possible, it offers the advantage of consistently providing up-to-date information.

[0118] The server receives the analysis results from the emotion engine and uses natural language processing algorithms and machine learning models to predict job satisfaction. This prediction is based on the user's past work history and emotional tendencies, and a customized model is used for each individual user.

[0119] Next, the server generates specific feedback to provide to the user based on the predicted job satisfaction. This feedback includes suggestions for improvement tailored to the user's emotional state and advice aimed at conditioning their work, and is sent to the user's terminal.

[0120] For example, if User B frequently smiles during work-related communication, the server detects this in real time through its emotion engine. Once a positive emotional state is detected, the server analyzes the contributing factors and identifies elements that improve satisfaction. As a result, User B receives specific feedback on how to apply these positive factors to other tasks.

[0121] Through the system described above, users will be able to deepen their understanding of their own emotions and work, and make more effective improvements to their work processes.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The server collects work data from the user's terminal. The terminal is configured to transfer message data and workload data to the server, and this also includes visual and audio data acquired from the camera and microphone.

[0125] Step 2:

[0126] The server filters the collected data from a personal information protection standpoint and prepares it in a format necessary for analysis. This process includes data cleaning and format conversion.

[0127] Step 3:

[0128] The server activates an emotion engine, performing facial expression analysis from visual data and tone analysis from audio data to analyze the user's emotional state in real time. This allows the user's mental tendencies to be understood.

[0129] Step 4:

[0130] The server uses natural language processing to analyze message data and identify the emotions expressed in the text. This allows it to infer the user's overall emotional state from their communication content, facial expressions, and voice.

[0131] Step 5:

[0132] The server uses emotional information provided by the emotion engine, along with the user's past work data and work history, to predict integrated job satisfaction. Machine learning models are used for this prediction.

[0133] Step 6:

[0134] The server generates personalized feedback for users based on their predicted job satisfaction. This feedback includes advice to stabilize emotions and specific suggestions for improving work performance.

[0135] Step 7:

[0136] The server sends the generated feedback to the user's device. Users can review this feedback and implement the recommended improvements to enhance their work efficiency and satisfaction.

[0137] (Example 2)

[0138] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0139] In today's work environment, workplace stress and satisfaction often directly impact individual productivity. However, many current systems struggle to assess individual employees' emotions and psychological states in real time and provide corresponding feedback. Furthermore, predicting job satisfaction based on employees' emotional states and suggesting improvement measures is not sufficiently automated. As a result, improving workplace satisfaction and effective work processes are hindered.

[0140] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0141] In this invention, the server includes means for collecting business data using data communication means, means for analyzing data including visual and auditory information from the collected data to estimate emotional states in real time, and means for predicting individually customized job satisfaction using a generative model. This makes it possible to predict job satisfaction in real time based on the user's emotional state and propose improvement measures.

[0142] "Data communication means" refers to technologies or devices for sending and receiving data between multiple devices, and plays a role in collecting business data via a network.

[0143] "Business data" refers to all information related to activities conducted within an organization, including message data, workload data, visual information, and audio information.

[0144] "Visual information" refers to video data acquired using devices such as cameras, and is used to analyze the user's facial expressions and actions.

[0145] "Audio information" refers to sound data acquired using devices such as microphones, and is used to analyze the user's tone and emotional state.

[0146] "Means for inferring emotional states" refers to technologies or devices that use natural language processing algorithms or speech recognition technologies to analyze emotions from a user's utterances or voice and determine their emotional state.

[0147] A "generative model" is a mathematical or computational structure that uses historical data and other factors to make specific predictions or generate data based on machine learning algorithms.

[0148] "Natural language generation technology" is a technology that uses machines to generate text based on natural language, and is used to provide feedback in a format that users can understand.

[0149] "Means of generating feedback" refers to technologies or devices for generating information or suggestions to provide to a user based on their emotional state or predicted job satisfaction.

[0150] This invention is a system that analyzes a user's emotional state in their work environment in real time, uses the results to predict their job satisfaction, and provides the user with specific feedback.

[0151] The user terminal uses a camera and microphone to collect visual and auditory information, such as the user's facial expressions and voice. Furthermore, it transmits message data via email and chat, as well as workload data, to the server via data communication.

[0152] The server receives multiple business data sets and performs real-time sentiment analysis using an integrated sentiment engine. This sentiment engine uses natural language processing algorithms and speech recognition technology to infer emotions from the user's speech content and tone of voice.

[0153] Based on the analyzed sentiment data and accumulated work information, the server uses a machine learning-based generative model to predict individually customized job satisfaction levels.

[0154] Next, the server uses natural language generation technology to generate feedback that includes specific improvement suggestions and advice regarding the predicted satisfaction level, and sends it to the user terminal via the network. The user terminal displays this feedback to the user, supporting effective business improvement.

[0155] For example, if a user is smiling frequently during work, the server analyzes the video data from the camera in real time to confirm a positive emotional state. Based on this, the server identifies the cause and generates feedback such as, "Let's try applying this positive attitude you've shown in your recent work to other projects."

[0156] Examples of prompts for the generative AI model include, "Please create a report summarizing the user's current emotional state and its impact." In this way, users can understand how their emotions and behaviors affect their work and use this information to make improvements.

[0157] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0158] Step 1:

[0159] The user terminal collects information from the user's email, chat, camera, microphone, etc. Input data includes text message data, visual information, and audio information. The terminal transmits this data to the server via the network. As a preprocessing step, the data is formatted into the required format.

[0160] Step 2:

[0161] The server receives business data sent from the terminal. Input data includes formatted text, visual data, and audio data. The server feeds this into its emotion engine, applying natural language processing algorithms and speech recognition technologies to infer the emotional state. The output is data representing the user's real-time emotional state.

[0162] Step 3:

[0163] The server uses the output data from the emotion engine to feed into a generative AI model. The input data includes emotional states and work history. Based on this, the server applies a machine learning algorithm to predict the user's job satisfaction. The output is numerical data indicating the predicted job satisfaction.

[0164] Step 4:

[0165] The server uses natural language generation technology to generate feedback based on predicted job satisfaction and emotional state data. Input data includes satisfaction scores and emotional data to derive specific suggestions. Output is a text message containing specific advice for the user.

[0166] Step 5:

[0167] The server sends the generated feedback to the user's terminal via the network. The terminal receives this feedback and presents it to the user. This allows the user to learn about specific improvement suggestions based on their emotional state and job satisfaction.

[0168] (Application Example 2)

[0169] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0170] In conventional store operations, it has been difficult to grasp employees' emotional states in real time and provide appropriate feedback based on that information. This could negatively impact service quality and employee satisfaction. This invention aims to improve customer service and employee satisfaction by efficiently analyzing employees' emotions during work and providing appropriate feedback.

[0171] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0172] In this invention, the server includes means for collecting multiple activity data using data communication technology, means for analyzing the collected activity data to infer the emotional state, means for predicting satisfaction based on the inferred emotional state and related activity information, and means for recognizing the emotional state in real time using acquired visual and audio data to support customer service operations. This makes it possible to instantly grasp the emotional state of employees and provide appropriate feedback.

[0173] "Data communication technology" refers to the technology used to send and receive data between information processing devices.

[0174] "Activity data" refers to all information generated during work, including workload and communication content.

[0175] "Emotional state" refers to the user's psychological reactions and emotions.

[0176] "Satisfaction level" refers to the sense of fulfillment and accomplishment that users feel towards their work.

[0177] "Visual and audio data" refers to image data and audio information acquired through cameras and microphones.

[0178] "Real-time recognition" refers to the process of immediately analyzing the content of acquired information and obtaining results.

[0179] "Customer service" refers to the work of providing goods and services to customers in a store.

[0180] "Feedback" refers to information and advice provided to users, with the aim of improving operations and increasing user satisfaction.

[0181] This invention is implemented in a system that recognizes the emotional state of employees in a store in real time and provides appropriate feedback. The system includes a server and information processing devices such as smart glasses. The server collects activity data from these information processing devices using data communication technology. This includes visual and audio data, acquired using the cameras and microphones of the smart glasses.

[0182] The collected data is sent to an emotion engine running on the server. This emotion engine analyzes visual and audio data and uses machine learning algorithms to infer the emotional state of employees. Specifically, advanced emotion recognition is possible by using Python, TensorFlow, and OpenCV. In this process, positive facial expressions such as smiles are detected from the collected visual data, and the tone of voice is analyzed from the audio data to determine whether the current emotion is "positive."

[0183] The server also uses the inferred emotional state to predict the employee's satisfaction level. Based on this predicted satisfaction level, the server generates feedback and sends it to the information processing unit. This allows employees to receive appropriate feedback tailored to their emotions, which can help them improve their work and increase their satisfaction. For example, a POS system screen might display advice such as, "Keep up the good work."

[0184] An example of a prompt would be, "If the employee's current mood is positive, please provide feedback on how they can maintain that mood."

[0185] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0186] Step 1:

[0187] The device collects visual and audio data using the smart glasses' camera and microphone. The device verifies that the visual data includes features such as facial expressions, and the audio data includes features such as voice tone. This data is transmitted to the server in real time.

[0188] Step 2:

[0189] The server inputs the received visual and audio data into the emotion engine. The emotion engine uses a machine learning algorithm to infer the emotional state based on the received data. As part of the data processing, it analyzes whether or not there is a smile from the visual data and the tone of voice from the audio data. As output, it generates the inferred emotional state (e.g., "positive").

[0190] Step 3:

[0191] The server predicts satisfaction levels based on emotional states and related work information. It uses natural language processing algorithms and generative AI models to compute data from previously outputted emotional states and past work history to obtain predicted satisfaction levels (e.g., "high satisfaction").

[0192] Step 4:

[0193] The server generates feedback using prompts via a generative AI model, based on the predicted satisfaction level. It takes satisfaction level and emotional state as input and outputs feedback such as "Keep up the good work."

[0194] Step 5:

[0195] The server sends the generated feedback to the terminal. The terminal then presents this feedback to the user via the information processing device's display and audio. This allows the user to utilize real-time emotional feedback in their work.

[0196] 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.

[0197] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0198] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0199] [Second Embodiment]

[0200] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0201] 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.

[0202] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0203] 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.

[0204] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0205] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0206] 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.

[0207] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0208] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0209] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0210] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0211] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0212] This invention provides a system that effectively analyzes and predicts employees' emotional states and job satisfaction based on their work data. The following describes embodiments of this system.

[0213] This system is primarily composed of servers, which are connected to multiple terminals via a network. The servers collect business data from employee terminals using data communication methods. This business data includes emails and chat messages sent and received during business communication, which are periodically transferred to the server.

[0214] The server analyzes the collected message data to infer the emotional state of employees. This process employs algorithms that use natural language processing (NLP) and machine learning models to identify emotions within the text. Specifically, emotional labels such as positive, negative, and neutral are automatically assigned.

[0215] Next, the server combines customer emotional states with work information to predict job satisfaction. This prediction is made using statistical modeling or machine learning models, taking into account past data and work patterns.

[0216] Based on predicted job satisfaction, the server generates feedback for employees. This feedback includes specific advice for improving their mood and suggestions for increasing work efficiency. The generated feedback is sent to the customer's terminal, allowing the user to use it to improve their own work.

[0217] For example, if user A frequently expresses negative emotions in their daily work, the server analyzes this information and performs further analysis. If the prediction phase determines that user A is under a high workload, it provides specific advice as feedback, such as "review your workload and take measures to manage stress." In this way, the system contributes to improving employee satisfaction and corporate productivity.

[0218] The following describes the processing flow.

[0219] Step 1:

[0220] The server automatically collects work data from employee terminals via the network. This data includes emails and chat messages, and text information related to work activities is continuously accumulated.

[0221] Step 2:

[0222] The server preprocesses the collected data, removing personal and confidential information. Additionally, text data is formatted and converted into a state suitable for analysis.

[0223] Step 3:

[0224] The server uses natural language processing techniques to analyze sentiment from pre-processed text data. Specifically, it performs word vectorization and tokenization, and assigns sentiment labels such as positive, negative, and neutral to each text.

[0225] Step 4:

[0226] Based on the analysis results, the server aggregates and analyzes each employee's emotional state and integrates it with related data such as job content and workload.

[0227] Step 5:

[0228] The server uses integrated data as input to predict employee job satisfaction using statistical models and machine learning algorithms. The predictive models also take into account comparisons with historical data and trend analysis.

[0229] Step 6:

[0230] The server generates personalized feedback for each employee based on their predicted job satisfaction results. This feedback includes specific advice for improving their mood.

[0231] Step 7:

[0232] The server sends the generated feedback to the employee's device. Users can then review it and take action to improve their work processes or manage their emotions.

[0233] (Example 1)

[0234] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0235] In today's work environment, accurately understanding employees' emotional states and how those states affect job satisfaction is challenging. Providing accurate feedback based on this understanding is crucial for improving employee motivation and work efficiency. Traditional methods have failed to adequately analyze the relationship between emotional states and work performance, making it difficult for improvement suggestions to yield tangible results. Therefore, a new approach is needed to address this challenge.

[0236] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0237] In this invention, the server includes means for acquiring multiple pieces of information data using data communication means, means for analyzing the acquired information data to infer an emotional state, and means for predicting activity satisfaction based on the inferred emotional state and related information. This makes it possible to accurately analyze the emotional state of employees and provide feedback based on that analysis to improve job satisfaction.

[0238] "Data communication means" refers to a method or technology for transferring information data between a server and a user device.

[0239] "Information data" refers to all data generated in the course of business operations, including emails and chat messages related to employees' work, and data on workload.

[0240] "Emotional state" refers to emotional states such as positive, negative, and neutral, derived from text analyzed using natural language processing technology.

[0241] "Activity satisfaction" is an indicator of employee satisfaction with their work, and is predicted based on emotional states and work-related information.

[0242] "Feedback" refers to advice and improvement suggestions provided to employees based on their predicted level of satisfaction with their activities.

[0243] A "generative AI model" is a machine learning model that helps analyze data and provide insights, and is used to infer employee sentiment and generate feedback.

[0244] This invention provides a system for efficiently analyzing and predicting employees' emotional states and activity satisfaction during their work. This system mainly consists of a server and multiple terminals.

[0245] The server is responsible for acquiring information data from each terminal using data communication methods. This information data includes emails and chat messages used by employees for work. By having the server regularly receive this information data, it is possible to accurately reflect the work situation.

[0246] The server utilizes natural language processing and machine learning technologies in analyzing information data. Specifically, a generative AI model infers emotional states from text data. This model assigns emotional labels such as positive, negative, and neutral to the information data. For example, the message "I'm glad this project was completed successfully" is analyzed as having a positive emotion.

[0247] Next, the server predicts activity satisfaction based on the inferred emotional state. Here, past work data and emotional patterns are combined and evaluated using statistical modeling and machine learning. Through this analysis, the server generates specific feedback that contributes to improving organizational productivity.

[0248] The generated feedback is sent to the employee's device. Based on this feedback, the user can identify areas for improvement in their work and take appropriate action.

[0249] As a concrete example, consider a case where a user frequently exhibits negative emotions during work. The server, based on this pattern, infers that the user is in a high-load work environment and provides specific feedback such as, "Please consider adjusting your workload and managing your stress."

[0250] An example of a prompt used as input to the generative AI model is: "Analyze the user's email and chat history, identify the correlation between the frequency of negative emotions and activity satisfaction, and provide specific advice for improvement."

[0251] Thus, the system of the present invention achieves improved employee satisfaction and increased efficiency throughout the organization.

[0252] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0253] Step 1:

[0254] The server periodically receives information data from each terminal using data communication methods. This information data includes emails and chat messages. The input consists of business communication data sent from each terminal, which is output and stored on the server.

[0255] Step 2:

[0256] The server analyzes the received information data using natural language processing (NLP) techniques. This analysis uses a generative AI model to infer emotional states from text. The input is the information data acquired in step 1, and the server uses this to classify the emotions in the data as positive, negative, or neutral, and outputs the data with emotional labels.

[0257] Step 3:

[0258] The server predicts activity satisfaction based on informational data with emotion labels. This step also takes into account past data and emotion patterns. The input consists of emotion-labeled data and historical work data, which the server analyzes using a machine learning model to output a predicted activity satisfaction level.

[0259] Step 4:

[0260] The server generates feedback based on the predicted activity satisfaction. This feedback includes specific suggestions, such as individual advice and suggestions for improvement. The input is the activity satisfaction prediction result from step 3, and the server creates the feedback based on it and outputs it as a text message.

[0261] Step 5:

[0262] The server sends the generated feedback to each employee's terminal. The input is the feedback created in step 4, which the server forwards to the user's terminal and outputs in a format that the user can review and utilize.

[0263] (Application Example 1)

[0264] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0265] In today's workplace, it is essential to understand employees' emotional states and job satisfaction in real time and provide appropriate feedback. However, traditional methods make it difficult to accurately grasp individual emotional states, and in particular, they fail to provide prompt support to employees whose mental health deteriorates due to workload. Therefore, there is a need for a system that monitors emotional states and provides improvement suggestions in real time in the real world.

[0266] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0267] In this invention, the server includes means for collecting multiple pieces of work information using information transmission technology, means for analyzing the collected work information to infer the emotional state, means for predicting work satisfaction based on the inferred emotional state and related work-related information, and means for presenting the created improvement proposals on a visual display device. This makes it possible to monitor the emotional state of employees in real time and provide feedback.

[0268] "Information transmission technology" refers to methods for efficiently sending and receiving information and data between multiple devices.

[0269] "Business information" refers to all information, including data and messages related to employees' work activities.

[0270] "Emotional status" is an indicator that shows an employee's current emotional response or state.

[0271] "Business-related information" refers to background information necessary for carrying out business operations and data associated with business processes.

[0272] "Job satisfaction" is an indicator that shows the level of satisfaction and fulfillment employees feel when performing their work.

[0273] "Improvement suggestions" refer to proposals aimed at improving work efficiency or emotional state, based on the detected situation.

[0274] An "information processing terminal" refers to a digital device used by users to receive and process information.

[0275] A "visual display device" refers to a hardware device used to present information to users visually.

[0276] The system implementing this invention has the function of providing real-time feedback by collecting employee work information, inferring their emotional state, and predicting their job satisfaction. The server collects work information from information processing terminals used by employees using information transmission technology. The collected information includes message information and workload information. The server utilizes natural language processing to analyze this data and infer the emotional state.

[0277] The server integrates analyzed emotional states with related work-related information and uses a machine learning model to predict work satisfaction. This model can utilize frameworks such as TensorFlow and PyTorch. Based on the predicted work satisfaction, the server generates improvement suggestions and presents them to the user in real time through smart glasses, which act as a visual display device.

[0278] For example, if an employee exhibits a high stress level during work and this is analyzed as a negative emotion, the server visually displays a suggestion to "take a deep breath and relax" on the employee's glasses. Because the user receives this suggestion in real time, they can immediately implement stress reduction measures.

[0279] Examples of prompt statements include the following:

[0280] Based on the following text data, predict the emotional state: "I'm a little tired today, but I managed to finish work."

[0281] By using this prompt, the generative AI model can appropriately analyze the emotional state and provide accurate feedback to the user.

[0282] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0283] Step 1:

[0284] The server collects business information from the information processing terminals used by employees. This business information includes message information and business load information. As input, it receives the text data transmitted from the terminal and stores it in the database.

[0285] Step 2:

[0286] The server analyzes the collected business information. For this analysis, it uses natural language processing algorithms to infer the emotional situation from the text data. As input, it uses the stored text data and applies NLP technology to assign sentiment labels (positive, negative, neutral). As output, it sends the analysis results to the generation AI model.

[0287] Step 3:

[0288] The server integrates the emotional situation and related information and predicts the business satisfaction using a machine learning model. For the input, it uses the above-inferred emotional data and related business information. It applies statistical modeling and obtains the predicted business satisfaction as output.

[0289] Step 4:

[0290] Based on the predicted business satisfaction, the server generates improvement suggestions. As input, it uses the prediction results and applies a generation AI model that generates proposal texts to output specific advice in text form.

[0291] Step 5:

[0292] The server sends the generated improvement suggestions to the information processing terminal and instructs it to display them on the visual display device. The terminal outputs the proposal received from the server as a notification to the user's smart glasses and presents it visually. This is a mechanism that allows the user to receive improvement measures in real time.

[0293] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0294] This invention is a system that analyzes business data collected via data communication means, infers the user's emotional state, predicts job satisfaction based on that inference, and provides feedback to the user. In particular, by combining it with an emotion engine, it becomes possible to recognize the user's emotions more accurately and in real time.

[0295] The system primarily consists of servers, with an emotion engine integrated into them. The servers collect various business data from user terminals via the network. This includes email and chat message data, workload data, and visual and audio data captured by cameras and microphones operating on the terminals. Based on this data, the emotion engine analyzes the user's current emotions. Because real-time emotion recognition is possible, it offers the advantage of consistently providing up-to-date information.

[0296] The server receives the analysis results from the emotion engine and uses natural language processing algorithms and machine learning models to predict job satisfaction. This prediction is based on the user's past work history and emotional tendencies, and a customized model is used for each individual user.

[0297] Next, the server generates specific feedback to provide to the user based on the predicted job satisfaction. This feedback includes suggestions for improvement tailored to the user's emotional state and advice aimed at conditioning their work, and is sent to the user's terminal.

[0298] As a specific example, when User B shows a lot of smiling faces during business communication, the server perceives this in real time through the emotion engine. When a positive emotional state is confirmed, the server analyzes the factors and identifies the elements contributing to the improvement of satisfaction. As a result, User B is provided with specific feedback on how to apply the positive factors to other tasks.

[0299] With the above system, users can deepen their understanding of their own emotions and business, and can perform more effective business improvement.

[0300] The following describes the process flow.

[0301] Step 1:

[0302] The server collects business data from the user's terminal. At this time, the terminal is set to transfer message data and business volume data to the server, and further includes visual and audio data obtained from the camera and microphone.

[0303] Step 2:

[0304] The server filters the collected data from the perspective of personal information protection and arranges it in the form required for analysis. At this time, data cleaning and format conversion are performed.

[0305] Step 3:

[0306] The server activates the emotion engine, performs facial expression analysis from visual data and tone analysis from audio data, and analyzes the user's emotional state in real time. In this way, the user's mental tendency is grasped.

[0307] Step 4:

[0308] The server uses natural language processing to analyze message data and identify the emotions expressed in the text. This allows it to infer the user's overall emotional state from their communication content, facial expressions, and voice.

[0309] Step 5:

[0310] The server uses emotional information provided by the emotion engine, along with the user's past work data and work history, to predict integrated job satisfaction. Machine learning models are used for this prediction.

[0311] Step 6:

[0312] The server generates personalized feedback for users based on their predicted job satisfaction. This feedback includes advice to stabilize emotions and specific suggestions for improving work performance.

[0313] Step 7:

[0314] The server sends the generated feedback to the user's device. Users can review this feedback and implement the recommended improvements to enhance their work efficiency and satisfaction.

[0315] (Example 2)

[0316] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0317] In today's work environment, workplace stress and satisfaction often directly impact individual productivity. However, many current systems struggle to assess individual employees' emotions and psychological states in real time and provide corresponding feedback. Furthermore, predicting job satisfaction based on employees' emotional states and suggesting improvement measures is not sufficiently automated. As a result, improving workplace satisfaction and effective work processes are hindered.

[0318] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0319] In this invention, the server includes means for collecting business data using data communication means, means for analyzing data including visual and auditory information from the collected data to estimate emotional states in real time, and means for predicting individually customized job satisfaction using a generative model. This makes it possible to predict job satisfaction in real time based on the user's emotional state and propose improvement measures.

[0320] "Data communication means" refers to technologies or devices for sending and receiving data between multiple devices, and plays a role in collecting business data via a network.

[0321] "Business data" refers to all information related to activities conducted within an organization, including message data, workload data, visual information, and audio information.

[0322] "Visual information" refers to video data acquired using devices such as cameras, and is used to analyze the user's facial expressions and actions.

[0323] "Audio information" refers to sound data acquired using devices such as microphones, and is used to analyze the user's tone and emotional state.

[0324] "Means for inferring emotional states" refers to technologies or devices that use natural language processing algorithms or speech recognition technologies to analyze emotions from a user's utterances or voice and determine their emotional state.

[0325] A "generative model" is a mathematical or computational structure that uses historical data and other factors to make specific predictions or generate data based on machine learning algorithms.

[0326] "Natural language generation technology" is a technology that uses machines to generate text based on natural language, and is used to provide feedback in a format that users can understand.

[0327] "Means of generating feedback" refers to technologies or devices for generating information or suggestions to provide to a user based on their emotional state or predicted job satisfaction.

[0328] This invention is a system that analyzes a user's emotional state in their work environment in real time, uses the results to predict their job satisfaction, and provides the user with specific feedback.

[0329] The user terminal uses a camera and microphone to collect visual and auditory information, such as the user's facial expressions and voice. Furthermore, it transmits message data via email and chat, as well as workload data, to the server via data communication.

[0330] The server receives multiple business data sets and performs real-time sentiment analysis using an integrated sentiment engine. This sentiment engine uses natural language processing algorithms and speech recognition technology to infer emotions from the user's speech content and tone of voice.

[0331] Based on the analyzed sentiment data and accumulated work information, the server uses a machine learning-based generative model to predict individually customized job satisfaction levels.

[0332] Next, the server uses natural language generation technology to generate feedback that includes specific improvement suggestions and advice regarding the predicted satisfaction level, and sends it to the user terminal via the network. The user terminal displays this feedback to the user, supporting effective business improvement.

[0333] For example, if a user is smiling frequently during work, the server analyzes the video data from the camera in real time to confirm a positive emotional state. Based on this, the server identifies the cause and generates feedback such as, "Let's try applying this positive attitude you've shown in your recent work to other projects."

[0334] Examples of prompts for the generative AI model include, "Please create a report summarizing the user's current emotional state and its impact." In this way, users can understand how their emotions and behaviors affect their work and use this information to make improvements.

[0335] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0336] Step 1:

[0337] The user terminal collects information from the user's email, chat, camera, microphone, etc. Input data includes text message data, visual information, and audio information. The terminal transmits this data to the server via the network. As a preprocessing step, the data is formatted into the required format.

[0338] Step 2:

[0339] The server receives business data sent from the terminal. Input data includes formatted text, visual data, and audio data. The server feeds this into its emotion engine, applying natural language processing algorithms and speech recognition technologies to infer the emotional state. The output is data representing the user's real-time emotional state.

[0340] Step 3:

[0341] The server uses the output data from the emotion engine to feed into a generative AI model. The input data includes emotional states and work history. Based on this, the server applies a machine learning algorithm to predict the user's job satisfaction. The output is numerical data indicating the predicted job satisfaction.

[0342] Step 4:

[0343] The server uses natural language generation technology to generate feedback based on predicted job satisfaction and emotional state data. Input data includes satisfaction scores and emotional data to derive specific suggestions. Output is a text message containing specific advice for the user.

[0344] Step 5:

[0345] The server sends the generated feedback to the user's terminal via the network. The terminal receives this feedback and presents it to the user. This allows the user to learn about specific improvement suggestions based on their emotional state and job satisfaction.

[0346] (Application Example 2)

[0347] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0348] In conventional store operations, it has been difficult to grasp employees' emotional states in real time and provide appropriate feedback based on that information. This could negatively impact service quality and employee satisfaction. This invention aims to improve customer service and employee satisfaction by efficiently analyzing employees' emotions during work and providing appropriate feedback.

[0349] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0350] In this invention, the server includes means for collecting multiple activity data using data communication technology, means for analyzing the collected activity data to infer the emotional state, means for predicting satisfaction based on the inferred emotional state and related activity information, and means for recognizing the emotional state in real time using acquired visual and audio data to support customer service operations. This makes it possible to instantly grasp the emotional state of employees and provide appropriate feedback.

[0351] "Data communication technology" refers to the technology used to send and receive data between information processing devices.

[0352] "Activity data" refers to all information generated during work, including workload and communication content.

[0353] "Emotional state" refers to the user's psychological reactions and emotions.

[0354] "Satisfaction level" refers to the sense of fulfillment and accomplishment that users feel towards their work.

[0355] "Visual and audio data" refers to image data and audio information acquired through cameras and microphones.

[0356] "Real-time recognition" refers to the process of immediately analyzing the content of acquired information and obtaining results.

[0357] "Customer service" refers to the work of providing goods and services to customers in a store.

[0358] "Feedback" refers to information and advice provided to users, with the aim of improving operations and increasing user satisfaction.

[0359] This invention is implemented in a system that recognizes the emotional state of employees in a store in real time and provides appropriate feedback. The system includes a server and information processing devices such as smart glasses. The server collects activity data from these information processing devices using data communication technology. This includes visual and audio data, acquired using the cameras and microphones of the smart glasses.

[0360] The collected data is sent to an emotion engine running on the server. This emotion engine analyzes visual and audio data and uses machine learning algorithms to infer the emotional state of employees. Specifically, advanced emotion recognition is possible by using Python, TensorFlow, and OpenCV. In this process, positive facial expressions such as smiles are detected from the collected visual data, and the tone of voice is analyzed from the audio data to determine whether the current emotion is "positive."

[0361] The server also uses the inferred emotional state to predict the employee's satisfaction level. Based on this predicted satisfaction level, the server generates feedback and sends it to the information processing unit. This allows employees to receive appropriate feedback tailored to their emotions, which can help them improve their work and increase their satisfaction. For example, a POS system screen might display advice such as, "Keep up the good work."

[0362] An example of a prompt would be, "If the employee's current mood is positive, please provide feedback on how they can maintain that mood."

[0363] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0364] Step 1:

[0365] The device collects visual and audio data using the smart glasses' camera and microphone. The device verifies that the visual data includes features such as facial expressions, and the audio data includes features such as voice tone. This data is transmitted to the server in real time.

[0366] Step 2:

[0367] The server inputs the received visual and audio data into the emotion engine. The emotion engine uses a machine learning algorithm to infer the emotional state based on the received data. As part of the data processing, it analyzes whether or not there is a smile from the visual data and the tone of voice from the audio data. As output, it generates the inferred emotional state (e.g., "positive").

[0368] Step 3:

[0369] The server predicts satisfaction levels based on emotional states and related work information. It uses natural language processing algorithms and generative AI models to compute data from previously outputted emotional states and past work history to obtain predicted satisfaction levels (e.g., "high satisfaction").

[0370] Step 4:

[0371] The server generates feedback using prompts via a generative AI model, based on the predicted satisfaction level. It takes satisfaction level and emotional state as input and outputs feedback such as "Keep up the good work."

[0372] Step 5:

[0373] The server sends the generated feedback to the terminal. The terminal then presents this feedback to the user via the information processing device's display and audio. This allows the user to utilize real-time emotional feedback in their work.

[0374] 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.

[0375] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0376] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0377] [Third Embodiment]

[0378] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0379] 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.

[0380] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0381] 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.

[0382] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0383] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0384] 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.

[0385] 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.

[0386] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0387] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0388] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0389] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0390] This invention provides a system that effectively analyzes and predicts employees' emotional states and job satisfaction based on their work data. The following describes embodiments of this system.

[0391] This system is primarily composed of servers, which are connected to multiple terminals via a network. The servers collect business data from employee terminals using data communication methods. This business data includes emails and chat messages sent and received during business communication, which are periodically transferred to the server.

[0392] The server analyzes the collected message data to infer the emotional state of employees. This process employs algorithms that use natural language processing (NLP) and machine learning models to identify emotions within the text. Specifically, emotional labels such as positive, negative, and neutral are automatically assigned.

[0393] Next, the server combines customer emotional states with work information to predict job satisfaction. This prediction is made using statistical modeling or machine learning models, taking into account past data and work patterns.

[0394] Based on predicted job satisfaction, the server generates feedback for employees. This feedback includes specific advice for improving their mood and suggestions for increasing work efficiency. The generated feedback is sent to the customer's terminal, allowing the user to use it to improve their own work.

[0395] For example, if user A frequently expresses negative emotions in their daily work, the server analyzes this information and performs further analysis. If the prediction phase determines that user A is under a high workload, it provides specific advice as feedback, such as "review your workload and take measures to manage stress." In this way, the system contributes to improving employee satisfaction and corporate productivity.

[0396] The following describes the processing flow.

[0397] Step 1:

[0398] The server automatically collects work data from employee terminals via the network. This data includes emails and chat messages, and text information related to work activities is continuously accumulated.

[0399] Step 2:

[0400] The server preprocesses the collected data, removing personal and confidential information. Additionally, text data is formatted and converted into a state suitable for analysis.

[0401] Step 3:

[0402] The server uses natural language processing techniques to analyze sentiment from pre-processed text data. Specifically, it performs word vectorization and tokenization, and assigns sentiment labels such as positive, negative, and neutral to each text.

[0403] Step 4:

[0404] Based on the analysis results, the server aggregates and analyzes each employee's emotional state and integrates it with related data such as job content and workload.

[0405] Step 5:

[0406] The server uses integrated data as input to predict employee job satisfaction using statistical models and machine learning algorithms. The predictive models also take into account comparisons with historical data and trend analysis.

[0407] Step 6:

[0408] The server generates personalized feedback for each employee based on their predicted job satisfaction results. This feedback includes specific advice for improving their mood.

[0409] Step 7:

[0410] The server sends the generated feedback to the employee's device. Users can then review it and take action to improve their work processes or manage their emotions.

[0411] (Example 1)

[0412] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0413] In today's work environment, accurately understanding employees' emotional states and how those states affect job satisfaction is challenging. Providing accurate feedback based on this understanding is crucial for improving employee motivation and work efficiency. Traditional methods have failed to adequately analyze the relationship between emotional states and work performance, making it difficult for improvement suggestions to yield tangible results. Therefore, a new approach is needed to address this challenge.

[0414] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0415] In this invention, the server includes means for acquiring multiple pieces of information data using data communication means, means for analyzing the acquired information data to infer an emotional state, and means for predicting activity satisfaction based on the inferred emotional state and related information. This makes it possible to accurately analyze the emotional state of employees and provide feedback based on that analysis to improve job satisfaction.

[0416] "Data communication means" refers to a method or technology for transferring information data between a server and a user device.

[0417] "Information data" refers to all data generated in the course of business operations, including emails and chat messages related to employees' work, and data on workload.

[0418] "Emotional state" refers to emotional states such as positive, negative, and neutral, derived from text analyzed using natural language processing technology.

[0419] "Activity satisfaction" is an indicator of employee satisfaction with their work, and is predicted based on emotional states and work-related information.

[0420] "Feedback" refers to advice and improvement suggestions provided to employees based on their predicted level of satisfaction with their activities.

[0421] A "generative AI model" is a machine learning model that helps analyze data and provide insights, and is used to infer employee sentiment and generate feedback.

[0422] This invention provides a system for efficiently analyzing and predicting employees' emotional states and activity satisfaction during their work. This system mainly consists of a server and multiple terminals.

[0423] The server is responsible for acquiring information data from each terminal using data communication methods. This information data includes emails and chat messages used by employees for work. By having the server regularly receive this information data, it is possible to accurately reflect the work situation.

[0424] The server utilizes natural language processing and machine learning technologies in analyzing information data. Specifically, a generative AI model infers emotional states from text data. This model assigns emotional labels such as positive, negative, and neutral to the information data. For example, the message "I'm glad this project was completed successfully" is analyzed as having a positive emotion.

[0425] Next, the server predicts activity satisfaction based on the inferred emotional state. Here, past work data and emotional patterns are combined and evaluated using statistical modeling and machine learning. Through this analysis, the server generates specific feedback that contributes to improving organizational productivity.

[0426] The generated feedback is sent to the employee's device. Based on this feedback, the user can identify areas for improvement in their work and take appropriate action.

[0427] As a concrete example, consider a case where a user frequently exhibits negative emotions during work. The server, based on this pattern, infers that the user is in a high-load work environment and provides specific feedback such as, "Please consider adjusting your workload and managing your stress."

[0428] An example of a prompt used as input to the generative AI model is: "Analyze the user's email and chat history, identify the correlation between the frequency of negative emotions and activity satisfaction, and provide specific advice for improvement."

[0429] Thus, the system of the present invention achieves improved employee satisfaction and increased efficiency throughout the organization.

[0430] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0431] Step 1:

[0432] The server periodically receives information data from each terminal using data communication methods. This information data includes emails and chat messages. The input consists of business communication data sent from each terminal, which is output and stored on the server.

[0433] Step 2:

[0434] The server analyzes the received information data using natural language processing (NLP) techniques. This analysis uses a generative AI model to infer emotional states from text. The input is the information data acquired in step 1, and the server uses this to classify the emotions in the data as positive, negative, or neutral, and outputs the data with emotional labels.

[0435] Step 3:

[0436] The server predicts activity satisfaction based on informational data with emotion labels. This step also takes into account past data and emotion patterns. The input consists of emotion-labeled data and historical work data, which the server analyzes using a machine learning model to output a predicted activity satisfaction level.

[0437] Step 4:

[0438] The server generates feedback based on the predicted activity satisfaction. This feedback includes specific suggestions, such as individual advice and suggestions for improvement. The input is the activity satisfaction prediction result from step 3, and the server creates the feedback based on it and outputs it as a text message.

[0439] Step 5:

[0440] The server sends the generated feedback to each employee's terminal. The input is the feedback created in step 4, which the server forwards to the user's terminal and outputs in a format that the user can review and utilize.

[0441] (Application Example 1)

[0442] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0443] In today's workplace, it is essential to understand employees' emotional states and job satisfaction in real time and provide appropriate feedback. However, traditional methods make it difficult to accurately grasp individual emotional states, and in particular, they fail to provide prompt support to employees whose mental health deteriorates due to workload. Therefore, there is a need for a system that monitors emotional states and provides improvement suggestions in real time in the real world.

[0444] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0445] In this invention, the server includes means for collecting multiple pieces of work information using information transmission technology, means for analyzing the collected work information to infer the emotional state, means for predicting work satisfaction based on the inferred emotional state and related work-related information, and means for presenting the created improvement proposals on a visual display device. This makes it possible to monitor the emotional state of employees in real time and provide feedback.

[0446] "Information transmission technology" refers to methods for efficiently sending and receiving information and data between multiple devices.

[0447] "Business information" refers to all information, including data and messages related to employees' work activities.

[0448] "Emotional status" is an indicator that shows an employee's current emotional response or state.

[0449] "Business-related information" refers to background information necessary for carrying out business operations and data associated with business processes.

[0450] "Job satisfaction" is an indicator that shows the level of satisfaction and fulfillment employees feel when performing their work.

[0451] "Improvement suggestions" refer to proposals aimed at improving work efficiency or emotional state, based on the detected situation.

[0452] An "information processing terminal" refers to a digital device used by users to receive and process information.

[0453] A "visual display device" refers to a hardware device used to present information to users visually.

[0454] The system implementing this invention has the function of providing real-time feedback by collecting employee work information, inferring their emotional state, and predicting their job satisfaction. The server collects work information from information processing terminals used by employees using information transmission technology. The collected information includes message information and workload information. The server utilizes natural language processing to analyze this data and infer the emotional state.

[0455] The server integrates analyzed emotional states with related work-related information and uses a machine learning model to predict work satisfaction. This model can utilize frameworks such as TensorFlow and PyTorch. Based on the predicted work satisfaction, the server generates improvement suggestions and presents them to the user in real time through smart glasses, which act as a visual display device.

[0456] For example, if an employee exhibits a high stress level during work and this is analyzed as a negative emotion, the server visually displays a suggestion to "take a deep breath and relax" on the employee's glasses. Because the user receives this suggestion in real time, they can immediately implement stress reduction measures.

[0457] Examples of prompt statements include the following:

[0458] Based on the following text data, predict the emotional state: "I'm a little tired today, but I managed to finish work."

[0459] By using this prompt, the generative AI model can appropriately analyze the emotional state and provide accurate feedback to the user.

[0460] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0461] Step 1:

[0462] The server collects business information from information processing terminals used by employees. This business information includes message information and workload information. It receives text data sent from the terminals as input and stores it in the database.

[0463] Step 2:

[0464] The server analyzes the collected business information. This analysis uses natural language processing algorithms to infer emotional states from text data. The stored text data is used as input, and emotional labels (positive, negative, neutral) are assigned using NLP techniques. The analysis results are then sent to a generating AI model as output.

[0465] Step 3:

[0466] The server integrates emotional states and related information, and uses a machine learning model to predict job satisfaction. The input uses the inferred emotional data and related job information described above. Statistical modeling is applied to obtain the predicted job satisfaction as output.

[0467] Step 4:

[0468] The server generates improvement suggestions based on predicted employee satisfaction. Using the prediction results as input, a generative AI model is applied to generate suggestion texts, outputting specific advice in text format.

[0469] Step 5:

[0470] The server sends the generated improvement suggestions to an information processing terminal and instructs it to display them on a visual display device. The terminal then outputs the suggestions received from the server as a notification to the user's smart glasses, presenting them visually. This system allows the user to receive improvement suggestions in real time.

[0471] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0472] This invention is a system that analyzes business data collected via data communication means, infers the user's emotional state, predicts job satisfaction based on that inference, and provides feedback to the user. In particular, by combining it with an emotion engine, it becomes possible to recognize the user's emotions more accurately and in real time.

[0473] The system primarily consists of servers, with an emotion engine integrated into them. The servers collect various business data from user terminals via the network. This includes email and chat message data, workload data, and visual and audio data captured by cameras and microphones operating on the terminals. Based on this data, the emotion engine analyzes the user's current emotions. Because real-time emotion recognition is possible, it offers the advantage of consistently providing up-to-date information.

[0474] The server receives the analysis results from the emotion engine and uses natural language processing algorithms and machine learning models to predict job satisfaction. This prediction is based on the user's past work history and emotional tendencies, and a customized model is used for each individual user.

[0475] Next, the server generates specific feedback to provide to the user based on the predicted job satisfaction. This feedback includes suggestions for improvement tailored to the user's emotional state and advice aimed at conditioning their work, and is sent to the user's terminal.

[0476] For example, if User B frequently smiles during work-related communication, the server detects this in real time through its emotion engine. Once a positive emotional state is detected, the server analyzes the contributing factors and identifies elements that improve satisfaction. As a result, User B receives specific feedback on how to apply these positive factors to other tasks.

[0477] Through the system described above, users will be able to deepen their understanding of their own emotions and work, and make more effective improvements to their work processes.

[0478] The following describes the processing flow.

[0479] Step 1:

[0480] The server collects work data from the user's terminal. The terminal is configured to transfer message data and workload data to the server, and this also includes visual and audio data acquired from the camera and microphone.

[0481] Step 2:

[0482] The server filters the collected data from a personal information protection standpoint and prepares it in a format necessary for analysis. This process includes data cleaning and format conversion.

[0483] Step 3:

[0484] The server activates an emotion engine, performing facial expression analysis from visual data and tone analysis from audio data to analyze the user's emotional state in real time. This allows the user's mental tendencies to be understood.

[0485] Step 4:

[0486] The server uses natural language processing to analyze message data and identify the emotions expressed in the text. This allows it to infer the user's overall emotional state from their communication content, facial expressions, and voice.

[0487] Step 5:

[0488] The server uses emotional information provided by the emotion engine, along with the user's past work data and work history, to predict integrated job satisfaction. Machine learning models are used for this prediction.

[0489] Step 6:

[0490] The server generates personalized feedback for users based on their predicted job satisfaction. This feedback includes advice to stabilize emotions and specific suggestions for improving work performance.

[0491] Step 7:

[0492] The server sends the generated feedback to the user's device. Users can review this feedback and implement the recommended improvements to enhance their work efficiency and satisfaction.

[0493] (Example 2)

[0494] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0495] In today's work environment, workplace stress and satisfaction often directly impact individual productivity. However, many current systems struggle to assess individual employees' emotions and psychological states in real time and provide corresponding feedback. Furthermore, predicting job satisfaction based on employees' emotional states and suggesting improvement measures is not sufficiently automated. As a result, improving workplace satisfaction and effective work processes are hindered.

[0496] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0497] In this invention, the server includes means for collecting business data using data communication means, means for analyzing data including visual and auditory information from the collected data to estimate emotional states in real time, and means for predicting individually customized job satisfaction using a generative model. This makes it possible to predict job satisfaction in real time based on the user's emotional state and propose improvement measures.

[0498] "Data communication means" refers to technologies or devices for sending and receiving data between multiple devices, and plays a role in collecting business data via a network.

[0499] "Business data" refers to all information related to activities conducted within an organization, including message data, workload data, visual information, and audio information.

[0500] "Visual information" refers to video data acquired using devices such as cameras, and is used to analyze the user's facial expressions and actions.

[0501] "Audio information" refers to sound data acquired using devices such as microphones, and is used to analyze the user's tone and emotional state.

[0502] "Means for inferring emotional states" refers to technologies or devices that use natural language processing algorithms or speech recognition technologies to analyze emotions from a user's utterances or voice and determine their emotional state.

[0503] A "generative model" is a mathematical or computational structure that uses historical data and other factors to make specific predictions or generate data based on machine learning algorithms.

[0504] "Natural language generation technology" is a technology that uses machines to generate text based on natural language, and is used to provide feedback in a format that users can understand.

[0505] "Means of generating feedback" refers to technologies or devices for generating information or suggestions to provide to a user based on their emotional state or predicted job satisfaction.

[0506] This invention is a system that analyzes a user's emotional state in their work environment in real time, uses the results to predict their job satisfaction, and provides the user with specific feedback.

[0507] The user terminal uses a camera and microphone to collect visual and auditory information, such as the user's facial expressions and voice. Furthermore, it transmits message data via email and chat, as well as workload data, to the server via data communication.

[0508] The server receives multiple business data sets and performs real-time sentiment analysis using an integrated sentiment engine. This sentiment engine uses natural language processing algorithms and speech recognition technology to infer emotions from the user's speech content and tone of voice.

[0509] Based on the analyzed sentiment data and accumulated work information, the server uses a machine learning-based generative model to predict individually customized job satisfaction levels.

[0510] Next, the server uses natural language generation technology to generate feedback that includes specific improvement suggestions and advice regarding the predicted satisfaction level, and sends it to the user terminal via the network. The user terminal displays this feedback to the user, supporting effective business improvement.

[0511] For example, if a user is smiling frequently during work, the server analyzes the video data from the camera in real time to confirm a positive emotional state. Based on this, the server identifies the cause and generates feedback such as, "Let's try applying this positive attitude you've shown in your recent work to other projects."

[0512] Examples of prompts for the generative AI model include, "Please create a report summarizing the user's current emotional state and its impact." In this way, users can understand how their emotions and behaviors affect their work and use this information to make improvements.

[0513] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0514] Step 1:

[0515] The user terminal collects information from the user's email, chat, camera, microphone, etc. Input data includes text message data, visual information, and audio information. The terminal transmits this data to the server via the network. As a preprocessing step, the data is formatted into the required format.

[0516] Step 2:

[0517] The server receives business data sent from the terminal. Input data includes formatted text, visual data, and audio data. The server feeds this into its emotion engine, applying natural language processing algorithms and speech recognition technologies to infer the emotional state. The output is data representing the user's real-time emotional state.

[0518] Step 3:

[0519] The server uses the output data from the emotion engine to feed into a generative AI model. The input data includes emotional states and work history. Based on this, the server applies a machine learning algorithm to predict the user's job satisfaction. The output is numerical data indicating the predicted job satisfaction.

[0520] Step 4:

[0521] The server uses natural language generation technology to generate feedback based on predicted job satisfaction and emotional state data. Input data includes satisfaction scores and emotional data to derive specific suggestions. Output is a text message containing specific advice for the user.

[0522] Step 5:

[0523] The server sends the generated feedback to the user's terminal via the network. The terminal receives this feedback and presents it to the user. This allows the user to learn about specific improvement suggestions based on their emotional state and job satisfaction.

[0524] (Application Example 2)

[0525] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0526] In conventional store operations, it has been difficult to grasp employees' emotional states in real time and provide appropriate feedback based on that information. This could negatively impact service quality and employee satisfaction. This invention aims to improve customer service and employee satisfaction by efficiently analyzing employees' emotions during work and providing appropriate feedback.

[0527] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0528] In this invention, the server includes means for collecting multiple activity data using data communication technology, means for analyzing the collected activity data to infer the emotional state, means for predicting satisfaction based on the inferred emotional state and related activity information, and means for recognizing the emotional state in real time using acquired visual and audio data to support customer service operations. This makes it possible to instantly grasp the emotional state of employees and provide appropriate feedback.

[0529] "Data communication technology" refers to the technology used to send and receive data between information processing devices.

[0530] "Activity data" refers to all information generated during work, including workload and communication content.

[0531] "Emotional state" refers to the user's psychological reactions and emotions.

[0532] "Satisfaction level" refers to the sense of fulfillment and accomplishment that users feel towards their work.

[0533] "Visual and audio data" refers to image data and audio information acquired through cameras and microphones.

[0534] "Real-time recognition" refers to the process of immediately analyzing the content of acquired information and obtaining results.

[0535] "Customer service" refers to the work of providing goods and services to customers in a store.

[0536] "Feedback" refers to information and advice provided to users, with the aim of improving operations and increasing user satisfaction.

[0537] This invention is implemented in a system that recognizes the emotional state of employees in a store in real time and provides appropriate feedback. The system includes a server and information processing devices such as smart glasses. The server collects activity data from these information processing devices using data communication technology. This includes visual and audio data, acquired using the cameras and microphones of the smart glasses.

[0538] The collected data is sent to an emotion engine running on the server. This emotion engine analyzes visual and audio data and uses machine learning algorithms to infer the emotional state of employees. Specifically, advanced emotion recognition is possible by using Python, TensorFlow, and OpenCV. In this process, positive facial expressions such as smiles are detected from the collected visual data, and the tone of voice is analyzed from the audio data to determine whether the current emotion is "positive."

[0539] The server also uses the inferred emotional state to predict the employee's satisfaction level. Based on this predicted satisfaction level, the server generates feedback and sends it to the information processing unit. This allows employees to receive appropriate feedback tailored to their emotions, which can help them improve their work and increase their satisfaction. For example, a POS system screen might display advice such as, "Keep up the good work."

[0540] An example of a prompt would be, "If the employee's current mood is positive, please provide feedback on how they can maintain that mood."

[0541] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0542] Step 1:

[0543] The device collects visual and audio data using the smart glasses' camera and microphone. The device verifies that the visual data includes features such as facial expressions, and the audio data includes features such as voice tone. This data is transmitted to the server in real time.

[0544] Step 2:

[0545] The server inputs the received visual and audio data into the emotion engine. The emotion engine uses a machine learning algorithm to infer the emotional state based on the received data. As part of the data processing, it analyzes whether or not there is a smile from the visual data and the tone of voice from the audio data. As output, it generates the inferred emotional state (e.g., "positive").

[0546] Step 3:

[0547] The server predicts satisfaction levels based on emotional states and related work information. It uses natural language processing algorithms and generative AI models to compute data from previously outputted emotional states and past work history to obtain predicted satisfaction levels (e.g., "high satisfaction").

[0548] Step 4:

[0549] The server generates feedback using prompts via a generative AI model, based on the predicted satisfaction level. It takes satisfaction level and emotional state as input and outputs feedback such as "Keep up the good work."

[0550] Step 5:

[0551] The server sends the generated feedback to the terminal. The terminal then presents this feedback to the user via the information processing device's display and audio. This allows the user to utilize real-time emotional feedback in their work.

[0552] 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.

[0553] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0554] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0555] [Fourth Embodiment]

[0556] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0557] 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.

[0558] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0559] 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.

[0560] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0561] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0562] 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.

[0563] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0564] 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.

[0565] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0566] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0567] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0568] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0569] This invention provides a system that effectively analyzes and predicts employees' emotional states and job satisfaction based on their work data. The following describes embodiments of this system.

[0570] This system is primarily composed of servers, which are connected to multiple terminals via a network. The servers collect business data from employee terminals using data communication methods. This business data includes emails and chat messages sent and received during business communication, which are periodically transferred to the server.

[0571] The server analyzes the collected message data to infer the emotional state of employees. This process employs algorithms that use natural language processing (NLP) and machine learning models to identify emotions within the text. Specifically, emotional labels such as positive, negative, and neutral are automatically assigned.

[0572] Next, the server combines customer emotional states with work information to predict job satisfaction. This prediction is made using statistical modeling or machine learning models, taking into account past data and work patterns.

[0573] Based on predicted job satisfaction, the server generates feedback for employees. This feedback includes specific advice for improving their mood and suggestions for increasing work efficiency. The generated feedback is sent to the customer's terminal, allowing the user to use it to improve their own work.

[0574] For example, if user A frequently expresses negative emotions in their daily work, the server analyzes this information and performs further analysis. If the prediction phase determines that user A is under a high workload, it provides specific advice as feedback, such as "review your workload and take measures to manage stress." In this way, the system contributes to improving employee satisfaction and corporate productivity.

[0575] The following describes the processing flow.

[0576] Step 1:

[0577] The server automatically collects work data from employee terminals via the network. This data includes emails and chat messages, and text information related to work activities is continuously accumulated.

[0578] Step 2:

[0579] The server preprocesses the collected data, removing personal and confidential information. Additionally, text data is formatted and converted into a state suitable for analysis.

[0580] Step 3:

[0581] The server uses natural language processing techniques to analyze sentiment from pre-processed text data. Specifically, it performs word vectorization and tokenization, and assigns sentiment labels such as positive, negative, and neutral to each text.

[0582] Step 4:

[0583] Based on the analysis results, the server aggregates and analyzes each employee's emotional state and integrates it with related data such as job content and workload.

[0584] Step 5:

[0585] The server uses integrated data as input to predict employee job satisfaction using statistical models and machine learning algorithms. The predictive models also take into account comparisons with historical data and trend analysis.

[0586] Step 6:

[0587] The server generates personalized feedback for each employee based on their predicted job satisfaction results. This feedback includes specific advice for improving their mood.

[0588] Step 7:

[0589] The server sends the generated feedback to the employee's device. Users can then review it and take action to improve their work processes or manage their emotions.

[0590] (Example 1)

[0591] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0592] In today's work environment, accurately understanding employees' emotional states and how those states affect job satisfaction is challenging. Providing accurate feedback based on this understanding is crucial for improving employee motivation and work efficiency. Traditional methods have failed to adequately analyze the relationship between emotional states and work performance, making it difficult for improvement suggestions to yield tangible results. Therefore, a new approach is needed to address this challenge.

[0593] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0594] In this invention, the server includes means for acquiring multiple pieces of information data using data communication means, means for analyzing the acquired information data to infer an emotional state, and means for predicting activity satisfaction based on the inferred emotional state and related information. This makes it possible to accurately analyze the emotional state of employees and provide feedback based on that analysis to improve job satisfaction.

[0595] "Data communication means" refers to a method or technology for transferring information data between a server and a user device.

[0596] "Information data" refers to all data generated in the course of business operations, including emails and chat messages related to employees' work, and data on workload.

[0597] "Emotional state" refers to emotional states such as positive, negative, and neutral, derived from text analyzed using natural language processing technology.

[0598] "Activity satisfaction" is an indicator of employee satisfaction with their work, and is predicted based on emotional states and work-related information.

[0599] "Feedback" refers to advice and improvement suggestions provided to employees based on their predicted level of satisfaction with their activities.

[0600] A "generative AI model" is a machine learning model that helps analyze data and provide insights, and is used to infer employee sentiment and generate feedback.

[0601] This invention provides a system for efficiently analyzing and predicting employees' emotional states and activity satisfaction during their work. This system mainly consists of a server and multiple terminals.

[0602] The server is responsible for acquiring information data from each terminal using data communication methods. This information data includes emails and chat messages used by employees for work. By having the server regularly receive this information data, it is possible to accurately reflect the work situation.

[0603] The server utilizes natural language processing and machine learning technologies in analyzing information data. Specifically, a generative AI model infers emotional states from text data. This model assigns emotional labels such as positive, negative, and neutral to the information data. For example, the message "I'm glad this project was completed successfully" is analyzed as having a positive emotion.

[0604] Next, the server predicts activity satisfaction based on the inferred emotional state. Here, past work data and emotional patterns are combined and evaluated using statistical modeling and machine learning. Through this analysis, the server generates specific feedback that contributes to improving organizational productivity.

[0605] The generated feedback is sent to the employee's device. Based on this feedback, the user can identify areas for improvement in their work and take appropriate action.

[0606] As a concrete example, consider a case where a user frequently exhibits negative emotions during work. The server, based on this pattern, infers that the user is in a high-load work environment and provides specific feedback such as, "Please consider adjusting your workload and managing your stress."

[0607] An example of a prompt used as input to the generative AI model is: "Analyze the user's email and chat history, identify the correlation between the frequency of negative emotions and activity satisfaction, and provide specific advice for improvement."

[0608] Thus, the system of the present invention achieves improved employee satisfaction and increased efficiency throughout the organization.

[0609] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0610] Step 1:

[0611] The server periodically receives information data from each terminal using data communication methods. This information data includes emails and chat messages. The input consists of business communication data sent from each terminal, which is output and stored on the server.

[0612] Step 2:

[0613] The server analyzes the received information data using natural language processing (NLP) techniques. This analysis uses a generative AI model to infer emotional states from text. The input is the information data acquired in step 1, and the server uses this to classify the emotions in the data as positive, negative, or neutral, and outputs the data with emotional labels.

[0614] Step 3:

[0615] The server predicts activity satisfaction based on informational data with emotion labels. This step also takes into account past data and emotion patterns. The input consists of emotion-labeled data and historical work data, which the server analyzes using a machine learning model to output a predicted activity satisfaction level.

[0616] Step 4:

[0617] The server generates feedback based on the predicted activity satisfaction. This feedback includes specific suggestions, such as individual advice and suggestions for improvement. The input is the activity satisfaction prediction result from step 3, and the server creates the feedback based on it and outputs it as a text message.

[0618] Step 5:

[0619] The server sends the generated feedback to each employee's terminal. The input is the feedback created in step 4, which the server forwards to the user's terminal and outputs in a format that the user can review and utilize.

[0620] (Application Example 1)

[0621] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0622] In today's workplace, it is essential to understand employees' emotional states and job satisfaction in real time and provide appropriate feedback. However, traditional methods make it difficult to accurately grasp individual emotional states, and in particular, they fail to provide prompt support to employees whose mental health deteriorates due to workload. Therefore, there is a need for a system that monitors emotional states and provides improvement suggestions in real time in the real world.

[0623] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0624] In this invention, the server includes means for collecting multiple pieces of work information using information transmission technology, means for analyzing the collected work information to infer the emotional state, means for predicting work satisfaction based on the inferred emotional state and related work-related information, and means for presenting the created improvement proposals on a visual display device. This makes it possible to monitor the emotional state of employees in real time and provide feedback.

[0625] "Information transmission technology" refers to methods for efficiently sending and receiving information and data between multiple devices.

[0626] "Business information" refers to all information, including data and messages related to employees' work activities.

[0627] "Emotional status" is an indicator that shows an employee's current emotional response or state.

[0628] "Business-related information" refers to background information necessary for carrying out business operations and data associated with business processes.

[0629] "Job satisfaction" is an indicator that shows the level of satisfaction and fulfillment employees feel when performing their work.

[0630] "Improvement suggestions" refer to proposals aimed at improving work efficiency or emotional state, based on the detected situation.

[0631] An "information processing terminal" refers to a digital device used by users to receive and process information.

[0632] A "visual display device" refers to a hardware device used to present information to users visually.

[0633] The system implementing this invention has the function of providing real-time feedback by collecting employee work information, inferring their emotional state, and predicting their job satisfaction. The server collects work information from information processing terminals used by employees using information transmission technology. The collected information includes message information and workload information. The server utilizes natural language processing to analyze this data and infer the emotional state.

[0634] The server integrates analyzed emotional states with related work-related information and uses a machine learning model to predict work satisfaction. This model can utilize frameworks such as TensorFlow and PyTorch. Based on the predicted work satisfaction, the server generates improvement suggestions and presents them to the user in real time through smart glasses, which act as a visual display device.

[0635] For example, if an employee exhibits a high stress level during work and this is analyzed as a negative emotion, the server visually displays a suggestion to "take a deep breath and relax" on the employee's glasses. Because the user receives this suggestion in real time, they can immediately implement stress reduction measures.

[0636] Examples of prompt statements include the following:

[0637] Based on the following text data, predict the emotional state: "I'm a little tired today, but I managed to finish work."

[0638] By using this prompt, the generative AI model can appropriately analyze the emotional state and provide accurate feedback to the user.

[0639] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0640] Step 1:

[0641] The server collects business information from information processing terminals used by employees. This business information includes message information and workload information. It receives text data sent from the terminals as input and stores it in the database.

[0642] Step 2:

[0643] The server analyzes the collected business information. This analysis uses natural language processing algorithms to infer emotional states from text data. The stored text data is used as input, and emotional labels (positive, negative, neutral) are assigned using NLP techniques. The analysis results are then sent to a generating AI model as output.

[0644] Step 3:

[0645] The server integrates emotional states and related information, and uses a machine learning model to predict job satisfaction. The input uses the inferred emotional data and related job information described above. Statistical modeling is applied to obtain the predicted job satisfaction as output.

[0646] Step 4:

[0647] The server generates improvement suggestions based on predicted employee satisfaction. Using the prediction results as input, a generative AI model is applied to generate suggestion texts, outputting specific advice in text format.

[0648] Step 5:

[0649] The server sends the generated improvement suggestions to an information processing terminal and instructs it to display them on a visual display device. The terminal then outputs the suggestions received from the server as a notification to the user's smart glasses, presenting them visually. This system allows the user to receive improvement suggestions in real time.

[0650] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0651] This invention is a system that analyzes business data collected via data communication means, infers the user's emotional state, predicts job satisfaction based on that inference, and provides feedback to the user. In particular, by combining it with an emotion engine, it becomes possible to recognize the user's emotions more accurately and in real time.

[0652] The system primarily consists of servers, with an emotion engine integrated into them. The servers collect various business data from user terminals via the network. This includes email and chat message data, workload data, and visual and audio data captured by cameras and microphones operating on the terminals. Based on this data, the emotion engine analyzes the user's current emotions. Because real-time emotion recognition is possible, it offers the advantage of consistently providing up-to-date information.

[0653] The server receives the analysis results from the emotion engine and uses natural language processing algorithms and machine learning models to predict job satisfaction. This prediction is based on the user's past work history and emotional tendencies, and a customized model is used for each individual user.

[0654] Next, the server generates specific feedback to provide to the user based on the predicted job satisfaction. This feedback includes suggestions for improvement tailored to the user's emotional state and advice aimed at conditioning their work, and is sent to the user's terminal.

[0655] For example, if User B frequently smiles during work-related communication, the server detects this in real time through its emotion engine. Once a positive emotional state is detected, the server analyzes the contributing factors and identifies elements that improve satisfaction. As a result, User B receives specific feedback on how to apply these positive factors to other tasks.

[0656] Through the system described above, users will be able to deepen their understanding of their own emotions and work, and make more effective improvements to their work processes.

[0657] The following describes the processing flow.

[0658] Step 1:

[0659] The server collects work data from the user's terminal. The terminal is configured to transfer message data and workload data to the server, and this also includes visual and audio data acquired from the camera and microphone.

[0660] Step 2:

[0661] The server filters the collected data from a personal information protection standpoint and prepares it in a format necessary for analysis. This process includes data cleaning and format conversion.

[0662] Step 3:

[0663] The server activates an emotion engine, performing facial expression analysis from visual data and tone analysis from audio data to analyze the user's emotional state in real time. This allows the user's mental tendencies to be understood.

[0664] Step 4:

[0665] The server uses natural language processing to analyze message data and identify the emotions expressed in the text. This allows it to infer the user's overall emotional state from their communication content, facial expressions, and voice.

[0666] Step 5:

[0667] The server uses emotional information provided by the emotion engine, along with the user's past work data and work history, to predict integrated job satisfaction. Machine learning models are used for this prediction.

[0668] Step 6:

[0669] The server generates personalized feedback for users based on their predicted job satisfaction. This feedback includes advice to stabilize emotions and specific suggestions for improving work performance.

[0670] Step 7:

[0671] The server sends the generated feedback to the user's device. Users can review this feedback and implement the recommended improvements to enhance their work efficiency and satisfaction.

[0672] (Example 2)

[0673] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0674] In today's work environment, workplace stress and satisfaction often directly impact individual productivity. However, many current systems struggle to assess individual employees' emotions and psychological states in real time and provide corresponding feedback. Furthermore, predicting job satisfaction based on employees' emotional states and suggesting improvement measures is not sufficiently automated. As a result, improving workplace satisfaction and effective work processes are hindered.

[0675] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0676] In this invention, the server includes means for collecting business data using data communication means, means for analyzing data including visual and auditory information from the collected data to estimate emotional states in real time, and means for predicting individually customized job satisfaction using a generative model. This makes it possible to predict job satisfaction in real time based on the user's emotional state and propose improvement measures.

[0677] "Data communication means" refers to technologies or devices for sending and receiving data between multiple devices, and plays a role in collecting business data via a network.

[0678] "Business data" refers to all information related to activities conducted within an organization, including message data, workload data, visual information, and audio information.

[0679] "Visual information" refers to video data acquired using devices such as cameras, and is used to analyze the user's facial expressions and actions.

[0680] "Audio information" refers to sound data acquired using devices such as microphones, and is used to analyze the user's tone and emotional state.

[0681] "Means for inferring emotional states" refers to technologies or devices that use natural language processing algorithms or speech recognition technologies to analyze emotions from a user's utterances or voice and determine their emotional state.

[0682] A "generative model" is a mathematical or computational structure that uses historical data and other factors to make specific predictions or generate data based on machine learning algorithms.

[0683] "Natural language generation technology" is a technology that uses machines to generate text based on natural language, and is used to provide feedback in a format that users can understand.

[0684] "Means of generating feedback" refers to technologies or devices for generating information or suggestions to provide to a user based on their emotional state or predicted job satisfaction.

[0685] This invention is a system that analyzes a user's emotional state in their work environment in real time, uses the results to predict their job satisfaction, and provides the user with specific feedback.

[0686] The user terminal uses a camera and microphone to collect visual and auditory information, such as the user's facial expressions and voice. Furthermore, it transmits message data via email and chat, as well as workload data, to the server via data communication.

[0687] The server receives multiple business data sets and performs real-time sentiment analysis using an integrated sentiment engine. This sentiment engine uses natural language processing algorithms and speech recognition technology to infer emotions from the user's speech content and tone of voice.

[0688] Based on the analyzed sentiment data and accumulated work information, the server uses a machine learning-based generative model to predict individually customized job satisfaction levels.

[0689] Next, the server uses natural language generation technology to generate feedback that includes specific improvement suggestions and advice regarding the predicted satisfaction level, and sends it to the user terminal via the network. The user terminal displays this feedback to the user, supporting effective business improvement.

[0690] For example, if a user is smiling frequently during work, the server analyzes the video data from the camera in real time to confirm a positive emotional state. Based on this, the server identifies the cause and generates feedback such as, "Let's try applying this positive attitude you've shown in your recent work to other projects."

[0691] Examples of prompts for the generative AI model include, "Please create a report summarizing the user's current emotional state and its impact." In this way, users can understand how their emotions and behaviors affect their work and use this information to make improvements.

[0692] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0693] Step 1:

[0694] The user terminal collects information from the user's email, chat, camera, microphone, etc. Input data includes text message data, visual information, and audio information. The terminal transmits this data to the server via the network. As a preprocessing step, the data is formatted into the required format.

[0695] Step 2:

[0696] The server receives business data sent from the terminal. Input data includes formatted text, visual data, and audio data. The server feeds this into its emotion engine, applying natural language processing algorithms and speech recognition technologies to infer the emotional state. The output is data representing the user's real-time emotional state.

[0697] Step 3:

[0698] The server uses the output data from the emotion engine to feed into a generative AI model. The input data includes emotional states and work history. Based on this, the server applies a machine learning algorithm to predict the user's job satisfaction. The output is numerical data indicating the predicted job satisfaction.

[0699] Step 4:

[0700] The server uses natural language generation technology to generate feedback based on predicted job satisfaction and emotional state data. Input data includes satisfaction scores and emotional data to derive specific suggestions. Output is a text message containing specific advice for the user.

[0701] Step 5:

[0702] The server sends the generated feedback to the user's terminal via the network. The terminal receives this feedback and presents it to the user. This allows the user to learn about specific improvement suggestions based on their emotional state and job satisfaction.

[0703] (Application Example 2)

[0704] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0705] In conventional store operations, it has been difficult to grasp employees' emotional states in real time and provide appropriate feedback based on that information. This could negatively impact service quality and employee satisfaction. This invention aims to improve customer service and employee satisfaction by efficiently analyzing employees' emotions during work and providing appropriate feedback.

[0706] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0707] In this invention, the server includes means for collecting multiple activity data using data communication technology, means for analyzing the collected activity data to infer the emotional state, means for predicting satisfaction based on the inferred emotional state and related activity information, and means for recognizing the emotional state in real time using acquired visual and audio data to support customer service operations. This makes it possible to instantly grasp the emotional state of employees and provide appropriate feedback.

[0708] "Data communication technology" refers to the technology used to send and receive data between information processing devices.

[0709] "Activity data" refers to all information generated during work, including workload and communication content.

[0710] "Emotional state" refers to the user's psychological reactions and emotions.

[0711] "Satisfaction level" refers to the sense of fulfillment and accomplishment that users feel towards their work.

[0712] "Visual and audio data" refers to image data and audio information acquired through cameras and microphones.

[0713] "Real-time recognition" refers to the process of immediately analyzing the content of acquired information and obtaining results.

[0714] "Customer service" refers to the work of providing goods and services to customers in a store.

[0715] "Feedback" refers to information and advice provided to users, with the aim of improving operations and increasing user satisfaction.

[0716] This invention is implemented in a system that recognizes the emotional state of employees in a store in real time and provides appropriate feedback. The system includes a server and information processing devices such as smart glasses. The server collects activity data from these information processing devices using data communication technology. This includes visual and audio data, acquired using the cameras and microphones of the smart glasses.

[0717] The collected data is sent to an emotion engine running on the server. This emotion engine analyzes visual and audio data and uses machine learning algorithms to infer the emotional state of employees. Specifically, advanced emotion recognition is possible by using Python, TensorFlow, and OpenCV. In this process, positive facial expressions such as smiles are detected from the collected visual data, and the tone of voice is analyzed from the audio data to determine whether the current emotion is "positive."

[0718] The server also uses the inferred emotional state to predict the employee's satisfaction level. Based on this predicted satisfaction level, the server generates feedback and sends it to the information processing unit. This allows employees to receive appropriate feedback tailored to their emotions, which can help them improve their work and increase their satisfaction. For example, a POS system screen might display advice such as, "Keep up the good work."

[0719] An example of a prompt would be, "If the employee's current mood is positive, please provide feedback on how they can maintain that mood."

[0720] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0721] Step 1:

[0722] The device collects visual and audio data using the smart glasses' camera and microphone. The device verifies that the visual data includes features such as facial expressions, and the audio data includes features such as voice tone. This data is transmitted to the server in real time.

[0723] Step 2:

[0724] The server inputs the received visual and audio data into the emotion engine. The emotion engine uses a machine learning algorithm to infer the emotional state based on the received data. As part of the data processing, it analyzes whether or not there is a smile from the visual data and the tone of voice from the audio data. As output, it generates the inferred emotional state (e.g., "positive").

[0725] Step 3:

[0726] The server predicts satisfaction levels based on emotional states and related work information. It uses natural language processing algorithms and generative AI models to compute data from previously outputted emotional states and past work history to obtain predicted satisfaction levels (e.g., "high satisfaction").

[0727] Step 4:

[0728] The server generates feedback using prompts via a generative AI model, based on the predicted satisfaction level. It takes satisfaction level and emotional state as input and outputs feedback such as "Keep up the good work."

[0729] Step 5:

[0730] The server sends the generated feedback to the terminal. The terminal then presents this feedback to the user via the information processing device's display and audio. This allows the user to utilize real-time emotional feedback in their work.

[0731] 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.

[0732] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0733] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0734] 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.

[0735] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0736] 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.

[0737] 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.

[0738] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0739] 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."

[0740] 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.

[0741] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0742] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0751] 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.

[0752] The following is further disclosed regarding the embodiments described above.

[0753] (Claim 1)

[0754] A means of collecting multiple business data using data communication means,

[0755] A method for analyzing collected business data to infer emotional states,

[0756] A means of predicting job satisfaction based on inferred emotional states and related work information,

[0757] A means of generating feedback based on predicted job satisfaction,

[0758] A means for transmitting the generated feedback to individual user terminals,

[0759] A system that includes this.

[0760] (Claim 2)

[0761] The system according to claim 1, which uses at least message data and workload data as business data.

[0762] (Claim 3)

[0763] The system according to claim 1, which uses a natural language processing algorithm to infer the state of emotion.

[0764] "Example 1"

[0765] (Claim 1)

[0766] A means for acquiring multiple pieces of information data using data communication means,

[0767] A method for analyzing acquired information data to infer emotional states,

[0768] A means of predicting activity satisfaction based on inferred emotional states and related information,

[0769] A means of generating feedback according to predicted activity satisfaction,

[0770] A means for transferring the generated feedback to individual user devices,

[0771] A system that includes this.

[0772] (Claim 2)

[0773] The system according to claim 1, which uses at least communication data and activity data as information data.

[0774] (Claim 3)

[0775] The system according to claim 1, which uses a generative AI model and a natural language processing algorithm to infer the state of emotion.

[0776] "Application Example 1"

[0777] (Claim 1)

[0778] A means of collecting multiple business information using information transmission technology,

[0779] A method for analyzing collected business information to infer emotional states,

[0780] A means of predicting job satisfaction based on inferred emotional states and related work-related information,

[0781] A means of creating improvement proposals based on predicted job satisfaction,

[0782] A means of transmitting the created improvement proposals to individual information processing terminals,

[0783] A means for displaying improvement suggestions transmitted to an information processing terminal on a visual display device,

[0784] A system that includes this.

[0785] (Claim 2)

[0786] The system according to claim 1, which uses at least message information and workload information as business information.

[0787] (Claim 3)

[0788] The system according to claim 1, which utilizes a natural language processing algorithm to infer the emotional state.

[0789] "Example 2 of combining an emotion engine"

[0790] (Claim 1)

[0791] A means of collecting multiple business data using data communication means,

[0792] A means of analyzing multiple data, including visual and auditory information, from collected business data to predict emotional states in real time,

[0793] A means of predicting individually customized job satisfaction using a generative model based on inferred emotional states and related work information,

[0794] A means of generating feedback using natural language generation technology based on predicted job satisfaction,

[0795] A means of sending and presenting the generated feedback to individual user terminals,

[0796] A system that includes this.

[0797] (Claim 2)

[0798] The system according to claim 1, which uses at least message data, workload data, visual information and audio information as business data.

[0799] (Claim 3)

[0800] The system according to claim 1, which uses natural language processing algorithms and speech recognition techniques to infer emotional states.

[0801] "Application example 2 when combining with an emotional engine"

[0802] (Claim 1)

[0803] A means of collecting multiple activity data using data communication technology,

[0804] A method for analyzing collected activity data to infer emotional states,

[0805] A means of predicting satisfaction based on inferred emotional states and related activity information,

[0806] A means of generating feedback according to the predicted satisfaction level,

[0807] A means for transmitting the generated feedback to individual information processing devices,

[0808] A means of supporting customer service by recognizing emotional states in real time using acquired visual and audio data,

[0809] A system that includes this.

[0810] (Claim 2)

[0811] The system according to claim 1, which uses at least communication data and workload data as information data.

[0812] (Claim 3)

[0813] The system according to claim 1, which uses a language processing algorithm to infer the state of emotion. [Explanation of symbols]

[0814] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting multiple business data using data communication means, A method for analyzing collected business data to infer emotional states, A means of predicting job satisfaction based on inferred emotional states and related work information, A means of generating feedback based on predicted job satisfaction, A means for transmitting the generated feedback to individual user terminals, A system that includes this.

2. The system according to claim 1, which uses at least message data and workload data as business data.

3. The system according to claim 1, which uses a natural language processing algorithm to infer the state of emotion.

Images